Ask Utarn
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.
/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.) Prefer /grill-novice when the technical decisions feel like the agent's call, not yours: it asks only the functional requirements, in plain simplified English, and recaps its technical assumptions for your veto before writing anything.
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.
When the raw reports land on a separate public tracker repo — users and testers filing against a shipped product, code living elsewhere — /bug-tracker works that queue instead (see Utarn-specific extras).
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 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, /grill-with-docs and /grill-novice are the three 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./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. User-invoked, so you type it when a human is genuinely in the loop; if the agent could just do it itself, it should. Still in the in-progress/ bucket, so it's not in the plugin — install it directly if you want it./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.
Utarn-specific extras
This fork keeps a few skills that the upstream router above doesn't route to. They overlap the main-flow skills but stay available for the workflows they were tuned for:
/to-prd — like /to-spec, but writes a PRD-shaped document. Kept for repos that already use the PRD vocabulary./to-issues and /to-issues-yes — like /to-tickets, but split a plan/spec/PRD into independently-grabbable issues using vertical slices (and /to-issues-yes publishes them straight to the project issue tracker as tracer-bullet issues). Predecessors of /to-tickets; reach for them when you want the older issue-splitting behaviour./to-tickets-yes — the assume-yes variant of /to-tickets: same tracer-bullet tickets with blocking edges, but it skips the approval round and publishes straight to the configured tracker. Reach for it when the breakdown is routine enough to trust without a back-and-forth./to-spec-yes — the assume-yes variant of /to-spec: same spec synthesis and publishing, but it takes the proposed seams as agreed instead of checking them with you. Reach for it when the seams are routine (an existing seam, placed where you'd place it); the spec's Testing Decisions section still records them, so the assumption stays visible./setup-utarn-skills-yes — the assume-defaults variant of /setup-utarn-skills: it derives every choice from the repo itself (remote → tracker, default triage labels, monorepo signals → doc layout) and writes the configuration without a confirmation round. Reach for it on a fresh repo where the defaults are what you'd pick anyway; run the interactive /setup-utarn-skills when you want a say in any of the three, or need a custom tracker like Jira/Linear./find-mismatch — a focused code review that hunts for bugs that break at runtime, plus JS/TS static analysis via fallow. A narrower alternative to /code-review when you specifically want mismatch-detection and static checks, not the two-axis Standards/Spec review./work-on-issues — fetch, implement, and close GitHub/GitLab issues sequentially (one main issue starting with PRD:/feat: at a time). An end-to-end issue driver that wraps the implement → review → close loop for tracked issues./bug-tracker and /init-bug-tracker — the public-tracker pair, for reports that arrive where the code doesn't live. /init-bug-tracker creates the tracker's full label taxonomy — states, types, priorities, verification, plus area:* labels derived from your repo — seeds its issue forms, and records the tracker in the ## Agent skills config. /bug-tracker then works the actionable queue one issue at a time: investigating and verifying reports with attachments, tagging, marking in-progress, solving issues via isolated subagents (similar to work-on-issues), posting resolution summaries back to the public tracker, and marking resolved and closing them. The public-tracker counterpart to /work-on-issues and /triage.
