which-skill
Skill13 starsChanged 4 months agoMITView on GitHub
Ask which skill or flow fits your situation. A router over the skills in this repo.
12 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- paureis/pau-skillstheir own version, first seen Nov 8, 2026
- leek/agent-skillstheir own version, first seen Nov 2, 2026
- aayushchugh/skillstheir own version, first seen Nov 1, 2026
- TanKaizokuO/claude-skillstheir own version, first seen Oct 20, 2026
- eyeix/skillstheir own version, first seen Oct 13, 2026
- karina-yjm/which-skilltheir own version, first seen Oct 11, 2026
Used with
Projects with it also use resolving-merge-conflicts, to-issues and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GoogleSkillresolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
Also in 3 projects that use this
GoogleSkillto-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
Also in 3 projects that use this
- +3 more from google
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- officialunofficial/skills★ 721% same
Wrote their own version · 11
- leek/agent-skills★ 5same name
- aayushchugh/skills★ 4same name
- icetomoyo/CodingSkills★ 4same name
- dhanji4U/skills★ 2same name
- mik2win/foureyes★ 2same name
- paureis/pau-skills★ 2same name
- risadams/ink-and-agency★ 2same name
- eyeix/skills★ 1same name
- karina-yjm/which-skill★ 1same name
- OmarBenje/whichskill★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- codebase-designSkill
- debugSkill
- domain-modelingSkill
- grillingSkill
- grill-plainSkill
- grillSkill
- handoffSkill
- implementSkill
- improve-archSkill
- prototypeSkill
- reconcileSkill
- researchSkill
- setup-okf-matt-skillsSkill
- tddSkill
- teachSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- vetSkill
- wayfinderSkill
- write-skillSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Branch — can you settle every question in conversation?: If a question needs a runnable answer (state, business logic, a UI you have to …
- Very specific: line 30
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 …
- Distinctive: line 48
Not feature work — upkeep.
“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Which skill?
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— sharpen the idea by interview. Start here when you have a codebase: it's stateful, retaining what it learns in the OKF knowledge bundle (knowledge/— glossary and ADRs). (No codebase? Use/grill-plain— see Standalone. Both run the same/grillingprimitive;grillis the one that leaves a paper trail.)- 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
/handoffin both directions (see Crossing sessions):/handoffout, then open a fresh session against that file,/prototypeto answer the question with throwaway code,/handoffback 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-ticketsto split it into tracer-bullet tickets, each declaring its blocking edges. On a local tracker that's an orderedtickets.mdyou work by hand; on a real tracker the edges become native blocking links, so any ticket whose blockers are done can be grabbed — kick off/implementper ticket, clearing context between each one. - No →
/implementright here, in the same context window.
Either way,
/implementbuilds each ticket by driving/tddinternally — one red-green slice at a time — then closes out by running/vet(a two-axis review — Standards + Spec — of the diff) and/reconcile(which brings the OKF bundle back into agreement with what was built), before committing code and knowledge together. Reach for/tddon its own when you just want to build a concrete behaviour test-first without a full spec, and/veton its own whenever you want to review a branch or PR against a fixed point.- Yes →
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 (~120k 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 — /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/implementlater picks up.Triage is only for issues you didn't create — bug reports, incoming feature requests, anything that arrives raw. Tickets that
/to-ticketsproduced are already agent-ready, so don't triage them.- Something's broken →
/debug. 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-archwhen 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 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. Then it merges onto the main flow at/to-spec(or, if the effort turned out small enough, straight to/implement). Where/grillsharpens an idea you can hold in one session, wayfinder is for the idea you can't.
Codebase health
Not feature work — upkeep.
/improve-arch— 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. 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/grilldrives to keep the knowledge bundle's glossary (knowledge/glossary/) clean. It writes the bundle on the design side;/reconcileis its build-side mirror — after/implement(or a bug fix, or a hand refactor) lands code, it re-syncs the bundle to what was actually built so knowledge doesn't drift between sessions./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./tddand/improve-archboth speak it.
Crossing sessions
/handoff— when a thread is full or you need to branch off (e.g. into a/prototypesession), 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./handoffforks;/compactcontinues.
Standalone
Off the main flow entirely.
/grill-plain— the same relentless interview as/grill, but for when you have no codebase. Stateless: it saves nothing locally, builds no knowledge bundle. 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, delete 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— research feeds the thinking, it doesn't replace it./teach— learn a concept over multiple sessions, using the current directory as a stateful workspace./write-skill— reference for writing and editing skills well.
Precondition
/setup-okf-matt-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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

