From bb8d09dda477ab56f4eccca29dec93435c1380c9 Mon Sep 17 00:00:00 2001 From: TO Date: Tue, 11 Aug 2026 23:34:09 +0200 Subject: [PATCH] Add writing-for-agents skill documentation and related files - Created SKILL.md and SKILL-MECHANICS.md for writing agent skills. - Added openai.yaml for agent interface configuration. - Introduced AGENTS.md for agent skills overview. - Established CONTEXT.md for personal leave planning terminology. - Documented ordered heuristic optimization in ADRs. - Defined personal client-side planner limitations in ADRs. - Created domain documentation for engineering skills. - Added issue tracker guidelines for GitLab. - Mapped triage labels for issue tracking. - Initialized skills-lock.json to manage skill dependencies. --- .agents/skills/ask-matt/PHASE-BOUNDARIES.md | 55 +++++ .agents/skills/ask-matt/SKILL.md | 90 ++++++++ .agents/skills/ask-matt/agents/openai.yaml | 5 + .agents/skills/code-review/SKILL.md | 87 ++++++++ .agents/skills/code-review/agents/openai.yaml | 3 + .agents/skills/codebase-design/DEEPENING.md | 37 ++++ .../skills/codebase-design/DESIGN-IT-TWICE.md | 44 ++++ .agents/skills/codebase-design/SKILL.md | 114 ++++++++++ .../skills/codebase-design/agents/openai.yaml | 3 + .agents/skills/diagnosing-bugs/SKILL.md | 140 ++++++++++++ .../skills/diagnosing-bugs/agents/openai.yaml | 3 + .../scripts/hitl-loop.template.sh | 44 ++++ .agents/skills/domain-modeling/ADR-FORMAT.md | 47 ++++ .../skills/domain-modeling/CONTEXT-FORMAT.md | 60 +++++ .agents/skills/domain-modeling/SKILL.md | 74 +++++++ .../skills/domain-modeling/agents/openai.yaml | 3 + .agents/skills/grill-me/SKILL.md | 7 + .agents/skills/grill-me/agents/openai.yaml | 5 + .agents/skills/grill-with-docs/SKILL.md | 7 + .../skills/grill-with-docs/agents/openai.yaml | 5 + .agents/skills/grilling/SKILL.md | 22 ++ .agents/skills/grilling/agents/openai.yaml | 3 + .agents/skills/handoff/SKILL.md | 16 ++ .agents/skills/handoff/agents/openai.yaml | 5 + .agents/skills/implement/SKILL.md | 15 ++ .agents/skills/implement/agents/openai.yaml | 5 + .../HTML-REPORT.md | 123 +++++++++++ .../improve-codebase-architecture/SKILL.md | 71 ++++++ .../agents/openai.yaml | 5 + .agents/skills/prototype/LOGIC.md | 67 ++++++ .agents/skills/prototype/SKILL.md | 26 +++ .agents/skills/prototype/UI.md | 112 ++++++++++ .agents/skills/prototype/agents/openai.yaml | 3 + .agents/skills/research/SKILL.md | 12 + .agents/skills/research/agents/openai.yaml | 3 + .../skills/resolving-merge-conflicts/SKILL.md | 14 ++ .../agents/openai.yaml | 3 + .../skills/setup-matt-pocock-skills/SKILL.md | 116 ++++++++++ .../agents/openai.yaml | 5 + .../skills/setup-matt-pocock-skills/domain.md | 51 +++++ .../issue-tracker-github.md | 45 ++++ .../issue-tracker-gitlab.md | 46 ++++ .../issue-tracker-local.md | 30 +++ .../setup-matt-pocock-skills/triage-labels.md | 15 ++ .agents/skills/tdd/SKILL.md | 38 ++++ .agents/skills/tdd/agents/openai.yaml | 3 + .agents/skills/tdd/mocking.md | 59 +++++ .agents/skills/tdd/tests.md | 77 +++++++ .agents/skills/teach/GLOSSARY-FORMAT.md | 35 +++ .../skills/teach/LEARNING-RECORD-FORMAT.md | 46 ++++ .agents/skills/teach/MISSION-FORMAT.md | 31 +++ .agents/skills/teach/RESOURCES-FORMAT.md | 32 +++ .agents/skills/teach/SKILL.md | 140 ++++++++++++ .agents/skills/teach/agents/openai.yaml | 5 + .agents/skills/to-questionnaire/SKILL.md | 53 +++++ .../to-questionnaire/agents/openai.yaml | 5 + .agents/skills/to-spec/SKILL.md | 75 +++++++ .agents/skills/to-spec/agents/openai.yaml | 5 + .agents/skills/to-tickets/SKILL.md | 105 +++++++++ .agents/skills/to-tickets/agents/openai.yaml | 5 + .agents/skills/triage/AGENT-BRIEF.md | 207 ++++++++++++++++++ .agents/skills/triage/OUT-OF-SCOPE.md | 105 +++++++++ .agents/skills/triage/SKILL.md | 112 ++++++++++ .agents/skills/triage/agents/openai.yaml | 5 + .agents/skills/wait-what/SKILL.md | 7 + .agents/skills/wait-what/agents/openai.yaml | 5 + .agents/skills/wayfinder/SKILL.md | 128 +++++++++++ .agents/skills/wayfinder/agents/openai.yaml | 5 + .agents/skills/wizard/SKILL.md | 44 ++++ .agents/skills/wizard/agents/openai.yaml | 3 + .agents/skills/wizard/template.sh | 204 +++++++++++++++++ .../writing-for-agents/SKILL-MECHANICS.md | 22 ++ .agents/skills/writing-for-agents/SKILL.md | 81 +++++++ .../writing-for-agents/agents/openai.yaml | 3 + AGENTS.md | 13 ++ CONTEXT.md | 50 +++++ .../0001-ordered-heuristic-optimization.md | 3 + ...02-personal-client-side-planner-for-now.md | 3 + docs/agents/domain.md | 51 +++++ docs/agents/issue-tracker.md | 46 ++++ docs/agents/triage-labels.md | 15 ++ skills-lock.json | 155 +++++++++++++ 82 files changed, 3627 insertions(+) create mode 100644 .agents/skills/ask-matt/PHASE-BOUNDARIES.md create mode 100644 .agents/skills/ask-matt/SKILL.md create mode 100644 .agents/skills/ask-matt/agents/openai.yaml create mode 100644 .agents/skills/code-review/SKILL.md create mode 100644 .agents/skills/code-review/agents/openai.yaml create mode 100644 .agents/skills/codebase-design/DEEPENING.md create mode 100644 .agents/skills/codebase-design/DESIGN-IT-TWICE.md create mode 100644 .agents/skills/codebase-design/SKILL.md create mode 100644 .agents/skills/codebase-design/agents/openai.yaml create mode 100644 .agents/skills/diagnosing-bugs/SKILL.md create mode 100644 .agents/skills/diagnosing-bugs/agents/openai.yaml create mode 100644 .agents/skills/diagnosing-bugs/scripts/hitl-loop.template.sh create mode 100644 .agents/skills/domain-modeling/ADR-FORMAT.md create mode 100644 .agents/skills/domain-modeling/CONTEXT-FORMAT.md create mode 100644 .agents/skills/domain-modeling/SKILL.md create mode 100644 .agents/skills/domain-modeling/agents/openai.yaml create mode 100644 .agents/skills/grill-me/SKILL.md create mode 100644 .agents/skills/grill-me/agents/openai.yaml create mode 100644 .agents/skills/grill-with-docs/SKILL.md create mode 100644 .agents/skills/grill-with-docs/agents/openai.yaml create mode 100644 .agents/skills/grilling/SKILL.md create mode 100644 .agents/skills/grilling/agents/openai.yaml create mode 100644 .agents/skills/handoff/SKILL.md create mode 100644 .agents/skills/handoff/agents/openai.yaml create mode 100644 .agents/skills/implement/SKILL.md create mode 100644 .agents/skills/implement/agents/openai.yaml create mode 100644 .agents/skills/improve-codebase-architecture/HTML-REPORT.md create mode 100644 .agents/skills/improve-codebase-architecture/SKILL.md create mode 100644 .agents/skills/improve-codebase-architecture/agents/openai.yaml create mode 100644 .agents/skills/prototype/LOGIC.md create mode 100644 .agents/skills/prototype/SKILL.md create mode 100644 .agents/skills/prototype/UI.md create mode 100644 .agents/skills/prototype/agents/openai.yaml create mode 100644 .agents/skills/research/SKILL.md create mode 100644 .agents/skills/research/agents/openai.yaml create mode 100644 .agents/skills/resolving-merge-conflicts/SKILL.md create mode 100644 .agents/skills/resolving-merge-conflicts/agents/openai.yaml create mode 100644 .agents/skills/setup-matt-pocock-skills/SKILL.md create mode 100644 .agents/skills/setup-matt-pocock-skills/agents/openai.yaml create mode 100644 .agents/skills/setup-matt-pocock-skills/domain.md create mode 100644 .agents/skills/setup-matt-pocock-skills/issue-tracker-github.md create mode 100644 .agents/skills/setup-matt-pocock-skills/issue-tracker-gitlab.md create mode 100644 .agents/skills/setup-matt-pocock-skills/issue-tracker-local.md create mode 100644 .agents/skills/setup-matt-pocock-skills/triage-labels.md create mode 100644 .agents/skills/tdd/SKILL.md create mode 100644 .agents/skills/tdd/agents/openai.yaml create mode 100644 .agents/skills/tdd/mocking.md create mode 100644 .agents/skills/tdd/tests.md create mode 100644 .agents/skills/teach/GLOSSARY-FORMAT.md create mode 100644 .agents/skills/teach/LEARNING-RECORD-FORMAT.md create mode 100644 .agents/skills/teach/MISSION-FORMAT.md create mode 100644 .agents/skills/teach/RESOURCES-FORMAT.md create mode 100644 .agents/skills/teach/SKILL.md create mode 100644 .agents/skills/teach/agents/openai.yaml create mode 100644 .agents/skills/to-questionnaire/SKILL.md create mode 100644 .agents/skills/to-questionnaire/agents/openai.yaml create mode 100644 .agents/skills/to-spec/SKILL.md create mode 100644 .agents/skills/to-spec/agents/openai.yaml create mode 100644 .agents/skills/to-tickets/SKILL.md create mode 100644 .agents/skills/to-tickets/agents/openai.yaml create mode 100644 .agents/skills/triage/AGENT-BRIEF.md create mode 100644 .agents/skills/triage/OUT-OF-SCOPE.md create mode 100644 .agents/skills/triage/SKILL.md create mode 100644 .agents/skills/triage/agents/openai.yaml create mode 100644 .agents/skills/wait-what/SKILL.md create mode 100644 .agents/skills/wait-what/agents/openai.yaml create mode 100644 .agents/skills/wayfinder/SKILL.md create mode 100644 .agents/skills/wayfinder/agents/openai.yaml create mode 100644 .agents/skills/wizard/SKILL.md create mode 100644 .agents/skills/wizard/agents/openai.yaml create mode 100644 .agents/skills/wizard/template.sh create mode 100644 .agents/skills/writing-for-agents/SKILL-MECHANICS.md create mode 100644 .agents/skills/writing-for-agents/SKILL.md create mode 100644 .agents/skills/writing-for-agents/agents/openai.yaml create mode 100644 AGENTS.md create mode 100644 CONTEXT.md create mode 100644 docs/adr/0001-ordered-heuristic-optimization.md create mode 100644 docs/adr/0002-personal-client-side-planner-for-now.md create mode 100644 docs/agents/domain.md create mode 100644 docs/agents/issue-tracker.md create mode 100644 docs/agents/triage-labels.md create mode 100644 skills-lock.json diff --git a/.agents/skills/ask-matt/PHASE-BOUNDARIES.md b/.agents/skills/ask-matt/PHASE-BOUNDARIES.md new file mode 100644 index 0000000..cb31e6a --- /dev/null +++ b/.agents/skills/ask-matt/PHASE-BOUNDARIES.md @@ -0,0 +1,55 @@ +# Phase boundaries + +A **phase** is a chunk of work inside a session — the grilling, the implementation, the QA. The definition is fuzzy on purpose: a phase ends when you think *"ok, we're done with that"*. + +The **phase boundary** is the gap between two phases, and it is the only place this decision belongs. Mid-phase there is no decision to make — continue, or split the work that's left into subagents. Compacting mid-phase makes the agent lose the thread. + +## The five options + +| Option | What it does | +| ------------ | --------------------------------------------------------------- | +| **Continue** | Stay in the session. No context switch at all. | +| **`/clear`** | Empty the context window and start from nothing. | +| **`/handoff`** | Write a portable markdown file and seed a session anywhere with it. | +| **Subagent** | Send the task to its own context window and get a report back. | +| **`/compact`** | Compress this context and seed a fresh session with the summary. | + +## The tree + +Work top to bottom at the boundary. The first **yes** wins. + +**1. Can you continue in this session?