菜单
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
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
| name | triage |
| description | Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs. |
| disable-model-invocation | true |
Walk issues on the project issue tracker through a small state machine of triage roles.
If this repo treats external pull requests as a request surface (see the issue-tracker config), triage covers them too: a PR is an issue with code attached — same roles, same states, same machine, with a handful of deltas marked "for a PR" below. Resolve a bare #42 to an issue or PR per the tracker config.
Every comment or issue posted to the issue tracker during triage must open with this disclaimer:
> *This was generated by AI during triage.*
.out-of-scope/ knowledge base worksTwo category roles:
bug — something is brokenenhancement — new feature or improvementFive state roles:
needs-triage — maintainer needs to evaluateneeds-info — waiting on reporter for more informationready-for-agent — fully specified, ready for an AFK agentready-for-human — needs human implementationwontfix — will not be actionedFor a PR, the same states read against the attached code: ready-for-agent means a brief is attached and an agent should take the next step on the diff; ready-for-human means it's ready for a human to merge.
Every triaged issue carries exactly one category role and one state role. If state roles conflict, flag it and ask the maintainer before doing anything else.
These are canonical role names — the label strings your issue tracker actually uses may differ. The mapping should already have been handed to you — run /setup-skills if not.
State transitions: an unlabeled issue usually enters at needs-triage; from there it moves to needs-info, ready-for-agent, ready-for-human, or wontfix. needs-info returns to needs-triage once the reporter replies. The maintainer can override at any point — flag any transition that looks unusual and ask before proceeding.
The maintainer invokes /triage and describes what they want in natural language. Read the request and act. Examples:
Query the issue tracker and present three buckets, oldest first:
needs-triage — evaluation in progress.needs-info with reporter activity since the last triage notes — due for re-evaluation.When PRs are in scope, fold external PRs into these buckets and tag each line [PR] or [issue]. Discovery surfaces only external PRs (the tracker config defines who counts as external) — a collaborator's in-flight PR isn't triage work. That filter is discovery-only; an explicitly named PR is always triaged, whoever authored it.
Show counts and a one-line summary per item. Let the maintainer choose.
Gather context. Read the whole issue or PR (body, comments, labels, author, dates; for a PR, the diff too). Parse any prior triage notes so you don't re-ask settled questions. Explore the codebase through the project's domain glossary, respecting ADRs in the area. Run two checks against the codebase: (a) redundancy — search for an existing implementation of the requested behaviour by domain concept (not just the request's wording), and report where you looked. If you find one, it's an already-implemented wontfix (step 5). (b) prior rejection — read .out-of-scope/*.md and surface any that resembles this request.
Recommend. Give the maintainer your category and state recommendation with reasoning, plus a short codebase summary relevant to the request — including whether it's already implemented. Wait for direction.
Verify the claim. Before any grilling, confirm the claim holds. For a bug, reproduce it from the reporter's steps. For a PR, confirm the diff does what it claims — check it out, run the relevant tests or commands. Report what happened: confirmed (with the code path), failed, or too thin to tell (a strong needs-info signal). A confirmed verification makes a far stronger agent brief.
Grill (if needed). If the request needs fleshing out, run the /grilling and /domain-modeling skills together — grill it into shape one question at a time, sharpening domain terms and updating CONTEXT.md/ADRs inline as decisions land.
Apply the outcome:
ready-for-agent — post an agent brief comment (AGENT-BRIEF.md).ready-for-human — same structure as an agent brief, but note why it can't be delegated (judgment calls, external access, design decisions, manual testing).needs-info — post triage notes (template below).wontfix — close, with the comment depending on why:
.out-of-scope/ (that KB holds rejected requests, not built ones)..out-of-scope/, link to it from a comment, then close (OUT-OF-SCOPE.md).needs-triage — apply the role. Add a comment if there's partial progress worth recording.If the maintainer says "move #42 to ready-for-agent", trust them and apply the role directly. Confirm what you're about to do (role changes, comment, close), then act. Skip grilling. If you're moving to ready-for-agent without a grilling session, ask whether they want an agent brief written.
## Triage Notes
**What we've established so far:**
- point 1
- point 2
**What we still need from you (@reporter):**
- question 1
- question 2
Capture everything settled during grilling under "established so far" so the work isn't lost. Questions must be specific and actionable, never "please provide more info".
If prior triage notes sit on the issue or PR, read them, check whether the reporter has answered any open questions, and present an updated picture before continuing. Don't re-ask settled questions.
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".