ask-matt

Files (3)

• PHASE-BOUNDARIES.md
• SKILL.md
• openai.yaml · agents/

SKILL.md (first lines)

# 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. **`/design-planning`** — for any non-trivial visual, interaction, or architecture choice, compare two genuinely different directions against explicit criteria and wait for the user's choice. It is the recovered home for the old "iterate, simplify, and think twice before executing" principles. When the choice lands, it appends a `decision` node to the area's project graph.
3. **`/planning`** — turn the approved direction into a deterministic implementation sequence, named seam, and verification matrix. It stops for approval; it does not edit production code or perform delivery. An approved plan lands as a `milestone` node in the same graph.
4. **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.
5. **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/<feature>/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 1–5 in **one unbroken context window** — don't compact or clear until after `/to-tickets` — so the grilling, design choice, execution plan, 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.
- **`/brainstorm`** — inspect the full diff and surrounding architecture without editing files, then surface a few high-leverage alternatives, tradeoffs, and ideas that the current change may have missed. A direction the user settles on in-session becomes a `decision` node in the project graph.
- **`/code-iteration`** — implement and refine code through bounded verification passes: acceptance criteria, baseline, smallest coherent change, executed checks with recorded evidence, and scope-honest VERIFIED/FAILED/BLOCKED verdicts. Pass records append to the project's iteration directory; where a project graph exists, it appends each pass and exchanges explicit handoff edges with `/design-iteration`.
- **`/custom-learning`** — learn a technology through a dependency-ordered Practice Map, one Subcard at a time, with a reviewable proof artifact at each gate.
- **`/design-iteration`** — refine an interface through visual feedback rounds against an append-only liked/rejected ledger: explicit user feedback is the only authority for verdicts, liked details survive until explicitly superseded, and rounds inspect rendered evidence rather than source. Where a project graph exists, it hands implementation-sized follow-ups to `/code-iteration` (and receives visual regressions back) as typed handoff edges rather than loose notes.
- **`/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/<name>` 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. The verdict becomes a `decision` node in the project graph.
- **`/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.
- **`/lesson-iteration`** — author a full deep lesson for the Practice Map from a topic: plan the curriculum, draft, audit for depth and consistency, then migrate it into the map's curriculum data.
- **`/lesson-script`** — the fast track to the same destination: one relay round to a chat model drafts a free-form essay **with its integration payload attached** (practice prompt, check prompt, theory), then the runbook salvages mechanically (the agent reads only diagnostics), converts, and wires it through one script invocation; the payload is what keeps the essay out of the agent's context entirely. For a lesson that deserves the full depth-audited loop, use `/lesson-iteration`.
- **`/minimize-iteration`** — compress a task into the shortest prompt that still delegates it to a separate chat model. The chat service routes prompts by token count — length is routing — so the prompt pays only for what the target model cannot infer (non-inferable specifics, the output contract, the reasoning bar), and the pasted reply is integrated against the repo afterwards. Model-invoked, so the agent fires it itself the moment a task is about to cross to a chat model.
- **`/orchestrate`** — run the relay loop around a designated specialist in a separate chat: the agent keeps the repo and the final say, sends one self-contained brief at a time sized to the specialist's context and timeout, salvage-integrates the pasted reply against the repo rather than pasting it wholesale, validates, and repeats until done. Where minimize-iteration is a single compressed crossing, orchestrate is the loop for work too large or design-heavy to cross once. Model-invoked, so the agent starts the loop itself when the user names the specialist or hands back a specialist reply to integrate.
- **`/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.

From vasyapym/vasyapym.github.io, MIT.

More from vasyapym/vasyapym.github.io