Imported from akillness/jeo-skills (
.agent-skills/triage/SKILL.md). Install upstream withnpx skills add akillness/jeo-skills --skill triage. Copyright stays with the author.
Triage
Move issues through a structured state machine. Every AI-generated comment must start with:
> *This was generated by AI during triage.*
Roles
Category roles (one per issue):
bug— something is brokenenhancement— new feature or improvement
State roles (one per issue):
needs-triage— needs evaluationneeds-info— waiting on reporterready-for-agent— fully specified, AFK-implementableready-for-human— needs human (judgment, design, manual testing)wontfix— will not be actioned
State transitions: needs-triage → needs-info | ready-for-agent | ready-for-human | wontfix. needs-info returns to needs-triage when reporter replies.
Label strings in the tracker may differ from these canonical names — run /setup-matt-pocock-skills to configure the mapping.
Invocation
Natural language: "Show me what needs attention", "Let's look at #42", "Move #42 to ready-for-agent", "What's ready for agents?"
Show what needs attention
Present three buckets (oldest first):
- Unlabeled — never triaged
needs-triage— evaluation in progressneeds-infowith reporter activity — needs re-evaluation
Show counts + one-line summary per issue. Let maintainer pick.
Triage a specific issue
-
Gather context — read full issue (body, comments, labels, dates). Check
.out-of-scope/for prior rejections. -
Recommend — state your category + state recommendation with reasoning. Wait for direction.
-
Reproduce (bugs only) — trace the relevant code, run tests. Report: confirmed repro, failed repro, or insufficient detail.
-
Grill if needed — run a
grill-with-docssession to flesh out the issue. -
Apply outcome:
ready-for-agent→ post an agent briefready-for-human→ same structure, note why it can't be automatedneeds-info→ post triage notes (template below)wontfix (bug)→ polite explanation, closewontfix (enhancement)→ write to.out-of-scope/, link comment, close
Quick state override
If maintainer says "move #42 to ready-for-agent" — trust them, apply directly. Confirm changes before acting. Skip grilling. Ask if they want 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 (specific and actionable)
- question 2
Resuming a session
If prior triage notes exist, read them, check if reporter answered questions, present updated picture. Don't re-ask resolved questions.
When to use this skill
- Use this skill when you need the workflow described above and want consistent, repeatable execution.
Instructions
- Identify the task trigger and expected output.
- Follow the workflow steps in this skill from top to bottom.
- Validate outputs before moving to the next step.
- Capture blockers and fallback path if any step fails.
Examples
- Example: Apply this skill to a small scope first, then scale to full scope after validation passes.
Best practices
- Keep outputs deterministic and auditable.
- Prefer small reversible changes over broad risky edits.
- Record assumptions explicitly.
References
- Project standards:
.agent-skills/skill-standardization/SKILL.md - Validator script:
.agent-skills/skill-standardization/scripts/validate_skill.sh