** Two things make the answer yes: the next phase needs this phase as a **primary source**, or you have enough [smart zone](https://www.aihero.dev/ai-coding-dictionary/smart-zone) left (~150k tokens) for the next phase to fit. Grilling → implementation is the standard yes: the implementation wants the reasoning verbatim, not a summary of it. Continue costs nothing and loses nothing, so rule it out before anything else. + +**2. Is the context irrelevant to what comes next?** Is everything in this session — the exploration, the decisions, the dead ends — disposable? If so, **`/clear`**. It is the cheapest move on the board: it takes no time and hands back the whole window. `/clear` also isn't terminal — the old session stays resumable. + +The cost of getting this wrong is one-way. Clear a *relevant* context and you lose the **why** behind what you built, and no amount of reading the diff back gets it returned. + +**3. Do you need to hand off?** `/handoff` is narrow. You need it only when you are: + +- swapping to a **new harness** (Claude → Codex), +- moving to a **new directory** or repo, +- sending the work to a **colleague**, +- or forking a side task you found **mid-phase** without derailing what you're doing. + +That list is the whole clause. What `/handoff` buys is **portability** — a file that travels. If nothing is travelling, you don't need it. + +**4. Can the task be done AFK?** Is it scoped tightly enough to run with you away from the keyboard, no steering? Then send it to a **subagent** and leave this session untouched. Automated review is the standard case: the agent reads the diff and reports, and you aren't needed while it does. + +**5. Otherwise, `/compact`.** Relevant context, same harness, same directory, and you need to stay in the loop — this is where the tree lands, and it lands here often. Pass it an instruction (`/compact we're going to QA this area`) so the summary keeps what the next phase needs. + +`/compact` is the **default, not the first reach**. It sits at the bottom because the four questions above it are all cheaper or more precise. The failure mode when people start here is a fresh session that is confidently wrong about a decision the summary flattened. + +## Primary and secondary sources + +Every move except **Continue** turns a **primary source** into a **secondary source** — the session as it happened, replaced by a summary of it. The trade is always the same shape: + +| Source | Information | Noise | Room to move | +| --------------------------------- | ----------- | ----- | ------------ | +| Primary (Continue) | Full | Lots | Little | +| Secondary (`/compact`, `/handoff`) | Lossy | Less | Lots | + +This is why question 1 comes first. You only pay the lossiness when staying costs more than it saves. + +## These are judgement calls + +The questions are not objective — each has taste in it, and the same boundary can go two ways on two days. The value is in asking them **in order**, at the boundary rather than in the middle of the work. diff --git a/.agents/skills/ask-matt/SKILL.md b/.agents/skills/ask-matt/SKILL.md new file mode 100644 index 0000000..7f3ab78 --- /dev/null +++ b/.agents/skills/ask-matt/SKILL.md @@ -0,0 +1,90 @@ +--- +name: ask-matt +description: Ask which skill or flow fits your situation. A router over the skills in this repo. +disable-model-invocation: true +--- + +# Ask Matt + +You don't remember every skill, so ask. + +A **flow** is a path through the skills. Most paths run along one **main flow**, and two **on-ramps** merge onto it. Everything else is standalone, or a vocabulary layer that runs underneath. + +## The main flow: idea → ship + +The route most work travels. You have an idea and want it built. + +1. **`/grill-with-docs`** — sharpen the idea by interview. Start here whenever you are **working in a working directory**: it's stateful, retaining what it learns in `CONTEXT.md` and ADRs. (No working directory? Use `/grill-me` — see Standalone. Both run the same `/grilling` primitive; `grill-with-docs` is the one that leaves a paper trail, which makes it the better of the two whenever a repo is there to leave it in.) +2. **Branch — can you settle every question in conversation?** If a question needs a runnable answer (state, business logic, a UI you have to see), detour through a prototype, bridged by **`/handoff`** in both directions (a prototype lives in its own directory, which is exactly what `/handoff` is for — see Phase boundaries): + - **`/handoff`** out, then open a fresh session against that file, + - **`/prototype`** to answer the question with throwaway code, + - **`/handoff`** back what you learned, and reference it from the original idea thread. +3. **Branch — is this a multi-session build?** + - **Yes** → **`/to-spec`** (turn the thread into a spec), then **`/to-tickets`** to split it into tracer-bullet tickets, each declaring its **blocking edges**. On a local tracker that's one file per ticket under `.scratch//issues/`, worked blockers-first by hand; on a real tracker the edges become native blocking links, so any ticket whose blockers are done can be grabbed — kick off **`/implement`** per ticket, **`/clear`ing context between each one**. Each ticket is self-contained, so the last one's context is disposable. + - **No** → **`/implement`** right here, in the same context window. + + Either way, **`/implement`** builds each issue by driving **`/tdd`** internally — one red-green slice at a time — then closes out by running **`/code-review`**, a two-axis review (Standards + Spec) of the diff, before committing. Reach for **`/tdd`** on its own when you just want to build a concrete behaviour test-first without a full spec, and **`/code-review`** on its own whenever you want to review a branch or PR against a fixed point. + +### Context hygiene + +Keep steps 1–3 in **one unbroken context window** — don't compact or clear until after `/to-tickets` — so the grilling, spec, and tickets all build on the same thinking. Each `/implement` then starts fresh, working from the ticket. + +The limit on this is the **[smart zone](https://www.aihero.dev/ai-coding-dictionary/smart-zone)**: the window (~150k tokens on state-of-the-art models) within which the model still reasons sharply. If a session approaches it before `/to-tickets`, don't push on degraded — `/compact` at the nearest phase boundary and carry on (see Phase boundaries). + +## On-ramps + +A starting situation that generates work, then merges onto the main flow. + +- **Bugs and requests piling up** → **`/triage`**. It moves issues through triage roles and produces agent-ready issues, which **`/implement`** later picks up. + + Triage is only for issues **you didn't create** — bug reports, incoming feature requests, anything that arrives raw. Tickets that `/to-tickets` produced are already agent-ready, so **don't triage them**. + +- **Something's broken** → **`/diagnosing-bugs`**. For the hard ones: the bug that resists a first glance, the intermittent flake, the regression that crept in between two known-good states. It refuses to theorise until it has a **tight feedback loop** — one command that already goes red on *this* bug — then fixes with a regression test. Its post-mortem hands off to **`/improve-codebase-architecture`** when the real finding is that there's no good seam to lock the bug down. + +- **A huge, foggy effort — a greenfield project or a huge feature build, too big for one session** → **`/wayfinder`**, the most cognitively demanding flow here. When the way from here to the destination isn't visible yet, it charts a **shared map** of **decision tickets** on the issue tracker and resolves them one at a time — producing **decisions, not deliverables** — until the fog is pushed back and the way is clear. Where **`/grill-with-docs`** sharpens an idea you can hold in one session, wayfinder is for the idea you can't — and it's slower and denser, so save it for exactly that, never a well-scoped feature. + + When the map clears, **it hands off, it doesn't build**: merge onto the main flow at **`/to-spec`**, which collapses the map's linked decisions into a buildable plan, then `/to-tickets` and `/implement` as usual. Looping the map straight into `/implement` skips that collapse and throws the linked detail away — go straight to `/implement` only when the effort turned out genuinely small. + +## Codebase health + +Not feature work — upkeep. + +- **`/improve-codebase-architecture`** — run whenever you have a spare moment to keep the codebase good for agents to operate in. It surfaces **deepening opportunities**; picking one _generates an idea_ you can take into the main flow at `/grill-with-docs`. It's the survey that finds the candidates; **`/codebase-design`** (below) is the bench you design the chosen one on. + +## Vocabulary underneath + +Two model-invoked references that run *beneath* the other skills — each the single source of truth for its vocabulary. Reach for them directly when the **words**, not the process, are the problem; or let the skills above pull them in. + +- **`/domain-modeling`** — sharpen the project's *domain* language: challenge a fuzzy term, resolve an overloaded word ("account" doing three jobs), record a hard-to-reverse decision as an ADR. It's the