triage
- 信任分
- 88/100
- 兼容 Agent
- 1
- 领域
- 工程开发
- 兼容 Agent
- Claude Code
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @mattpocock · 未声明 license
- 安装命令数
- 1 条
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
想读作者英文原文? ↓ 滚到正文区切换 · 在 GitHub 查看 ↗
triage 把项目 issue tracker 当成一个小状态机来跑:每条 issue 永远恰好挂一个 category 标签 + 一个 state 标签,agent 用本技能在状态间挪 issue。triage 期间所有 comment 与 issue 必须以 > *This was generated by AI during triage.* 开头——透明地标记 AI 出处。
设计思路
作者的目标:让维护者用「这看一下」、"#42 该 ready-for-agent 了"这种自然语言指令,技能就能把状态机推进;同时强制让 issue 永远停在一个明确状态,避免「triage 一半丢着」的中间态。
角色(标签)
两个 category:bug(坏了)/ enhancement(新功能 / 改进)。五个 state:needs-triage(待评估)、needs-info(等 reporter 补充)、ready-for-agent(已规约清楚、AFK agent 可拿)、ready-for-human(必须人来)、wontfix。每条 issue 必须恰好一个 category + 一个 state;冲突就 flag 并问维护者。canonical 名是统一的,实际项目里 label 字符串可能不同——映射由 /setup-matt-pocock-skills 提供。
状态迁移
未标记 → needs-triage → needs-info / ready-for-agent / ready-for-human / wontfix。needs-info 收到 reporter 回复后回 needs-triage 再评估。维护者随时可 override 任何转换;遇到看着不寻常的转移先 flag再做。
调用方式
维护者打 /triage + 自然语言:「Show me anything that needs my attention」「Let's look at #42」「Move #42 to ready-for-agent」「What's ready for agents to pick up?」——技能解释意图后行动。
"需要关注" 三桶
按 oldest-first 列:① Unlabeled(从未 triage);② needs-triage(评估中);③ needs-info 但 reporter 在最近 triage notes 后有活动(要重评估)。每桶给计数 + 每条一行摘要,让维护者挑。
单条 issue 处理
Gather context:完整读 body / comments / labels / reporter / 时间,解析此前 triage notes 避免重复问;探代码用项目领域术语、尊重该区域 ADR;据此提议下一步。
适合谁
- 接 GitHub / GitLab issue 的开源 / 内部项目
- 维护者想「打字驱动 triage」而不必点 GitHub UI
- 多 agent 协作希望 AFK / HITL 边界清晰
何时不要用
- 没有 issue tracker:本技能假设 GitHub / GitLab / 兼容 API
- 单 issue 简单到跑流程更慢:直接改 label 即可
配套
to-issues(拆 issue)、to-prd(写 PRD 后发 issue)、setup-matt-pocock-skills(label 字符串前置映射)、receiving-code-review(同体系的 review 纪律)。
Triage
Move issues on the project issue tracker through a small state machine of triage roles.
Every comment or issue posted to the issue tracker during triage must start with this disclaimer:
> *This was generated by AI during triage.*
Reference docs
- AGENT-BRIEF.md — how to write durable agent briefs
- OUT-OF-SCOPE.md — how the
.out-of-scope/knowledge base works
Roles
Two category roles:
bug— something is brokenenhancement— new feature or improvement
Five 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 actioned
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-matt-pocock-skills 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.
Invocation
The maintainer invokes /triage and describes what they want in natural language. Interpret the request and act. Examples:
- "Show me anything that needs my attention"
- "Let's look at #42"
- "Move #42 to ready-for-agent"
- "What's ready for agents to pick up?"
Show what needs attention
Query the issue tracker and present three buckets, oldest first:
- Unlabeled — never triaged.
needs-triage— evaluation in progress.needs-infowith reporter activity since the last triage notes — needs re-evaluation.
Show counts and a one-line summary per issue. Let the maintainer pick.
Triage a specific issue
Gather context. Read the full issue (body, comments, labels, reporter, dates). 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. Read
.out-of-scope/*.mdand surface any prior rejection that resembles this issue.Recommend. Tell the maintainer your category and state recommendation with reasoning, plus a brief codebase summary relevant to the issue. Wait for direction.
Reproduce (bugs only). Before any grilling, attempt reproduction: read the reporter's steps, trace the relevant code, run tests or commands. Report what happened — successful repro with code path, failed repro, or insufficient detail (a strong
needs-infosignal). A confirmed repro makes a much stronger agent brief.Grill (if needed). If the issue needs fleshing out, run a
/grill-with-docssession.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(bug) — polite explanation, then close.wontfix(enhancement) — write to.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.
Quick state override
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.
Needs-info template
## 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".
Resuming a previous session
If prior triage notes exist on the issue, read them, check whether the reporter has answered any outstanding questions, and present an updated picture before continuing. Don't re-ask resolved questions.