Ask Matt
You don't remember every skill, so ask.
Before stating what a skill does or recommending a step be skipped, read that skill's SKILL.md: the summaries here are for orientation only.
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.
- Choose the grill depth. Use
/grill-with-docs for the normal codebase-backed interview: it is stateful, retaining what it learns in CONTEXT.md and ADRs. Use /grill-for-unknowns instead only when the user explicitly requests its map-vs-territory pass, blindspot/unknown-unknown discovery, unknown-known prototypes, or a subagent launch packet; it owns that session's grilling loop, so do not also run /grilling or /grill-with-docs. (No codebase? Use /grill-me — see Standalone.)
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.
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, /clearing 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: 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, so go straight to /implement only when the effort turned out genuinely small.
Codebase health
Not feature work, just upkeep.
/improve-codebase-architecture runs 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 is 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 writes 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 compresses this context and seeds a fresh session with it. The default, at the bottom of the tree rather than the first reach.
Read 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 is 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.
/prototype is 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.
/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, since research feeds the thinking rather than replacing it.
/wizard plans human-driven setup only when explicitly invoked. Preserve its explicit-only metadata and the user authorization for credential writes; ordinary environment diagnosis does not invoke it.
/teach: learn a concept over multiple sessions, using the current directory as a stateful workspace.
/writing-great-skills is the kept snapshot for writing documents agents consume: skills, AGENTS.md, pointed-at docs. Upstream renamed this to writing-for-agents; Core does not vendor that successor.
/resolving-merge-conflicts works 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 finishes the operation. It never runs --abort. Standalone and off every flow: reach for it when you are already mid-conflict.
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.
1---2name: ask-matt-23description: Ask which skill or flow fits your situation. A router over the skills in this repo.4disable-model-invocation: true5metadata:6 source: https://skillmd.com/skills/asymmetric-al/ask-matt-27---89# Ask Matt1011You don't remember every skill, so ask.1213Before stating what a skill does or recommending a step be skipped, read that skill's SKILL.md: the summaries here are for orientation only.1415A **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.1617## The main flow: idea → ship1819The route most work travels. You have an idea and want it built.2021<!-- CORE-OVERLAY-START -->22231. **Choose the grill depth.** Use **`/grill-with-docs`** for the normal codebase-backed interview: it is stateful, retaining what it learns in `CONTEXT.md` and ADRs. Use **`/grill-for-unknowns` instead** only when the user explicitly requests its map-vs-territory pass, blindspot/unknown-unknown discovery, unknown-known prototypes, or a subagent launch packet; it owns that session's grilling loop, so do not also run `/grilling` or `/grill-with-docs`. (No codebase? Use `/grill-me` — see Standalone.)2425<!-- CORE-OVERLAY-END -->26272. **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):28 - **`/handoff`** out, then open a fresh session against that file,29 - **`/prototype`** to answer the question with throwaway code,30 - **`/handoff`** back what you learned, and reference it from the original idea thread.31323. **Branch: is this a multi-session build?**33 - **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.34 - **No** → **`/implement`** right here, in the same context window.3536 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.3738### Context hygiene3940Keep 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.4142The 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).4344## On-ramps4546A starting situation that generates work, then merges onto the main flow.4748- **Bugs and requests piling up** → **`/triage`**. It moves issues through triage roles and produces agent-ready issues, which **`/implement`** later picks up.4950 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**.5152- **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.5354- **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.5556 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, so go straight to `/implement` only when the effort turned out genuinely small.5758## Codebase health5960Not feature work, just upkeep.6162- **`/improve-codebase-architecture`** runs 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.6364## Vocabulary underneath6566Two 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.6768- **`/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.69- **`/codebase-design`** is 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.7071## Phase boundaries7273A **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:7475- **Continue**: stay put. Costs nothing, loses nothing.76- **`/clear`**: empty the window, when nothing here matters to what's next.77- **`/handoff`** writes 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.78- **Subagent**: send a tightly-scoped task to its own window and get a report back.79- **`/compact`** compresses this context and seeds a fresh session with it. The **default**, at the bottom of the tree rather than the first reach.8081Read [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.8283## Standalone8485Off the main flow entirely.8687- **`/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.88- **`/grilling`** is 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.89- **`/prototype`** is 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.90- **`/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`, since research feeds the thinking rather than replacing it.91- **`/wizard`** plans human-driven setup only when explicitly invoked. Preserve its explicit-only metadata and the user authorization for credential writes; ordinary environment diagnosis does not invoke it.92- **`/teach`**: learn a concept over multiple sessions, using the current directory as a stateful workspace.93- **`/writing-great-skills`** is the kept snapshot for writing documents agents consume: skills, AGENTS.md, pointed-at docs. Upstream renamed this to writing-for-agents; Core does not vendor that successor.94- **`/resolving-merge-conflicts`** works 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 finishes the operation. It never runs `--abort`. Standalone and off every flow: reach for it when you are already mid-conflict.9596## Precondition9798**`/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.