Precondition
/setup-utarn-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-utarn3description: Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.4---56# Ask Utarn78You don't remember every skill, so ask.910A **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.1112## The main flow: idea → ship1314The route most work travels. You have an idea and want it built.15161. **`/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.) Prefer **`/grill-novice`** when the technical decisions feel like the agent's call, not yours: it asks only the functional requirements, in plain simplified English, and recaps its technical assumptions for your veto before writing anything.172. **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):18 - **`/handoff`** out, then open a fresh session against that file,19 - **`/prototype`** to answer the question with throwaway code,20 - **`/handoff`** back what you learned, and reference it from the original idea thread.213. **Branch — is this a multi-session build?**22 - **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.23 - **No** → **`/implement`** right here, in the same context window.2425 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.2627### Context hygiene2829Keep 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.3031The 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).3233## On-ramps3435A starting situation that generates work, then merges onto the main flow.3637- **Bugs and requests piling up** → **`/triage`**. It moves issues through triage roles and produces agent-ready issues, which **`/implement`** later picks up.3839 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**.4041 When the raw reports land on a **separate public tracker repo** — users and testers filing against a shipped product, code living elsewhere — **`/bug-tracker`** works that queue instead (see Utarn-specific extras).4243- **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.4445- **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.4647 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.4849## Codebase health5051Not feature work — upkeep.5253- **`/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.5455## Vocabulary underneath5657Two 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.5859- **`/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.60- **`/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.6162## Phase boundaries6364A **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:6566- **Continue** — stay put. Costs nothing, loses nothing.67- **`/clear`** — empty the window, when nothing here matters to what's next.68- **`/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.69- **Subagent** — send a tightly-scoped task to its own window and get a report back.70- **`/compact`** — compress this context and seed a fresh session with it. The **default**, at the bottom of the tree rather than the first reach.7172Read [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.7374## Standalone7576Off the main flow entirely.7778- **`/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.79- **`/grilling`** — the interview primitive itself: rounds, the frontier, facts are the agent's job and decisions are yours. `/grill-me`, `/grill-with-docs` and `/grill-novice` are the three 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.80- **`/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.81- **`/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.82- **`/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.83- **`/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`.84- **`/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. User-invoked, so you type it when a human is genuinely in the loop; if the agent could just do it itself, it should. Still in the `in-progress/` bucket, so it's not in the plugin — install it directly if you want it.85- **`/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.86- **`/teach`** — learn a concept over multiple sessions, using the current directory as a stateful workspace.87- **`/writing-for-agents`** — reference for writing documents agents consume: skills, AGENTS.md, pointed-at docs.8889## Utarn-specific extras9091This fork keeps a few skills that the upstream router above doesn't route to. They overlap the main-flow skills but stay available for the workflows they were tuned for:9293- **`/to-prd`** — like `/to-spec`, but writes a PRD-shaped document. Kept for repos that already use the PRD vocabulary.94- **`/to-issues`** and **`/to-issues-yes`** — like `/to-tickets`, but split a plan/spec/PRD into independently-grabbable issues using vertical slices (and `/to-issues-yes` publishes them straight to the project issue tracker as tracer-bullet issues). Predecessors of `/to-tickets`; reach for them when you want the older issue-splitting behaviour.95- **`/to-tickets-yes`** — the assume-yes variant of `/to-tickets`: same tracer-bullet tickets with blocking edges, but it skips the approval round and publishes straight to the configured tracker. Reach for it when the breakdown is routine enough to trust without a back-and-forth.96- **`/to-spec-yes`** — the assume-yes variant of `/to-spec`: same spec synthesis and publishing, but it takes the proposed seams as agreed instead of checking them with you. Reach for it when the seams are routine (an existing seam, placed where you'd place it); the spec's Testing Decisions section still records them, so the assumption stays visible.97- **`/setup-utarn-skills-yes`** — the assume-defaults variant of `/setup-utarn-skills`: it derives every choice from the repo itself (remote → tracker, default triage labels, monorepo signals → doc layout) and writes the configuration without a confirmation round. Reach for it on a fresh repo where the defaults are what you'd pick anyway; run the interactive `/setup-utarn-skills` when you want a say in any of the three, or need a custom tracker like Jira/Linear.98- **`/find-mismatch`** — a focused code review that hunts for bugs that break at runtime, plus JS/TS static analysis via `fallow`. A narrower alternative to `/code-review` when you specifically want mismatch-detection and static checks, not the two-axis Standards/Spec review.99- **`/work-on-issues`** — fetch, implement, and close GitHub/GitLab issues sequentially (one main issue starting with `PRD:`/`feat:` at a time). An end-to-end issue driver that wraps the implement → review → close loop for tracked issues.100- **`/bug-tracker`** and **`/init-bug-tracker`** — the public-tracker pair, for reports that arrive where the code doesn't live. `/init-bug-tracker` creates the tracker's full label taxonomy — states, types, priorities, verification, plus `area:*` labels derived from your repo — seeds its issue forms, and records the tracker in the `## Agent skills` config. `/bug-tracker` then works the actionable queue one issue at a time: investigating and verifying reports with attachments, tagging, marking in-progress, solving issues via isolated subagents (similar to `work-on-issues`), posting resolution summaries back to the public tracker, and marking resolved and closing them. The public-tracker counterpart to `/work-on-issues` and `/triage`.101102## Precondition103104**`/setup-utarn-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.
utarn