active discipline `/grill-with-docs` drives to keep `CONTEXT.md` a clean glossary. +- **`/codebase-design`** — the deep-module vocabulary (module, interface, depth, seam, adapter, leverage, locality) for designing a module's *shape*: a lot of behaviour behind a small interface at a clean seam. `/tdd` and `/improve-codebase-architecture` both speak it. + +## Phase boundaries + +A **phase** is a chunk of work inside a session — the grilling, the implementation, the QA. At the **boundary** between two of them you have five options, and picking between them is the fuzziest decision in this whole map: + +- **Continue** — stay put. Costs nothing, loses nothing. +- **`/clear`** — empty the window, when nothing here matters to what's next. +- **`/handoff`** — write a portable markdown file. Narrow: only for a **new harness**, a **new directory**, a **colleague**, or forking a side task **mid-phase**. What it buys is portability. +- **Subagent** — send a tightly-scoped task to its own window and get a report back. +- **`/compact`** — compress this context and seed a fresh session with it. The **default**, at the bottom of the tree rather than the first reach. + +Read [PHASE-BOUNDARIES.md](PHASE-BOUNDARIES.md) for the ordered tree — the five questions, the reasoning behind each branch, and why the primary-source cost makes **Continue** the one to rule out first. Make the decision **at** a boundary; mid-phase, continue or split the rest into subagents. + +## Standalone + +Off the main flow entirely. + +- **`/grill-me`** — the same relentless interview as `/grill-with-docs`, but **stateless**: it saves nothing locally and builds no `CONTEXT.md`. Reach for it when you are **not working in a working directory** — sharpening a plan, a design, a piece of writing, anything with no repo under it. If you are in a working directory, use `/grill-with-docs` instead: it runs the same interview and leaves a paper trail, so it is strictly the better one. +- **`/grilling`** — the interview primitive itself: rounds, the frontier, facts are the agent's job and decisions are yours. `/grill-me` and `/grill-with-docs` are the two named ways in, and `/triage`, `/wayfinder` and `/improve-codebase-architecture` all run it internally. Reach for it directly only when you want the interview with no wrapper around it. +- **`/resolving-merge-conflicts`** — work an in-progress merge or rebase conflict hunk by hunk, resolving by **intent** traced to each side's primary source rather than by picking lines, then finish the operation. It never runs `--abort`. Standalone and off every flow: reach for it when you are already mid-conflict. +- **`/prototype`** — a small, throwaway program that answers one design question: does this state model feel right, or what should this UI look like. Throwaway is a constraint on how the code is written, not a promise to destroy it: the answer folds into the real code, and the prototype itself is kept as a **primary source** on a `prototype/` branch out of main, pointed at from the implementation issue. It's the detour in step 2 of the main flow, but reach for it any time a design question is hard to settle on paper. +- **`/research`** — delegate reading legwork to a **background agent**: it investigates a question against **primary sources**, then leaves a cited Markdown file in the repo. Keep working while it reads. The file it produces is something to take *into* the main flow at `/grill-with-docs` — research feeds the thinking, it doesn't replace it. +- **`/to-questionnaire`** — when the thing blocking you isn't in your head or the codebase but in **someone else's**, this writes them a questionnaire to fill in. It's the inverse of `/grill-me`: instead of interviewing you about the subject, it interviews you about the **send** — who it's going to, what you need back — and aims the questions at the gap. What comes back is material for `/grill-with-docs` or `/to-spec`. +- **`/wizard`** — for the steps only a **human** can take: provisioning infrastructure, setting up credentials or CI secrets, clicking through an unfamiliar third-party dashboard, running a one-off migration or cutover. It generates an interactive bash script that opens each URL, captures each value, and writes it into `.env` and GitHub secrets — so the procedure stops being something you re-explain to an agent every time. Model-invoked, so the agent reaches for it the moment it hits a wall only you can pass. If the agent could just do it itself, it should; this is for where a human is genuinely in the loop. +- **`/wait-what`** — the corrective for a message that didn't land. Use it mid-conversation, inside any other skill, and the agent re-pitches what it just said with the context you were missing, in plain English, using the `CONTEXT.md` vocabulary. It works after the fact; `/grill-with-docs` is the upfront cure, because a shared language agreed early is what stops the jargon arriving at all. +- **`/teach`** — learn a concept over multiple sessions, using the current directory as a stateful workspace. +- **`/writing-for-agents`** — reference for writing documents agents consume: skills, AGENTS.md, pointed-at docs. + +## Precondition + +**`/setup-matt-pocock-skills`** — run before your first engineering flow to configure the issue tracker, triage labels, and doc layout the other skills assume. Custom issue trackers also work. diff --git a/.agents/skills/ask-matt/agents/openai.yaml b/.agents/skills/ask-matt/agents/openai.yaml new file mode 100644 index 0000000..5c60d51 --- /dev/null +++ b/.agents/skills/ask-matt/agents/openai.yaml @@ -0,0 +1,5 @@ +interface: + display_name: "Ask Matt" + short_description: "Find the right skill or workflow" +policy: + allow_implicit_invocation: false diff --git a/.agents/skills/code-review/SKILL.md b/.agents/skills/code-review/SKILL.md new file mode 100644 index 0000000..2d276fe --- /dev/null +++ b/.agents/skills/code-review/SKILL.md @@ -0,0 +1,87 @@ +--- +name: code-review +description: Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". +--- + +Two-axis review of the diff between `HEAD` and a fixed point the user supplies: + +- **Standards** — does the code conform to this repo's documented coding standards? +- **Spec** — does the code faithfully implement the originating issue / spec? + +Both axes run as **parallel sub-agents** so they don't pollute each other's context, then this skill aggregates their findings. + +The issue tracker should have been provided to you — run `/setup-matt-pocock-skills` if `docs/agents/issue-tracker.md` is missing. + +## Process + +### 1. Pin the fixed point + +Whatever the user said is the fixed point — a commit SHA, branch name, tag, `main`, `HEAD~5`, etc. If they didn't specify one, ask for it. + +Capture the diff command once: `git diff ...HEAD` (three-dot, so the comparison is against the merge-base). Also note the list of commits via `git log ..HEAD --oneline`. + +Before going further, confirm the fixed point resolves (`git rev-parse `) and the diff is non-empty. A bad ref or empty diff should fail here — not inside two parallel sub-agents. + +### 2. Identify the spec source + +Look for the originating spec, in this order: + +1. Issue references in the commit messages (`#123`, `Closes #45`, GitLab `!67`, etc.) — fetch via the workflow in `docs/agents/issue-tracker.md`. +2. A path the user passed as an argument. +3. A spec file under `docs/`, `specs/`, or `.scratch/` matching the branch name or feature. +4. If nothing is found, ask the user where the spec is. If they say there isn't one, the **Spec** sub-agent will skip and report "no spec available". + +### 3. Identify the standards sources + +Anything in the repo that documents how code should be written, such as `CODING_STANDARDS.md` or `CONTRIBUTING.md`. + +On top of whatever the repo documents, the Standards axis always carries the **smell baseline** below — a fixed set of Fowler code smells (_Refactoring_, ch.3) that applies even when a repo documents nothing. Two rules bind it: + +- **The repo overrides.** A documented repo standard always wins; where it endorses something the baseline would flag, suppress the smell. +- **Always a judgement call.** Each smell is a labelled heuristic ("possible Feature Envy"), never a hard violation — and, like any standard here, skip anything tooling already enforces. + +Each smell reads *what it is* → *how to fix*; match it against the diff: + +- **Mysterious Name** — a function, variable, or type whose name doesn't reveal what it does or holds. → rename it; if no honest name comes, the design's murky. +- **Duplicated Code** — the same logic shape appears in more than one hunk or file in the change. → extract the shared shape, call it from both. +- **Feature Envy** — a method that reaches into another object's data more than its own. → move the method onto the data it envies. +- **Data Clumps** — the same few fields or params keep travelling together (a type wanting to be born). → bundle them into one type, pass that. +- **Primitive Obsession** — a primitive or string standing in for a domain concept that deserves its own type. → give the concept its own small type. +- **Repeated Switches** — the same `switch`/`if`-cascade on the same type recurs across the change. → replace with polymorphism, or one map both sites share. +- **Shotgun Surgery** — one logical change forces scattered edits across many files in the diff. → gather what changes together into one module. +- **Divergent Change** — one file or module is edited for several unrelated reasons. → split so each module changes for one reason. +- **Speculative Generality** — abstraction, parameters, or hooks added for needs the spec doesn't have. → delete it; inline back until a real need shows. +- **Message Chains** — long `a.b().c().d()` navigation the caller shouldn't depend on. → hide the walk behind one method on the first object. +- **Middle Man** — a class or function that mostly just delegates onward. → cut it, call the real target direct. +- **Refused Bequest** — a subclass or implementer that ignores or overrides most of what it