triage — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited triage (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Move issues through the project tracker using a small state machine of triage roles.
Every comment or issue posted to the tracker during triage must start with the following disclaimer:
> *This was generated by AI during triage.*.out-of-scope/ knowledge base is structuredTwo category roles:
bug — something is brokenenhancement — a new feature or improvementFive state roles:
needs-triage — maintainer assessment requiredneeds-info — waiting on additional information from the reporterready-for-agent — fully specified, ready for an AFK agentready-for-human — requires human implementationwontfix — will not be fixedEach triaged issue must have exactly one category role and one state role. If state roles conflict, flag it and ask the maintainer before doing anything.
These are the canonical role names — the actual label strings in the tracker may differ. The mapping must be supplied up front — if it is not, run /setup-matt-pocock-skills.
State transitions: an issue with no labels usually lands in needs-triage first; from there it moves to needs-info, ready-for-agent, ready-for-human, or wontfix. From needs-info the issue returns to needs-triage as soon as the reporter replies. The maintainer may override a transition at any time — flag unusual transitions and ask before continuing.
The maintainer calls /triage and describes their wish in natural language. Interpret the request and act. Examples:
Query the issue tracker and present three blocks, starting with the oldest:
Show the count and a one-line summary per issue. Let the maintainer choose.
.out-of-scope/*.md and surface any prior rejection that resembles this issue.Report the outcome — successful reproduction with a code path, failed attempt, or insufficient details (a strong signal to move to needs-info). A confirmed reproduction makes the agent brief much stronger.
/grill-with-docs session.ready-for-agent — post a comment with the agent brief (AGENT-BRIEF.md).ready-for-human — same structure as the agent brief, but state why it cannot 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) — record it under .out-of-scope/, link to the file from the comment, then close (OUT-OF-SCOPE.md).needs-triage — set the role. Optionally comment if there has been partial progress.If the maintainer says "move #42 to ready-for-agent", trust them and set the role directly. Confirm what you are about to do (role changes, comment, close), then act. Skip interrogation. On a transition to ready-for-agent without an interrogation session, ask whether an agent brief should be drafted.
## Triage Notes
**What we've established so far:**
- point 1
- point 2
**What we still need from you (@reporter):**
- question 1
- question 2Capture everything that was clarified during interrogation in the "established so far" section so the work is not lost. Questions must be specific and actionable, not "please provide more information".
If the issue already has triage notes, read them, check whether the reporter has answered the outstanding questions, and present an updated picture before continuing. Do not re-ask about points that have already been settled.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.