Triage

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.*

Issue tracker detection

This skill needs an issue tracker. At session start, detect which one is available:

• If gh auth status succeeds and the repo has a GitHub remote → use GitHub Issues via gh issue commands. Default.
• If glab auth status succeeds → use GitLab Issues via glab issue commands.
• Otherwise → fall back to a local .scratch/issues/ markdown convention (one file per issue, filename NNNN-slug.md, frontmatter for labels and state). Tell the user once: "No remote tracker detected; using .scratch/issues/ for local triage."

If none of the above is acceptable to the user, they should configure one before invoking /triage again.

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 broken
• enhancement — new feature or improvement

Five state roles:

• needs-triage — maintainer needs to evaluate
• needs-info — waiting on reporter for more information
• ready-for-agent — fully specified, ready for an AFK agent
• ready-for-human — needs human implementation
• wontfix — 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. Label mapping: if the repo's issue tracker uses different label strings, look for .claude-plugin/triage-labels.json at the repo root with shape { "bug": "type:bug", "ready-for-agent": "ai:ready", ... } and use those mappings. If the file does not exist, use the canonical names above as the actual labels and create them on first use.

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:

1. Unlabeled — never triaged.
2. needs-triage — evaluation in progress.
3. needs-info with 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

1. Gather context. Read the full issue (body, comments, labels, reporter, dates). Parse any prior triage notes so you don't re-ask resolved questions.

   Domain glossary check. Before exploring the codebase:

   • If the project has a CONTEXT.md / domain glossary, read it and use the glossary's vocabulary in triage notes and agent briefs.
   • If CONTEXT.md does NOT exist, surface this once — say: "No CONTEXT.md yet. I'll triage with code-extracted terms; if a load-bearing domain term emerges during this triage, I'll suggest seeding CONTEXT.md then." Don't block — proceed if AFK.
   • If docs/adr/ exists, respect any ADRs in the area.

   Read .out-of-scope/*.md and surface any prior rejection that resembles this issue.

2. Recommend. Tell the maintainer your category and state recommendation with reasoning, plus a brief codebase summary relevant to the issue. Wait for direction.

3. 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-info signal). A confirmed repro makes a much stronger agent brief.

4. Grill (if needed). If the issue needs fleshing out, run a grill-with-docs session.

5. 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.

Use with

• grill-with-docs — invoked inline at Step 4 when an issue needs to be fleshed out before becoming an agent brief. The grilling session also feeds CONTEXT.md / ADRs if they exist. Its ADR discipline also applies to wontfix enhancements: the rejection often encodes an architectural decision worth preserving as an ADR (not just an .out-of-scope/ entry).
• to-prd — for new feature requests that arrive as raw issues, run to-prd first to crystallise the conversation, then triage the resulting PRD issue with this skill.
• cpr — once an agent has implemented a ready-for-agent issue, cpr is the PR-loop counterpart that closes the loop (PR → CI → merge).

Origin

Adapted from mattpocock/skills — engineering/triage. License: MIT.