inherits. → drop the inheritance, use composition. + +### 4. Spawn both sub-agents in parallel + +**Standards sub-agent prompt** — include: + +- The full diff command and commit list. +- The list of standards-source files you found in step 3, **plus the smell baseline from step 3** pasted in full — the sub-agent has no other access to it. +- The brief: "Report — per file/hunk where relevant — (a) every place the diff violates a documented standard: cite the standard (file + the rule); and (b) any baseline smell you spot: name it and quote the hunk. Distinguish hard violations from judgement calls — documented-standard breaches can be hard, but baseline smells are always judgement calls, and a documented repo standard overrides the baseline. Skip anything tooling enforces. Under 400 words." + +**Spec sub-agent prompt** — include: + +- The diff command and commit list. +- The path or fetched contents of the spec. +- The brief: "Report: (a) requirements the spec asked for that are missing or partial; (b) behaviour in the diff that wasn't asked for (scope creep); (c) requirements that look implemented but where the implementation looks wrong. Quote the spec line for each finding. Under 400 words." + +If the spec is missing, skip the Spec sub-agent and note this in the final report. + +### 5. Aggregate + +Present the two reports under `## Standards` and `## Spec` headings, verbatim or lightly cleaned. Do **not** merge or rerank findings — the two axes are deliberately separate (see _Why two axes_). + +End with a one-line summary: total findings per axis, and the worst issue _within each axis_ (if any). Don't pick a single winner across axes — that's the reranking the separation exists to prevent. + +## Why two axes + +A change can pass one axis and fail the other: + +- Code that follows every standard but implements the wrong thing → **Standards pass, Spec fail.** +- Code that does exactly what the issue asked but breaks the project's conventions → **Spec pass, Standards fail.** + +Reporting them separately stops one axis from masking the other. diff --git a/.agents/skills/code-review/agents/openai.yaml b/.agents/skills/code-review/agents/openai.yaml new file mode 100644 index 0000000..9076774 --- /dev/null +++ b/.agents/skills/code-review/agents/openai.yaml @@ -0,0 +1,3 @@ +interface: + display_name: "Code Review" + short_description: "Review a diff on standards and spec" diff --git a/.agents/skills/codebase-design/DEEPENING.md b/.agents/skills/codebase-design/DEEPENING.md new file mode 100644 index 0000000..3938457 --- /dev/null +++ b/.agents/skills/codebase-design/DEEPENING.md @@ -0,0 +1,37 @@ +# Deepening + +How to deepen a cluster of shallow modules safely, given its dependencies. Assumes the vocabulary in [SKILL.md](SKILL.md) — **module**, **interface**, **seam**, **adapter**. + +## Dependency categories + +When assessing a candidate for deepening, classify its dependencies. The category determines how the deepened module is tested across its seam. + +### 1. In-process + +Pure computation, in-memory state, no I/O. Always deepenable — merge the modules and test through the new interface directly. No adapter needed. + +### 2. Local-substitutable + +Dependencies that have local test stand-ins (PGLite for Postgres, in-memory filesystem). Deepenable if the stand-in exists. The deepened module is tested with the stand-in running in the test suite. The seam is internal; no port at the module's external interface. + +### 3. Remote but owned (Ports & Adapters) + +Your own services across a network boundary (microservices, internal APIs). Define a **port** (interface) at the seam. The deep module owns the logic; the transport is injected as an **adapter**. Tests use an in-memory adapter. Production uses an HTTP/gRPC/queue adapter. + +Recommendation shape: *"Define a port at the seam, implement an HTTP adapter for production and an in-memory adapter for testing, so the logic sits in one deep module even though it's deployed across a network."* + +### 4. True external (Mock) + +Third-party services (Stripe, Twilio, etc.) you don't control. The deepened module takes the external dependency as an injected port; tests provide a mock adapter. + +## Seam discipline + +- **One adapter means a hypothetical seam. Two adapters means a real one.** Don't introduce a port unless at least two adapters are justified (typically production + test). A single-adapter seam is just indirection. +- **Internal seams vs external seams.** A deep module can have internal seams (private to its implementation, used by its own tests) as well as the external seam at its interface. Don't expose internal seams through the interface just because tests use them. + +## Testing strategy: replace, don't layer + +- Old unit tests on shallow modules become waste once tests at the deepened module's interface exist — delete them. +- Write new tests at the deepened module's interface. The **interface is the test surface**. +- Tests assert on observable outcomes through the interface, not internal state. +- Tests should survive internal refactors — they describe behaviour, not implementation. If a test has to change when the implementation changes, it's testing past the interface. diff --git a/.agents/skills/codebase-design/DESIGN-IT-TWICE.md b/.agents/skills/codebase-design/DESIGN-IT-TWICE.md new file mode 100644 index 0000000..8419ad6 --- /dev/null +++ b/.agents/skills/codebase-design/DESIGN-IT-TWICE.md @@ -0,0 +1,44 @@ +# Design It Twice + +When the user wants to explore alternative interfaces for a chosen deepening candidate, use this parallel sub-agent pattern. Based on "Design It Twice" (Ousterhout) — your first idea is unlikely to be the best. + +Uses the vocabulary in [SKILL.md](SKILL.md) — **module**, **interface**, **seam**, **adapter**, **leverage**. + +## Process + +### 1. Frame the problem space + +Before spawning sub-agents, write a user-facing explanation of the problem space for the chosen candidate: + +- The constraints any new interface would need to satisfy +- The dependencies it would rely on, and which category they fall into (see [DEEPENING.md](DEEPENING.md)) +- A rough illustrative code sketch to ground the constraints — not a proposal, just a way to make the constraints concrete + +Show this to the user, then immediately proceed to Step 2. The user reads and thinks while the sub-agents work in parallel. + +### 2. Spawn sub-agents + +Spawn 3+ sub-agents in parallel. Each must produce a **radically different** interface for the deepened module. + +Prompt each sub-agent with a separate technical brief (file paths, coupling details, dependency category from [DEEPENING.md](DEEPENING.md), what sits behind the seam). The brief is independent of the user-facing problem-space explanation in Step 1. Give each agent a different design constraint: + +- Agent 1: "Minimize the interface — aim for 1–3 entry points max. Maximise leverage per entry point." +- Agent 2: "Maximise flexibility — support many use cases and extension." +- Agent 3: "Optimise for the most common caller — make the default case trivial." +- Agent 4 (if applicable): "Design around ports & adapters for cross-seam dependencies." + +Include both [SKILL.md](SKILL.md) vocabulary and CONTEXT.md vocabulary in the brief so each sub-agent names things consistently with the architecture language and the project's domain language. + +Each sub-agent outputs: + +1. Interface (types, methods, params — plus invariants, ordering, error modes) +2. Usage example showing how callers use it +3. What the implementation hides behind the seam +4. Dependency strategy and adapters (see [DEEPENING.md](DEEPENING.md)) +5. Trade-offs — where leverage is high, where it's thin + +### 3. Present and compare + +Present designs sequentially so the user can absorb each one, then compare them in prose. Contrast by **depth** (leverage at the interface), **locality** (where change concentrates), and **seam placement**. + +After comparing, give your own recommendation: which design you think is strongest and why. If elements from different designs would combine well, propose a hybrid. Be opinionated — the user wants a strong read, not a menu. diff --git a/.agents/skills/codebase-design/SKILL.md b/.agents/skills/codebase-design/SKILL.md new file mode 100644 index 0000000..16620c2 --- /dev/null +++ b/.agents/skills/codebase-design/SKILL.md @@ -0,0 +1,114 @@ +--- +name: codebase-design +description: Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary. +--- + +# Codebase Design + +Design **deep modules**: a lot of behaviour behind a small interface, placed at a clean seam, testable through that interface. Use this language and these principles wherever code is being designed or restructured. The aim is leverage for callers, locality for maintainers, and testability for everyone. + +## Glossary + +Use these terms exactly — don't substitute "component," "service," "API," or "boundary." Consistent language is the whole point. + +**Module** — anything with an interface and an implementation. Deliberately scale-agnostic: a function, class, package, or tier-spanning slice. _Avoid_: unit, component, service. + +**Interface** — everything a caller must know to use the module correctly: the type signature, but also invariants, ordering constraints, error modes, required configuration, and performance characteristics. _Avoid_: API, signature (too narrow — they refer only to the type-level surface). + +**Implementation** — what's inside a module, its body of code. Distinct from **Adapter**: a thing can be a small adapter with a large implementation (a Postgres repo) or a large adapter with a small implementation (an in-memory fake). Reach for "adapter" when the seam is the topic; "implementation" otherwise. + +**Depth** — leverage at the interface: the amount of behaviour a caller (or test) can exercise per unit of interface they have to learn. A module is **deep** when a large amount of behaviour sits behind a small interface, **shallow** when the interface is nearly as complex as the implementation. + +**Seam** _(Michael Feathers)_ — a