# Triage > Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs. - Skill: `caneff/triage` (Agent Skill, multi-file: 4 files) - Install (CLI): `npx skillmds@latest add caneff/triage` - Raw SKILL.md: https://api.skillmd.com/api/skills/caneff/triage/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: caneff (https://skillmd.com/u/caneff) - Updated: 2026-09-22 - Page: https://skillmd.com/skills/caneff/triage --- # Triage 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.* ``` ## Reference docs - [AGENT-BRIEF.md](AGENT-BRIEF.md) — how to write durable agent briefs - [OUT-OF-SCOPE.md](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 Six **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 - `backlog` — real work, parked until something else lands or the maintainer schedules it - `wontfix` — will not be actioned For 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. A build-lifecycle label the tracker adds outside triage — `in-progress` while an agent builds a claimed ticket — is not a state role and never counts as a conflict, including alongside `ready-for-human`: that pair means the ticket is mid-build for a human to merge, not caught between two states. 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`, `backlog`, or `wontfix`. `needs-info` returns to `needs-triage` once the reporter replies. `backlog` moves to `ready-for-agent` or `ready-for-human` when whatever it waits on lands. 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" (issue or PR) - "Move #42 to ready-for-agent" - "What's ready for agents to pick up?" ## Show what needs attention Query the issue tracker and present four 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. 4. **`backlog` whose gate has since closed** — the blocking issue is closed, or the named condition has passed. Read each one's gate comment; a parked issue nobody re-reads is a forgotten issue with better labelling. 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. **Large list (more than five items), or the maintainer says "all":** do not walk it one issue at a time. Read every body first. For each, decide whether it should be done at all before deciding how — clarity and low effort are not reasons to do a thing: - **Would the proposed mechanism change behaviour?** A retro item whose body says the prior prose rule was a no-op must not become another prose rule. Either name a mechanical form (a script the step runs, a file the worker must read, a hook) or dismiss it. - **Is the evidence repeated or one incident?** One run's pain earns a note, not a rule. Split a ticket that mixes both and keep the repeated part. - **Is it already covered?** By an existing rule, a fix that landed since, or an architecture change that removed the failure mode. Dismiss with the pointer. Then sort what survives into three buckets and present that before any per-issue work: 1. **Worth talking about** — a design or scope decision only the maintainer can make. Name the decision in one line. Merge issues that share it. 2. **Handle myself now** — one-liners in docs or config; batch them into one commit. 3. **Brief and label without discussion** — spec already clear; post the agent brief and move on. Merge issues that are one ticket in disguise. Plus a **dismiss** line for anything that is a checklist item, already done, or has no gate. Then ask the maintainer to confirm the sort. Buckets 2 and 3 run start to finish on a "go"; bucket 1 comes back one issue at a time. ## Triage a specific issue or PR 1. **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. 2. **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. 3. **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. 4. **Grill (if needed).** If the request needs fleshing out, run the `/grilling` and `/domain-modeling` skills together — grill it into shape a round of questions at a time, sharpening domain terms and updating `CONTEXT.md`/ADRs inline as decisions land. 5. **Apply the outcome:** - `ready-for-agent` — post an agent brief comment ([AGENT-BRIEF.md](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). - `backlog` — leave the issue open and name the gate in a comment: what has to land before it moves, and which role it moves to then. Choose this only when you can name that gate — a dependency, a decision, a season. If nothing would ever unpark it, the honest answer is `wontfix`. - `wontfix` — close, with the comment depending on *why*: - **Already implemented** — the change already exists in the codebase. Point to where it lives; do **not** write to `.out-of-scope/` (that KB is for *rejected* requests, not built ones). - **Rejected (bug)** — polite explanation, then close. - **Rejected (enhancement)** — write to `.out-of-scope/`, link to it from a comment, then close ([OUT-OF-SCOPE.md](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 ```markdown ## 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 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.