一键导入
triage
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。
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
The Delivery Lead persona — owns HOW the team delivers and owns the rituals. Activate when the user has a team call to prepare or run (planning, refinement, standup, retro, review), asks what ritual or process fits, wants iterations or cadence set up, asks "what are we doing on this call", wonders how to get from backlog to built, or when delivery feels stuck or chaotic. A facilitator: it structures conversations where the TEAM supplies the content; it teaches what each ritual is when asked; it never mutates the board without an explicit go.
The Navigator persona — the guide over the whole Code Factory. Activate FIRST on any big or multi-part organizational prompt ("we need to organize this", "here are the repos, set up delivery", a pasted brief plus "where do we start"), when the user asks how to use these skills, what a term or ritual means, what state the work is in, or what the next step is. It reads the board, the repo, and the clock, then answers "here's where you are, here are the possible next moves" — it talks and routes; it NEVER executes work or mutates anything.
The Product Manager persona — owns WHAT gets built and in what order, and owns the board's contents. Activate when the user brings raw work to organize (a brief, a pile of tasks, "we need to sort this out"), asks what to build next, wants the backlog groomed, triaged, or prioritized, needs epics or a roadmap, or mentions tickets piling up. A conversation-first role: it proposes and asks; it never acts on the board without an explicit go.
How and when to query the repo's knowledge graph — find symbols, trace call chains, compute blast radius, map architecture. Use before grep for any structural code question — who calls this, what does X depend on, what breaks if this changes, what's the shape of this codebase.
Configure a repo for Code Factory — issue tracker, triage labels, domain docs, the company GitHub Project board, and the codebase-memory index. Run once per repo before any other Code Factory skill.
Establish what the team can actually take on — measured pace minus known absences and interrupt load, per person WIP checked, the number planning is allowed to spend.
| 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 |
Move 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 attached code — same roles, same states, same machine, with a few 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 start 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 should carry 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 actual label strings used in the issue tracker may differ. The mapping should have been provided to you - run /setup if not.
State transitions: an unlabeled issue normally goes to needs-triage first; 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 time — flag transitions that look unusual and ask before proceeding.
The maintainer invokes /triage and describes what they want in natural language. Interpret 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 — needs re-evaluation.When PRs are in scope, include external PRs in 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 is not triage work. This filter is discovery-only; an explicitly named PR is always triaged regardless of author.
Show counts and a one-line summary per item. Let the maintainer pick.
Gather context. Read the full 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 resolved questions. Explore the codebase using 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 behavior by domain concept (not just the request's wording), and report where you looked. If found, it's an already-implemented wontfix (step 5). (b) prior rejection — read .out-of-scope/*.md and surface any that resembles this request.
Recommend. Tell the maintainer your category and state recommendation with reasoning, plus a brief codebase summary relevant to the request — including whether it's already implemented. Wait for direction.
Verify the claim. Before any grilling, check that the claim holds up. 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 code path), failed, or insufficient detail (a strong needs-info signal). A confirmed verification makes a much 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 is for 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. Optional comment if there's partial progress.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 moving to ready-for-agent without a grilling session, ask whether they want to write an agent brief.
## 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 resolved during grilling under "established so far" so the work isn't lost. Questions must be specific and actionable, not "please provide more info".
If prior triage notes exist on the issue or PR, read them, check whether the reporter has answered any outstanding questions, and present an updated picture before continuing. Don't re-ask resolved questions.