place where you can alter behaviour without editing in that place; the *location* at which a module's interface lives. Where to put the seam is its own design decision, distinct from what goes behind it. _Avoid_: boundary (overloaded with DDD's bounded context). + +**Adapter** — a concrete thing that satisfies an interface at a seam. Describes *role* (what slot it fills), not substance (what's inside). + +**Leverage** — what callers get from depth: more capability per unit of interface they learn. One implementation pays back across N call sites and M tests. + +**Locality** — what maintainers get from depth: change, bugs, knowledge, and verification concentrate in one place rather than spreading across callers. Fix once, fixed everywhere. + +## Deep vs shallow + +**Deep module** = small interface + lots of implementation: + +``` +┌─────────────────────┐ +│ Small Interface │ ← Few methods, simple params +├─────────────────────┤ +│ │ +│ Deep Implementation│ ← Complex logic hidden +│ │ +└─────────────────────┘ +``` + +**Shallow module** = large interface + little implementation (avoid): + +``` +┌─────────────────────────────────┐ +│ Large Interface │ ← Many methods, complex params +├─────────────────────────────────┤ +│ Thin Implementation │ ← Just passes through +└─────────────────────────────────┘ +``` + +When designing an interface, ask: + +- Can I reduce the number of methods? +- Can I simplify the parameters? +- Can I hide more complexity inside? + +## Principles + +- **Depth is a property of the interface, not the implementation.** A deep module can be internally composed of small, mockable, swappable parts — they just aren't part of the interface. A module can have **internal seams** (private to its implementation, used by its own tests) as well as the **external seam** at its interface. +- **The deletion test.** Imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep. +- **The interface is the test surface.** Callers and tests cross the same seam. If you want to test *past* the interface, the module is probably the wrong shape. +- **One adapter means a hypothetical seam. Two adapters means a real one.** Don't introduce a seam unless something actually varies across it. + +## Designing for testability + +Good interfaces make testing natural: + +1. **Accept dependencies, don't create them.** + + ```typescript + // Testable + function processOrder(order, paymentGateway) {} + + // Hard to test + function processOrder(order) { + const gateway = new StripeGateway(); + } + ``` + +2. **Return results, don't produce side effects.** + + ```typescript + // Testable + function calculateDiscount(cart): Discount {} + + // Hard to test + function applyDiscount(cart): void { + cart.total -= discount; + } + ``` + +3. **Small surface area.** Fewer methods = fewer tests needed. Fewer params = simpler test setup. + +## Relationships + +- A **Module** has exactly one **Interface** (the surface it presents to callers and tests). +- **Depth** is a property of a **Module**, measured against its **Interface**. +- A **Seam** is where a **Module**'s **Interface** lives. +- An **Adapter** sits at a **Seam** and satisfies the **Interface**. +- **Depth** produces **Leverage** for callers and **Locality** for maintainers. + +## Rejected framings + +- **Depth as ratio of implementation-lines to interface-lines** (Ousterhout): rewards padding the implementation. We use depth-as-leverage instead. +- **"Interface" as the TypeScript `interface` keyword or a class's public methods**: too narrow — interface here includes every fact a caller must know. +- **"Boundary"**: overloaded with DDD's bounded context. Say **seam** or **interface**. + +## Going deeper + +- **Deepening a cluster given its dependencies** — see [DEEPENING.md](DEEPENING.md): dependency categories, seam discipline, and replace-don't-layer testing. +- **Exploring alternative interfaces** — see [DESIGN-IT-TWICE.md](DESIGN-IT-TWICE.md): spin up parallel sub-agents to design the interface several radically different ways, then compare on depth, locality, and seam placement. diff --git a/.agents/skills/codebase-design/agents/openai.yaml b/.agents/skills/codebase-design/agents/openai.yaml new file mode 100644 index 0000000..3180715 --- /dev/null +++ b/.agents/skills/codebase-design/agents/openai.yaml @@ -0,0 +1,3 @@ +interface: + display_name: "Codebase Design" + short_description: "Vocabulary for deep-module design" diff --git a/.agents/skills/diagnosing-bugs/SKILL.md b/.agents/skills/diagnosing-bugs/SKILL.md new file mode 100644 index 0000000..7f8acf7 --- /dev/null +++ b/.agents/skills/diagnosing-bugs/SKILL.md @@ -0,0 +1,140 @@ +--- +name: diagnosing-bugs +description: Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow. +--- + +# Diagnosing Bugs + +A discipline for hard bugs. Skip phases only when explicitly justified. + +When exploring the codebase, read `CONTEXT.md` (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching. + +## Redact + +This skill has you show commands, outputs and captured artifacts. **Redact every secret first** — write `` in its place. Build loops against env vars, so the credential stays in the environment rather than in what you show. Captured artifacts carry auth headers: quote only the lines that carry the signal. + +If the redacted output is not enough to diagnose the bug, say so and ask the user. + +## Phase 1 — Build a feedback loop + +**This is the skill.** Everything else is mechanical. If you have a **tight** pass/fail signal for the bug — one that goes red on _this_ bug — you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't have one, no amount of staring at code will save you. + +Spend disproportionate effort here. **Be aggressive. Be creative. Refuse to give up.** + +### Ways to construct one — try them in roughly this order + +1. **Failing test** at whatever seam reaches the bug — unit, integration, e2e. +2. **Curl / HTTP script** against a running dev server. +3. **CLI invocation** with a fixture input, diffing stdout against a known-good snapshot. +4. **Headless browser script** (Playwright / Puppeteer) — drives the UI, asserts on DOM/console/network. +5. **Replay a captured trace.** Save a real network request / payload / event log to disk; replay it through the code path in isolation. +6. **Throwaway harness.** Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call. +7. **Property / fuzz loop.** If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode. +8. **Bisection harness.** If the bug appeared between two known states (commit, dataset, version), automate "boot at state X, check, repeat" so you can `git bisect run` it. +9. **Differential loop.** Run the same input through old-version vs new-version (or two configs) and diff outputs. +10. **HITL bash script.** Last resort. If a human must click, drive _them_ with `scripts/hitl-loop.template.sh` so the loop is still structured. Captured output feeds back to you. + +Build the right feedback loop, and the bug is 90% fixed. + +### Tighten the loop + +Treat the loop as a product. Once you have _a_ loop, **tighten** it: + +- Can I make it faster? (Cache setup, skip unrelated init, narrow the test scope.) +- Can I make the signal sharper? (Assert on the specific symptom, not "didn't crash".) +- Can I make it more deterministic? (Pin time, seed RNG, isolate filesystem, freeze network.) + +A 30-second flaky loop is barely better than no loop; a 2-second deterministic one is tight — a debugging superpower. + +### Non-deterministic bugs + +The goal is not a clean repro but a **higher reproduction rate**. Loop the trigger 100×, parallelise, add stress, narrow timing windows, inject sleeps. A 50%-flake bug is debuggable; 1% is not — keep raising the rate until it's debuggable. + +### When you genuinely cannot build a loop + +Stop and say so explicitly. List what you tried. Ask the user for: (a) access to whatever environment reproduces it, (b) a redacted captured artifact (HAR file, log dump, core dump, screen recording with timestamps), or (c) permission to add temporary production instrumentation. Do **not** proceed to hypothesise without a loop. + +### Completion criterion — a tight loop that goes red + +Phase 1 is done when the loop is **tight** and **red-capable**: you can name **one command** — a script path, a test invocation, a curl — that you have **already run at least once** (show the invocation and its output, redacted), and that is: + +- [ ] **Red-capable** — it drives the actual bug code path and asserts the **user's exact symptom**, so it can go red on this bug and green once fixed. Not "runs without erroring" — it must be able to _catch this specific bug_. +- [ ] **Deterministic** — same verdict every run (flaky bugs: a pinned, high reproduction rate, per above). +- [ ] **Fast** — seconds, not minutes. +- [ ] **Agent-runnable** — you can run it unattended; a human in the loop only via `scripts/hitl-loop.template.sh`. + +If you catch yourself reading code to build a theory before this command exists, **stop — jumping straight to a hypothesis is the exact failure this skill prevents.** No red-capable command, no Phase 2. + +## Phase 2 — Reproduce + minimise + +Run the loop. Watch it go red — the bug appears. + +Confirm: + +- [ ] The loop produces the failure mode the **user** described — not a different failure that happens to be nearby. Wrong bug = wrong fix. +- [ ] The failure is reproducible across multiple runs (or, for non-deterministic bugs, reproducible at a high enough rate to debug against). +- [ ] You have captured the exact symptom (error message, wrong output, slow timing) so later phases can verify the fix actually addresses it. + +### Minimise + +Once it's red, shrink the repro to the **smallest scenario that still goes red**. Cut inputs, callers, config, data, and steps **one at a time**, re-running the loop after each cut — keep only what's load-bearing for the failure. + +Why bother: a minimal repro shrinks the hypothesis space in Phase 3 (fewer moving parts left to suspect) and becomes the clean regression test in Phase 5. + +Done when **every remaining element is load-bearing** — removing any one of them makes the loop go green. + +Do not proceed until you have reproduced **and** minimised. + +## Phase 3 — Hypothesise + +Generate **3–5 ranked hypotheses** before testing any of them. Single-hypothesis generation anchors on the first plausible idea. + +Each hypothesis must be **falsifiable**: state the prediction it makes. + +> Format: "If is the cause, then will make the bug disappear / will make it worse." + +If you cannot state the prediction, the hypothesis is a vibe — discard or sharpen it. + +**Show the ranked list to the user before testing.