---
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 three **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 when you **have a codebase**: it's stateful, retaining what it learns in `CONTEXT.md` and ADRs. (No codebase? Use `/grill-me` — see Standalone. Both run the same `/grilling` primitive; `grill-with-docs` is the one that leaves a paper trail.)
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 (see Crossing sessions):
   - **`/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-issues`** to split it into tracer-bullet issues, each declaring its **blocking edges** and AFK/HITL mode. The default tracker is existing Beads state or local `.scratch`; a hosted tracker is used only when explicitly configured. Work the unblocked frontier: start each AFK issue with **`/implement`** in a fresh context, and surface each HITL issue to the human.
   - **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-issues` — so the grilling, spec, and issues all build on the same thinking. Each AFK `/implement` or HITL work session then starts fresh, working from one issue.

The limit on this is the **[smart zone](https://www.aihero.dev/ai-coding-dictionary/smart-zone)**: the window (~120k tokens on state-of-the-art models) within which the model still reasons sharply. If a session approaches it before `/to-issues`, don't push on degraded — `/handoff` and continue in a fresh thread.

## 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. Issues that `/to-issues` produced are already classified and scoped, so **don't triage them**: route AFK issues to `/implement` and bring HITL issues to the human.

- **Something's broken** → **`/diagnose`**. 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`**. When the way from here to the destination isn't visible yet, it charts a **shared map** of investigation issues 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. Then it merges onto the main flow at **`/to-spec`** (or, if the effort turned out small enough, straight to **`/implement`**). Where **`/grill-with-docs`** sharpens an idea you can hold in one session, wayfinder is for the idea you can't.

- **A scoped Sandcastle run needs to start, attach, or stay supervised** → **`/sandcastle-shadow-monitor`**. Give it the referenced scope, PRD, or issue. It validates runner and queue ownership before launch, watches the run by bounded log deltas, and keeps restart-safe generic churn evidence separate from issue failures without taking over tracker transitions.

## 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.
- **`/setup-coding-quality-checks`** — install or strengthen the repo's local formatters, linters, typechecks, tests, security scanners, and hooks.
- **`/zoom-out`** — orient an unfamiliar section of code inside the larger system before deciding what to change.

## Vocabulary underneath

Three model-invoked references 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.
- **`/code-structure`** — the service-layer boundary between domain orchestration and reusable operational mechanics. Reach for it when repeated workflows need one shared capability without leaking domain policy into the service.

## Crossing sessions

- **`/handoff`** — when a thread is full or you need to branch off (e.g. into a `/prototype` session), this compacts the conversation into a markdown file. You don't continue in place — you **open a new session and reference that file** to carry the context across. It's the bridge between context windows, in either direction. Use it when you want a **fresh session** but need the **current conversation preserved**.
- **`/compact`** (built-in) — stay in the **same conversation**, letting the earlier turns be summarized. Use it at **intentional breaks between phases**, when you don't mind losing the verbatim history. Don't compact mid-phase — the agent can lose its way. `/handoff` forks; `/compact` continues.

## Standalone

Usable independently; some also support or detour from the main flow.

- **`/grill-me`** — the same relentless interview as `/grill-with-docs`, but for when you have **no codebase**. Stateless: it saves nothing locally, builds no `CONTEXT.md`. Reach for it to sharpen any plan or design that doesn't live in a repo.
- **`/prototype`** — a small, throwaway program that answers one design question: does this state model feel right, or what should this UI look like. Throwaway from day one — keep the answer, then delete or absorb the code. 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-qa`** — turn completed issue work into a local QA To Do session without mutating the source tracker.
- **`/resolving-merge-conflicts`** — resolve an in-progress Git merge or rebase by reconstructing both sides' intent and validating the result.
- **`/setup-pre-commit`** — add a Husky pre-commit pipeline for formatting, typechecking, and tests.
- **`/git-guardrails-opencode`** — block dangerous Git commands in OpenCode before they execute.
- **`/migrate-to-shoehorn`** — replace TypeScript `as` assertions in tests with `@total-typescript/shoehorn`.
- **`/scaffold-exercises`** — create structured exercise directories with problems, solutions, and explainers.
- **`/caveman`** — switch to ultra-compressed communication while retaining technical accuracy.
- **`/find-skills`** — discover and verify installable skills when a missing capability may already exist in the wider ecosystem.
- **`/opensrc`** — inspect the exact package or upstream repository source when source code, not documentation or memory, must settle the answer.
- **`/use-subagents-frequently`** — keep broad or parallelizable work out of the main context by delegating bounded independent slices.
- **`/write-a-skill`** — create a new skill with progressive disclosure and bundled resources.
- **`/teach`** — learn a concept over multiple sessions, using the current directory as a stateful workspace.
- **`/writing-great-skills`** — reference for writing and editing skills well.

## Precondition

**`/setup-agent-skills`** — run before your first engineering flow to configure the issue tracker, triage labels, and doc layout the other skills assume. It recommends Beads only when existing repo configuration actually uses Beads; otherwise it recommends `.scratch`. Hosted trackers are explicit opt-ins.