/crew-skill
AGENT_TEMPLATE.md states the contract for a component. Full installs carry it (refreshed on update); the
plugin edition does not. No gate routes to it, so this command is the route, and it ends in the gates.
A component is not finished when it is written. It is finished when the suite says so.
1. Decide the shape before writing anything
Read .claude/AGENT_TEMPLATE.md. Then answer, in one line each:
- What is the smallest form that works? A rule in an existing skill's body beats a new skill; a new skill beats
a new agent. Every new skill costs its NAME in every session, forever, for every user — and its description too,
until the listing overflows its budget, at which point descriptions start being dropped from the skills you
invoke least. Say what that buys.
- Who reaches it? An agent, a command, or the discipline's trigger map. If the answer is "the model will notice
the description", stop — that is the dark component §3b exists to catch.
- Read or write? A component that reports and a component that changes files do not belong together: different
risk, different done-criterion. Split them.
- Is it stack-neutral? Anything shipped to every profile names no language, framework or vendor as the case.
The example you have in mind is not the scope.
2. Write it
- Skill:
.claude/skills/<name>/SKILL.md — the directory name and the name: field must match. Keep the body
lean; depth goes to references/*.md and is loaded on demand.
- Agent: a thin trigger — who and when. The how lives in the skill it applies; do not copy the method in.
- The
description says when to reach for this, not what its author knows.
3. Register it — the cascade, in this order
Skipping one of these is how a component ships half-installed:
- Route it. Name it in an agent body, a command, or the trigger map. §3b checks exactly this.
- Golden case. Add a positive line to
.claude/eval/golden-routing.txt — and a negative one
(prompt|!target) for a neighbour it must NOT steal.
- Catalog + counts (Crewforth repository only —
packaging/ is not installed anywhere).
Add the Turkish summary line (packaging/skill-summaries.tr.tsv; agents and commands have their own .tr.tsv),
which the site build requires (cd site && npm ci && npm run build), and the diagrams if the component set changed:
node packaging/gen-diagrams.mjs writes assets/, and smoke fails while any of them is stale.
- Plugin edition (Crewforth repository only).
bash packaging/build-plugin.sh — in the same commit, or the
release stops at the sync gate.
- Budget. A new skill moves
BUDGET_SKILL_LISTING (the skill listing in characters, counted like Claude Code
counts it; /crew-doctor reports the same number). Raise it in the same commit with the justification comment the
file's convention requires. Never raise it to make a red gate green without saying why.
4. Prove it — run all four, in this order, with the Bash tool, not PowerShell
bash .claude/eval/scan-skill.sh .claude/skills/<name> # supply-chain: SAFE, and rc=3 means NOT scanned
bash .claude/eval/routing-eval.sh # the golden case, positive and negative
bash .claude/eval/smoke-test.sh # structure, budget, §3b routed, cross-links
CREW_NO_STAR=1 bash .claude/eval/doctor.sh # the live install still healthy (star line off here)
In the plugin edition none of the four commands above exist — it ships no eval/ scripts — so there the proof is
the Crewforth repository's own suite, not a local run.
Do not finish while §3b is red. "It works when I invoke it by name" is not the claim being tested — the claim
is that something reaches it without being told to. If the suite skips a case, that is not a pass: chase why.
1---2name: crew-skill3description: Author or change a Crewforth component (skill / agent / command) against the template and its gates.4disable-model-invocation: true5metadata:6 source: https://skillmd.com/skills/byerlikaya/crew-skill7 kind: command8---910# /crew-skill1112`AGENT_TEMPLATE.md` states the contract for a component. Full installs carry it (refreshed on `update`); the13plugin edition does not. No gate routes to it, so this command is the route, and it ends in the gates.1415**A component is not finished when it is written. It is finished when the suite says so.**1617## 1. Decide the shape before writing anything18Read `.claude/AGENT_TEMPLATE.md`. Then answer, in one line each:1920- **What is the smallest form that works?** A rule in an existing skill's body beats a new skill; a new skill beats21 a new agent. Every new skill costs its NAME in every session, forever, for every user — and its description too,22 until the listing overflows its budget, at which point descriptions start being dropped from the skills you23 invoke least. Say what that buys.24- **Who reaches it?** An agent, a command, or the discipline's trigger map. If the answer is "the model will notice25 the description", stop — that is the dark component §3b exists to catch.26- **Read or write?** A component that reports and a component that changes files do not belong together: different27 risk, different done-criterion. Split them.28- **Is it stack-neutral?** Anything shipped to every profile names no language, framework or vendor as *the* case.29 The example you have in mind is not the scope.3031## 2. Write it32- Skill: `.claude/skills/<name>/SKILL.md` — the directory name and the `name:` field must match. Keep the body33 lean; depth goes to `references/*.md` and is loaded on demand.34- Agent: a thin trigger — *who and when*. The *how* lives in the skill it applies; do not copy the method in.35- The `description` says **when to reach for this**, not what its author knows.3637## 3. Register it — the cascade, in this order38Skipping one of these is how a component ships half-installed:391. **Route it.** Name it in an agent body, a command, or the trigger map. §3b checks exactly this.402. **Golden case.** Add a positive line to `.claude/eval/golden-routing.txt` — and a **negative** one41 (`prompt|!target`) for a neighbour it must NOT steal.423. **Catalog + counts** *(Crewforth repository only — `packaging/` is not installed anywhere)*.43 Add the Turkish summary line (`packaging/skill-summaries.tr.tsv`; agents and commands have their own `.tr.tsv`),44 which the site build requires (`cd site && npm ci && npm run build`), and the diagrams if the component set changed:45 `node packaging/gen-diagrams.mjs` writes `assets/`, and smoke fails while any of them is stale.464. **Plugin edition** *(Crewforth repository only)*. `bash packaging/build-plugin.sh` — in the same commit, or the47 release stops at the sync gate.485. **Budget.** A new skill moves `BUDGET_SKILL_LISTING` (the skill listing in characters, counted like Claude Code49 counts it; `/crew-doctor` reports the same number). Raise it in the same commit with the justification comment the50 file's convention requires. Never raise it to make a red gate green without saying why.5152## 4. Prove it — run all four, in this order, with the Bash tool, not PowerShell53```54bash .claude/eval/scan-skill.sh .claude/skills/<name> # supply-chain: SAFE, and rc=3 means NOT scanned55bash .claude/eval/routing-eval.sh # the golden case, positive and negative56bash .claude/eval/smoke-test.sh # structure, budget, §3b routed, cross-links57CREW_NO_STAR=1 bash .claude/eval/doctor.sh # the live install still healthy (star line off here)58```5960In the plugin edition none of the four commands above exist — it ships no `eval/` scripts — so there the proof is61the Crewforth repository's own suite, not a local run.6263**Do not finish while §3b is red.** "It works when I invoke it by name" is not the claim being tested — the claim64is that something reaches it without being told to. If the suite skips a case, that is not a pass: chase why.