** They often have domain knowledge that re-ranks instantly ("we just deployed a change to #3"), or know hypotheses they've already ruled out. Cheap checkpoint, big time saver. Don't block on it — proceed with your ranking if the user is AFK. + +## Phase 4 — Instrument + +Each probe must map to a specific prediction from Phase 3. **Change one variable at a time.** + +Tool preference: + +1. **Debugger / REPL inspection** if the env supports it. One breakpoint beats ten logs. +2. **Targeted logs** at the boundaries that distinguish hypotheses. +3. Never "log everything and grep". + +**Tag every debug log** with a unique prefix, e.g. `[DEBUG-a4f2]`. Cleanup at the end becomes a single grep. Untagged logs survive; tagged logs die. + +**Perf branch.** For performance regressions, logs are usually wrong. Instead: establish a baseline measurement (timing harness, `performance.now()`, profiler, query plan), then bisect. Measure first, fix second. + +## Phase 5 — Fix + regression test + +Write the regression test **before the fix** — but only if there is a **correct seam** for it. + +A correct seam is one where the test exercises the **real bug pattern** as it occurs at the call site. If the only available seam is too shallow (single-caller test when the bug needs multiple callers, unit test that can't replicate the chain that triggered the bug), a regression test there gives false confidence. + +**If no correct seam exists, that itself is the finding.** Note it. The codebase architecture is preventing the bug from being locked down. Flag this for the next phase. + +If a correct seam exists: + +1. Turn the minimised repro into a failing test at that seam. +2. Watch it fail. +3. Apply the fix. +4. Watch it pass. +5. Re-run the Phase 1 feedback loop against the original (un-minimised) scenario. + +## Phase 6 — Cleanup + post-mortem + +Required before declaring done: + +- [ ] Original repro no longer reproduces (re-run the Phase 1 loop) +- [ ] Regression test passes (or absence of seam is documented) +- [ ] All `[DEBUG-...]` instrumentation removed (`grep` the prefix) +- [ ] Throwaway prototypes deleted (or moved to a clearly-marked debug location) +- [ ] The hypothesis that turned out correct is stated in the commit / PR message — so the next debugger learns + +**Then ask: what would have prevented this bug?** If the answer involves architectural change (no good test seam, tangled callers, hidden coupling) hand off to the `/improve-codebase-architecture` skill with the specifics. Make the recommendation **after** the fix is in, not before — you have more information now than when you started. diff --git a/.agents/skills/diagnosing-bugs/agents/openai.yaml b/.agents/skills/diagnosing-bugs/agents/openai.yaml new file mode 100644 index 0000000..a13a755 --- /dev/null +++ b/.agents/skills/diagnosing-bugs/agents/openai.yaml @@ -0,0 +1,3 @@ +interface: + display_name: "Diagnosing Bugs" + short_description: "Diagnose hard bugs and regressions" diff --git a/.agents/skills/diagnosing-bugs/scripts/hitl-loop.template.sh b/.agents/skills/diagnosing-bugs/scripts/hitl-loop.template.sh new file mode 100644 index 0000000..43daedd --- /dev/null +++ b/.agents/skills/diagnosing-bugs/scripts/hitl-loop.template.sh @@ -0,0 +1,44 @@ +#!/usr/bin/env bash +# Human-in-the-loop reproduction loop. +# Copy this file, edit the steps below, and run it. +# The agent runs the script; the user follows prompts in their terminal. +# +# Usage: +# bash hitl-loop.template.sh +# +# Two helpers: +# step "" → show instruction, wait for Enter +# capture VAR "" → show question, read response into VAR +# +# At the end, captured values are printed as KEY=VALUE for the agent to parse. +# +# `capture` prints its value back to the terminal, where the agent reads it — so +# capture observations, and leave signing in to the user as a `step`. + +set -euo pipefail + +step() { + printf '\n>>> %s\n' "$1" + read -r -p " [Enter when done] " _ +} + +capture() { + local var="$1" question="$2" answer + printf '\n>>> %s\n' "$question" + read -r -p " > " answer + printf -v "$var" '%s' "$answer" +} + +# --- edit below --------------------------------------------------------- + +step "Open the app at http://localhost:3000 and sign in." + +capture ERRORED "Click the 'Export' button. Did it throw an error? (y/n)" + +capture ERROR_MSG "Paste the error message (or 'none'):" + +# --- edit above --------------------------------------------------------- + +printf '\n--- Captured ---\n' +printf 'ERRORED=%s\n' "$ERRORED" +printf 'ERROR_MSG=%s\n' "$ERROR_MSG" diff --git a/.agents/skills/domain-modeling/ADR-FORMAT.md b/.agents/skills/domain-modeling/ADR-FORMAT.md new file mode 100644 index 0000000..da7e78e --- /dev/null +++ b/.agents/skills/domain-modeling/ADR-FORMAT.md @@ -0,0 +1,47 @@ +# ADR Format + +ADRs live in `docs/adr/` and use sequential numbering: `0001-slug.md`, `0002-slug.md`, etc. + +Create the `docs/adr/` directory lazily — only when the first ADR is needed. + +## Template + +```md +# {Short title of the decision} + +{1-3 sentences: what's the context, what did we decide, and why.} +``` + +That's it. An ADR can be a single paragraph. The value is in recording *that* a decision was made and *why* — not in filling out sections. + +## Optional sections + +Only include these when they add genuine value. Most ADRs won't need them. + +- **Status** frontmatter (`proposed | accepted | deprecated | superseded by ADR-NNNN`) — useful when decisions are revisited +- **Considered Options** — only when the rejected alternatives are worth remembering +- **Consequences** — only when non-obvious downstream effects need to be called out + +## Numbering + +Scan `docs/adr/` for the highest existing number and increment by one. + +## When to offer an ADR + +All three of these must be true: + +1. **Hard to reverse** — the cost of changing your mind later is meaningful +2. **Surprising without context** — a future reader will look at the code and wonder "why on earth did they do it this way?" +3. **The result of a real trade-off** — there were genuine alternatives and you picked one for specific reasons + +If a decision is easy to reverse, skip it — you'll just reverse it. If it's not surprising, nobody will wonder why. If there was no real alternative, there's nothing to record beyond "we did the obvious thing." + +### What qualifies + +- **Architectural shape.** "We're using a monorepo." "The write model is event-sourced, the read model is projected into Postgres." +- **Integration patterns between contexts.** "Ordering and Billing communicate via domain events, not synchronous HTTP." +- **Technology choices that carry lock-in.** Database, message bus, auth provider, deployment target. Not every library — just the ones that would take a quarter to swap out. +- **Boundary and scope decisions.** "Customer data is owned by the Customer context; other contexts reference it by ID only." The explicit no-s are as valuable as the yes-s. +- **Deliberate deviations from the obvious path.** "We're using manual SQL instead of an ORM because X." Anything where a reasonable reader would assume the opposite. These stop the next engineer from "fixing" something that was deliberate. +- **Constraints not visible in the code.** "We can't use AWS because of compliance requirements." "Response times must be under 200ms because of the partner API contract." +- **Rejected alternatives when the rejection is non-obvious.** If you considered GraphQL and picked REST for subtle reasons, record it — otherwise someone will suggest GraphQL again in six months. diff --git a/.agents/skills/domain-modeling/CONTEXT-FORMAT.md b/.agents/skills/domain-modeling/CONTEXT-FORMAT.md new file mode 100644 index 0000000..eaf2a18 --- /dev/null +++ b/.agents/skills/domain-modeling/CONTEXT-FORMAT.md @@ -0,0 +1,60 @@ +# CONTEXT.md Format + +## Structure + +```md +# {Context Name} + +{One or two sentence description of what this context is and why it exists.} + +## Language + +**Order**: +{A one or two sentence description of the term} +_Avoid_: Purchase, transaction + +**Invoice**: +A request for payment sent to a customer after delivery. +_Avoid_: Bill, payment request + +**Customer**: +A person or organization that places orders. +_Avoid_: Client, buyer, account +``` + +## Rules + +- **Be opinionated.** When multiple words exist for the same concept, pick the best one and list the others under `_Avoid_`. +- **Keep definitions tight.** One or two sentences max. Define what it IS, not what it does. +- **Only include terms specific to this project's context.