菜单
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Recurring maintenance pass over automated dependency-bump PRs (Dependabot, Renovate, or similar) — rebase, relock, verify, and report what's ready to merge. Meant to be handed to a time-based loop or schedule, not run once.
Post-deploy verification loop — poll a rollout until every instance is on the new version and healthy, then run one smoke check against a real user path. Meant to be handed to a time-based loop with a timeout, not polled by hand.
Reference for designing agent loops — cycles of work that repeat until a stop condition is met. Covers the four loop shapes, writing completion criteria, carrying state and isolating work across cycles, and what running unattended still leaves on you.
Recurring check-in on a stack of dependent PRs — rebase children onto updated parents, surface CI state, flag anything waiting on a human-only gate, and report only what changed since last time. Meant to be handed to a time-based loop, not run once.
Pick the skill or flow that fits your situation. A router over the skills in this repo.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
| name | setup-skills |
| description | Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills. |
| disable-model-invocation | true |
Lay down the per-repo configuration the engineering skills rely on:
CONTEXT.md and ADRs live, and how consumers should read themThis is prompt-driven, not a deterministic script. Explore, show what you found, confirm with the user, then write.
Inspect the repo to learn its starting state. Read what's actually there rather than assuming:
git remote -v and .git/config — is this a GitHub repo? Which one?AGENTS.md and CLAUDE.md at the repo root — does either exist? Does either already carry an ## Agent skills section?CONTEXT.md and CONTEXT-MAP.md at the repo rootdocs/adr/ and any src/*/docs/adr/ directoriesdocs/agents/ — has this skill already produced output here?.scratch/ — a sign a local-markdown issue tracker convention is already in playSummarise what exists and what's missing. Then walk the user through the three decisions one at a time — show a section, take the user's answer, then move on. Don't dump all three at once.
Assume the user hasn't met these terms before. Open each section with a short explainer (what it is, why these skills need it, what shifts if they choose otherwise). Then lay out the choices and the default.
Section A — Issue tracker.
Explainer: The "issue tracker" is where this repo's issues live. Skills like
to-issues,triage, andto-prdread from and write to it — they need to know whether to reach forgh issue create, drop a markdown file under.scratch/, or follow some other workflow you describe. Pick the place you genuinely track work for this repo.
Default posture: these skills were built for GitHub. If a git remote points at GitHub, propose that. If a git remote points at GitLab (gitlab.com or a self-hosted host), propose GitLab. Otherwise (or if the user prefers), offer:
gh CLI)glab CLI).scratch/<feature>/ in this repo (good for solo projects or repos without a remote)If — and only if — the user picked GitHub or GitLab, ask one follow-up:
Explainer: Open-source repos often get feature requests as pull requests, not just issues — a PR is an issue with code attached. Turn this on and
/triagefolds external PRs into the same queue, running them through the same labels and states as issues (collaborators' in-flight PRs are left alone). Leave it off if PRs aren't a request surface for you.
docs/agents/issue-tracker.md. For local-markdown and other trackers, skip this question — there are no PRs.Section B — Triage label vocabulary.
Explainer: When the
triageskill handles an incoming issue, it walks it through a state machine — needs evaluation, waiting on reporter, ready for an AFK agent to grab, ready for a human, or won't fix. To do that it applies labels (or your tracker's equivalent) that match strings you've actually set up. If your repo already uses different names (saybug:triageinstead ofneeds-triage), map them here so the skill reaches for the right ones instead of minting duplicates.
The five canonical roles:
needs-triage — maintainer needs to evaluateneeds-info — waiting on reporterready-for-agent — fully specified, AFK-ready (an agent can grab it with no human context)ready-for-human — needs human implementationwontfix — will not be actionedDefault: each role's string equals its name. Ask whether the user wants to override any. If their tracker has no existing labels, the defaults are fine.
Section C — Domain docs.
Explainer: Some skills (
improve-codebase-architecture,diagnosing-bugs,tdd) read aCONTEXT.mdfile to pick up the project's domain language, anddocs/adr/for past architectural decisions. They need to know whether the repo runs one global context or several (say a monorepo with separate frontend/backend contexts) so they look in the right place.
Confirm the layout:
CONTEXT.md + docs/adr/ at the repo root. Most repos are this.CONTEXT-MAP.md at the root pointing to per-context CONTEXT.md files (typically a monorepo).Show the user a draft of:
## Agent skills block to add to whichever of CLAUDE.md / AGENTS.md you're editing (selection rules in step 4)docs/agents/issue-tracker.md, docs/agents/triage-labels.md, docs/agents/domain.mdLet them edit before you write.
Pick the file to edit:
CLAUDE.md exists, edit it.AGENTS.md exists, edit it.Never create AGENTS.md when CLAUDE.md already exists (or vice versa) — always edit the one already there.
If an ## Agent skills block already exists in the chosen file, update its contents in place rather than appending a duplicate. Leave the user's edits to the surrounding sections alone.
The block:
## Agent skills
### Issue tracker
[one-line summary of where issues are tracked, plus whether external PRs are a triage surface]. See `docs/agents/issue-tracker.md`.
### Triage labels
[one-line summary of the label vocabulary]. See `docs/agents/triage-labels.md`.
### Domain docs
[one-line summary of layout — "single-context" or "multi-context"]. See `docs/agents/domain.md`.
Then write the three docs files, seeding them from the templates in this skill folder:
For "other" issue trackers, write docs/agents/issue-tracker.md from scratch out of the user's description.
Tell the user setup is complete and which engineering skills will now read from these files. Note that they can edit docs/agents/*.md directly later — re-running this skill is only needed to switch issue trackers or start over.