** General programming concepts (timeouts, error types, utility patterns) don't belong even if the project uses them extensively. Before adding a term, ask: is this a concept unique to this context, or a general programming concept? Only the former belongs. +- **Group terms under subheadings** when natural clusters emerge. If all terms belong to a single cohesive area, a flat list is fine. + +## Single vs multi-context repos + +**Single context (most repos):** One `CONTEXT.md` at the repo root. + +**Multiple contexts:** A `CONTEXT-MAP.md` at the repo root lists the contexts, where they live, and how they relate to each other: + +```md +# Context Map + +## Contexts + +- [Ordering](./src/ordering/CONTEXT.md) — receives and tracks customer orders +- [Billing](./src/billing/CONTEXT.md) — generates invoices and processes payments +- [Fulfillment](./src/fulfillment/CONTEXT.md) — manages warehouse picking and shipping + +## Relationships + +- **Ordering → Fulfillment**: Ordering emits `OrderPlaced` events; Fulfillment consumes them to start picking +- **Fulfillment → Billing**: Fulfillment emits `ShipmentDispatched` events; Billing consumes them to generate invoices +- **Ordering ↔ Billing**: Shared types for `CustomerId` and `Money` +``` + +The skill infers which structure applies: + +- If `CONTEXT-MAP.md` exists, read it to find contexts +- If only a root `CONTEXT.md` exists, single context +- If neither exists, create a root `CONTEXT.md` lazily when the first term is resolved + +When multiple contexts exist, infer which one the current topic relates to. If unclear, ask. diff --git a/.agents/skills/domain-modeling/SKILL.md b/.agents/skills/domain-modeling/SKILL.md new file mode 100644 index 0000000..d0f7e1a --- /dev/null +++ b/.agents/skills/domain-modeling/SKILL.md @@ -0,0 +1,74 @@ +--- +name: domain-modeling +description: Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model. +--- + +# Domain Modeling + +Actively build and sharpen the project's domain model as you design. This is the *active* discipline — challenging terms, inventing edge-case scenarios, and writing the glossary and decisions down the moment they crystallise. (Merely *reading* `CONTEXT.md` for vocabulary is not this skill — that's a one-line habit any skill can do. This skill is for when you're changing the model, not just consuming it.) + +## File structure + +Most repos have a single context: + +``` +/ +├── CONTEXT.md +├── docs/ +│ └── adr/ +│ ├── 0001-event-sourced-orders.md +│ └── 0002-postgres-for-write-model.md +└── src/ +``` + +If a `CONTEXT-MAP.md` exists at the root, the repo has multiple contexts. The map points to where each one lives: + +``` +/ +├── CONTEXT-MAP.md +├── docs/ +│ └── adr/ ← system-wide decisions +├── src/ +│ ├── ordering/ +│ │ ├── CONTEXT.md +│ │ └── docs/adr/ ← context-specific decisions +│ └── billing/ +│ ├── CONTEXT.md +│ └── docs/adr/ +``` + +Create files lazily — only when you have something to write. If no `CONTEXT.md` exists, create one when the first term is resolved. If no `docs/adr/` exists, create it when the first ADR is needed. + +## During the session + +### Challenge against the glossary + +When the user uses a term that conflicts with the existing language in `CONTEXT.md`, call it out immediately. "Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?" + +### Sharpen fuzzy language + +When the user uses vague or overloaded terms, propose a precise canonical term. "You're saying 'account' — do you mean the Customer or the User? Those are different things." + +### Discuss concrete scenarios + +When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts. + +### Cross-reference with code + +When the user states how something works, check whether the code agrees. If you find a contradiction, surface it: "Your code cancels entire Orders, but you just said partial cancellation is possible — which is right?" + +### Update CONTEXT.md inline + +When a term is resolved, update `CONTEXT.md` right there. Don't batch these up — capture them as they happen. Use the format in [CONTEXT-FORMAT.md](./CONTEXT-FORMAT.md). + +`CONTEXT.md` should be totally devoid of implementation details. Do not treat `CONTEXT.md` as a spec, a scratch pad, or a repository for implementation decisions. It is a glossary and nothing else. + +### Offer ADRs sparingly + +Only offer to create an ADR when all three are true: + +1. **Hard to reverse** — the cost of changing your mind later is meaningful +2. **Surprising without context** — a future reader will wonder "why did they do it this way?" +3. **The result of a real trade-off** — there were genuine alternatives and you picked one for specific reasons + +If any of the three is missing, skip the ADR. Use the format in [ADR-FORMAT.md](./ADR-FORMAT.md). diff --git a/.agents/skills/domain-modeling/agents/openai.yaml b/.agents/skills/domain-modeling/agents/openai.yaml new file mode 100644 index 0000000..7f1522d --- /dev/null +++ b/.agents/skills/domain-modeling/agents/openai.yaml @@ -0,0 +1,3 @@ +interface: + display_name: "Domain Modeling" + short_description: "Build and sharpen a domain model" diff --git a/.agents/skills/grill-me/SKILL.md b/.agents/skills/grill-me/SKILL.md new file mode 100644 index 0000000..9470cfc --- /dev/null +++ b/.agents/skills/grill-me/SKILL.md @@ -0,0 +1,7 @@ +--- +name: grill-me +description: A relentless interview to sharpen a plan or design. +disable-model-invocation: true +--- + +Run a `/grilling` session. diff --git a/.agents/skills/grill-me/agents/openai.yaml b/.agents/skills/grill-me/agents/openai.yaml new file mode 100644 index 0000000..4d6fb0c --- /dev/null +++ b/.agents/skills/grill-me/agents/openai.yaml @@ -0,0 +1,5 @@ +interface: + display_name: "Grill Me" + short_description: "Sharpen a plan through interview" +policy: + allow_implicit_invocation: false diff --git a/.agents/skills/grill-with-docs/SKILL.md b/.agents/skills/grill-with-docs/SKILL.md new file mode 100644 index 0000000..bed05d2 --- /dev/null +++ b/.agents/skills/grill-with-docs/SKILL.md @@ -0,0 +1,7 @@ +--- +name: grill-with-docs +description: A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go. +disable-model-invocation: true +--- + +Run a `/grilling` session, using the `/domain-modeling` skill. diff --git a/.agents/skills/grill-with-docs/agents/openai.yaml b/.agents/skills/grill-with-docs/agents/openai.yaml new file mode 100644 index 0000000..5dbe278 --- /dev/null +++ b/.agents/skills/grill-with-docs/agents/openai.yaml @@ -0,0 +1,5 @@ +interface: + display_name: "Grill with Docs" + short_description: "Grill a design and write its docs" +policy: + allow_implicit_invocation: false diff --git a/.agents/skills/grilling/SKILL.md b/.agents/skills/grilling/SKILL.md new file mode 100644 index 0000000..95bd01e --- /dev/null +++ b/.agents/skills/grilling/SKILL.md @@ -0,0 +1,22 @@ +--- +name: grilling +description: Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases. +--- + +Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it. + +Work the tree in **rounds**. The **frontier** is every decision whose prerequisites are already settled — the questions you can ask _now_ without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round. + +Each question should be formatted like so: + +``` +❓ **Q1** - ****: + +➡️ +``` + +Each round the user answers reshapes the tree — settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a _later_ round, not this one. + +Finding _facts_ is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it — don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report — ask the rest of the frontier now. The _decisions_ are the user's — put each to them and wait. + +The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding. diff --git a/.agents/skills/grilling/agents/openai.yaml b/.agents/skills/grilling/agents/openai.yaml new file mode 100644 index 0000000..ddbdb96 --- /dev/null +++ b/.agents/skills/grilling/agents/openai.yaml @@ -0,0 +1,3 @@ +interface: + display_name: "Grilling" + short_description: "Stress-test thinking a round of questions at a time" diff --git a/.agents/skills/handoff/SKILL.md b/.agents/skills/handoff/SKILL.md new file mode 100644 index 0000000..043d9e1 --- /dev/null +++ b/.agents/skills/handoff/SKILL.md @@ -0,0 +1,16 @@ +--- +name: handoff +description: Compact the current conversation into a handoff document for another agent to pick up. +argument-hint: "What will the next session be used for?" +disable-model-invocation: true +--- + +Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS - not the current workspace. + +Include a "suggested skills" section in the document, which suggests skills that the agent should invoke. + +Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead. + +Redact any sensitive information, such as API keys, passwords, or personally identifiable information. + +If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly. diff --git a/.agents/skills/handoff/agents/openai.yaml b/.agents/skills/handoff/agents/openai.yaml new file mode 100644 index 0000000..6e1d8da --- /dev/null +++ b/.agents/skills/handoff/agents/openai.yaml @@ -0,0 +1,5 @@ +interface: + display_name: "Handoff" + short_description: "Compact a conversation into a handoff" +policy: + allow_implicit_invocation: false diff --git a/.agents/skills/implement/SKILL.md b/.agents/skills/implement/SKILL.md new file mode 100644 index 0000000..7a0b11f --- /dev/null +++ b/.agents/skills/implement/SKILL.md @@ -0,0 +1,15 @@ +--- +name: implement +description: "Implement a piece of work based on a spec or set of tickets." +disable-model-invocation: true +--- + +Implement the work described by the user in the spec or tickets. + +Use /tdd where possible, at pre-agreed seams. + +Run typechecking regularly, single test files regularly, and the full test suite once at the end. + +Once done, use /code-review to review the work. + +Commit your work to the current branch. diff --git a/.agents/skills/implement/agents/openai.yaml b/.agents/skills/implement/agents/openai.yaml new file mode 100644 index 0000000..f8794dc --- /dev/null +++ b/.agents/skills/implement/agents/openai.yaml @@ -0,0 +1,5 @@ +interface: + display_name: "Implement" + short_description: "Build work from a spec or tickets" +policy: + allow_implicit_invocation: false diff --git a/.agents/skills/improve-codebase-architecture/HTML-REPORT.md b/.agents/skills/improve-codebase-architecture/HTML-REPORT.md new file mode 100644 index 0000000..17f6d2c --- /dev/null +++ b/.agents/skills/improve-codebase-architecture/HTML-REPORT.md @@ -0,0 +1,123 @@ +# HTML Report Format + +The architectural review is rendered as a single self-contained HTML file in the OS temp directory. Tailwind and Mermaid both come from CDNs. Mermaid handles graph-shaped diagrams reliably; hand-built divs and inline SVG handle the more editorial visuals (mass diagrams, cross-sections). Mix the two — don't lean on Mermaid for everything, it'll start to look generic. + +## Scaffold + +```html + + + + + Architecture review — {{repo name}} + + + + + +
+
...
+
...
+
...
+
+ + +``` + +## Header + +Repo name, date, and a compact legend: solid box = module, dashed line = seam, red arrow = leakage, thick dark box = deep module. No introduction paragraph — straight into the candidates. + +## Candidate card + +The diagrams carry the weight. Prose is sparse, plain, and uses the glossary terms (from the `/codebase-design` skill) without ceremony. + +Each candidate is one `
`: + +- **Title** — short, names the deepening (e.g. "Collapse the Order intake pipeline"). +- **Badge row** — recommendation strength (`Strong` = emerald, `Worth exploring` = amber, `Speculative` = slate), plus a tag for the dependency category (`in-process`, `local-substitutable`, `ports & adapters`, `mock`). +- **Files** — monospaced list, `font-mono text-sm`. +- **Before / After diagram** — the centrepiece. Two columns, side by side. See patterns below. +- **Problem** — one sentence. What hurts. +- **Solution** — one sentence. What changes. +- **Wins** — bullets, ≤6 words each. e.g. "Tests hit one interface", "Pricing logic stops leaking", "Delete 4 shallow wrappers". +- **ADR callout** (if applicable) — one line in an amber-tinted box. + +No paragraphs of explanation. If the diagram needs a paragraph to be understood, redraw the diagram. + +## Diagram patterns + +Pick the pattern that fits the candidate. Mix them. Don't make every diagram look the same — variety is part of the point. + +### Mermaid graph (the workhorse for dependencies / call flow) + +Use a Mermaid `flowchart` or `graph` when the point is "X calls Y calls Z, and look at the mess." Wrap it in a Tailwind-styled card so it doesn't feel parachuted in. Style with classDef to colour leakage edges red and the deep module dark. Sequence diagrams work well for "before: 6 round-trips; after: 1." + +```html +
+ 
+    flowchart LR
+      A[OrderHandler] --> B[OrderValidator]
+      B --> C[OrderRepo]
+      C -.leak.-> D[PricingClient]
+      classDef leak stroke:#dc2626,stroke-width:2px;
+      class C,D leak
+
+
+``` + +### Hand-built boxes-and-arrows (when Mermaid's layout fights you) + +Modules as `
`s with borders and labels. Arrows as inline SVG `` or `` elements positioned absolutely over a relative container. Reach for this when you want the "after" diagram to feel like one thick-bordered deep module with greyed-out internals — Mermaid won't render that with the right weight. + +### Cross-section (good for layered shallowness) + +Stack horizontal bands (`h-12 border-l-4`) to show layers a call passes through. Before: 6 thin layers each doing nothing. After: 1 thick band labelled with the consolidated responsibility. + +### Mass diagram (good for "interface as wide as implementation") + +Two rectangles per module — one for interface surface area, one for implementation. Before: interface rectangle is nearly as tall as the implementation rectangle (shallow). After: interface rectangle is short, implementation rectangle is tall (deep). + +### Call-graph collapse + +Before: a tree of function calls rendered as nested boxes. After: the same tree collapsed into one box, with the now-internal calls shown faded inside it. + +## Style guidance + +- Lean editorial, not corporate-dashboard. Generous whitespace. Serif optional for headings (`font-serif` works well with stone/slate). +- Colour sparingly: one accent (emerald or indigo) plus red for leakage and amber for warnings. +- Keep diagrams ~320px tall so before/after sits comfortably side by side without scrolling. +- Use `text-xs uppercase tracking-wider` for module labels inside diagrams — they should read as schematic, not as UI. +- The only scripts are the Tailwind CDN and the Mermaid ESM import. The report is otherwise static — no app code, no interactivity beyond Mermaid's own rendering. + +## Top recommendation section + +One larger card. Candidate name, one sentence on why, anchor link to its card. That's it. + +## Tone + +Plain English, concise — but the architectural nouns and verbs come straight from the `/codebase-design` skill. Concision is not an excuse to drift. + +**Use exactly:** module, interface, implementation, depth, deep, shallow, seam, adapter, leverage, locality. + +**Never substitute:** component, service, unit (for module) · API, signature (for interface) · boundary (for seam) · layer, wrapper (for module, when you mean module). + +**Phrasings that fit the style:** + +- "Order intake module is shallow — interface nearly matches the implementation." +- "Pricing leaks across the seam." +- "Deepen: one interface, one place to test." +- "Two adapters justify the seam: HTTP in prod, in-memory in tests." + +**Wins bullets** name the gain in glossary terms: *"locality: bugs concentrate in one module"*, *"leverage: one interface, N call sites"*, *"interface shrinks; implementation absorbs the wrappers"*. Don't write *"easier to maintain"* or *"cleaner code"* — those terms aren't in the glossary and don't earn their place. + +No hedging, no throat-clearing, no "it's worth noting that…". If a sentence could be a bullet, make it a bullet. If a bullet could be cut, cut it. If a term isn't in the `/codebase-design` glossary, reach for one that is before inventing a new one. diff --git a/.agents/skills/improve-codebase-architecture/SKILL.md b/.agents/skills/improve-codebase-architecture/SKILL.md new file mode 100644 index 0000000..529761a --- /dev/null +++ b/.agents/skills/improve-codebase-architecture/SKILL.md @@ -0,0 +1,71 @@ +--- +name: improve-codebase-architecture +description: Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. +disable-model-invocation: true +--- + +# Improve Codebase Architecture + +Surface architectural friction and propose **deepening opportunities** — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability. + +This command is _informed_ by the project's domain model and built on a shared design vocabulary: + +- Run the `/codebase-design` skill for the architecture vocabulary (**module**, **interface**, **depth**, **seam**, **adapter**, **leverage**, **locality**) and its principles (the deletion test, "the interface is the test surface", "one adapter = hypothetical seam, two = real"). Use these terms exactly in every suggestion — don't drift into "component," "service," "API," or "boundary." +- The domain language in `CONTEXT.md` gives names to good seams; ADRs in `docs/adr/` record decisions this command should not re-litigate. + +## Process + +### 1. Explore + +**Scope before you scan — YAGNI.** Deepening a module pays off by making future changes to it easier, so put extra weight on the parts of the codebase that have recently changed. Decide *where* to look before you look: + +- If the user named a direction — a module, a subsystem, a pain point — take it, and skip the inference below. +- Otherwise, walk back a good stretch of the commit history (`git log --oneline`) to find the codebase's hot spots — the files and areas that keep coming up — and let those paths pull your attention first. If the changes are scattered with no clear hot spot, widen the net. + +Read the project's domain glossary (`CONTEXT.md`) and any ADRs in the area you're touching first. + +Then spawn a sub-agent to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction: + +- Where does understanding one concept require bouncing between many small modules? +- Where are modules **shallow** — interface nearly as complex as the implementation? +- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no **locality**)? +- Where do tightly-coupled modules leak across their seams? +- Which parts of the codebase are untested, or hard to test through their current interface? + +Apply the **deletion test** to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want. + +### 2. Present candidates as an HTML report + +Write a self-contained HTML file to the OS temp directory so nothing lands in the repo. Resolve the temp dir from `$TMPDIR`, falling back to `/tmp` (or `%TEMP%` on Windows), and write to `/architecture-review-.html` so each run gets a fresh file. Open it for the user — `xdg-open ` on Linux, `open ` on macOS, `start ` on Windows — and tell them the absolute path. + +The report uses **Tailwind via CDN** for layout and styling, and **Mermaid via CDN** for diagrams where a graph/flow/sequence reliably communicates the structure. Mix Mermaid with hand-crafted CSS/SVG visuals — use Mermaid when relationships are graph-shaped (call graphs, dependencies, sequences), and hand-built divs/SVG when you want something more editorial (mass diagrams, cross-sections, collapse animations). Each candidate gets a **before/after visualisation**. Be visual. + +For each candidate, render a card with: + +- **Files** — which files/modules are involved +- **Problem** — why the current architecture is causing friction +- **Solution** — plain English description of what would change +- **Benefits** — explained in terms of locality and leverage, and how tests would improve +- **Before / After diagram** — side-by-side, custom-drawn, illustrating the shallowness and the deepening +- **Recommendation strength** — one of `Strong`, `Worth exploring`, `Speculative`, rendered as a badge + +End the report with a **Top recommendation** section: which candidate you'd tackle first and why. + +**Use CONTEXT.md vocabulary for the domain, and the `/codebase-design` vocabulary for the architecture.** If `CONTEXT.md` defines "Order," talk about "the Order intake module" — not "the FooBarHandler," and not "the Order service." + +**ADR conflicts**: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly in the card (e.g. a warning callout: _"contradicts ADR-0007 — but worth reopening because…"_). Don't list every theoretical refactor an ADR forbids. + +See [HTML-REPORT.md](HTML-REPORT.md) for the full HTML scaffold, diagram patterns, and styling guidance. + +Do NOT propose interfaces yet. After the file is written, ask the user: "Which of these would you like to explore?" + +### 3. Grilling loop + +Once the user picks a candidate, run the `/grilling` skill to walk the decision tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive. + +Side effects happen inline as decisions crystallize — run the `/domain-modeling` skill to keep the domain model current as you go: + +- **Naming a deepened module after a concept not in `CONTEXT.md`?** Add the term to `CONTEXT.md`. Create the file lazily if it doesn't exist. +- **Sharpening a fuzzy term during the conversation?** Update `CONTEXT.md` right there. +- **User rejects the candidate with a load-bearing reason?** Offer an ADR, framed as: _"Want me to record this as an ADR so future architecture reviews don't re-suggest it?"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing — skip ephemeral reasons ("not worth it right now") and self-evident ones. +- **Want to explore alternative interfaces for the deepened module?** Run the `/codebase-design` skill and use its design-it-twice parallel sub-agent pattern. diff --git a/.agents/skills/improve-codebase-architecture/agents/openai.yaml b/.agents/skills/improve-codebase-architecture/agents/openai.yaml new file mode 100644 index 0000000..706fdca --- /dev/null +++ b/.agents/skills/improve-codebase-architecture/agents/openai.yaml @@ -0,0 +1,5 @@ +interface: + display_name: "Improve Codebase Architecture" + short_description: "Find and grill architecture improvements" +policy: + allow_implicit_invocation: false diff --git a/.agents/skills/prototype/LOGIC.md b/.agents/skills/prototype/LOGIC.md new file mode 100644 index 0000000..5f5a3fd --- /dev/null +++ b/.agents/skills/prototype/LOGIC.md @@ -0,0 +1,67 @@ +# Logic Prototype + +A single, self-contained HTML file — a **shareable demo** — that lets anyone drive a state model by clicking buttons. Use this when the question is about **business logic, state transitions, or data shape** — the kind of thing that looks reasonable on paper but only feels wrong once you push it through real cases. + +Because it's one file with nothing to install, you can hand it to a non-developer — a designer, a PM, a domain expert — and let them feel the model for themselves. So it speaks their language, not the code's. + +## When this is the right shape + +- "I'm not sure if this state machine handles the edge case where X then Y." +- "Does this data model actually let me represent the case where..." +- "I want to feel out what the API should look like before writing it." +- Anything where someone wants to **press buttons and watch state change**. + +If the question is "what should this look like" — wrong branch. Use [UI.md](UI.md). + +## Process + +### 1. State the question + +Before writing code, write down what state model and what question you're prototyping. One paragraph, at the top of the demo (in a visible intro, not just a comment). A logic prototype that answers the wrong question is pure waste — make the question explicit so it can be checked later, whether the user is watching now or returning to it AFK. + +### 2. Isolate the logic in a portable module + +Put the actual logic — the bit that's answering the question — in a single `