메뉴
Move issues through evidence-backed category and readiness states.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | triage |
| description | Move issues through evidence-backed category and readiness states. |
Move issues through a small, explicit state machine. Read docs/agents/issue-tracker.md, the domain glossary, relevant ADRs, and the active initiative RUN.md before changing tracker state.
Every public tracker comment generated during triage starts with:
> *This was generated by AI during triage.*
Categories:
bug — accepted behavior is brokenenhancement — new behavior or an improvementStates:
needs-triage — evaluation has not finishedneeds-info — a precise missing input blocks evaluationready-for-agent — acceptance, evidence, authority, and boundaries are sufficient for autonomous workready-for-human — judgment or authority outside the active controller envelope is requiredwontfix — the request is rejected or already implementedEach actionable issue has exactly one category and one state. A fully specified child that is dependency-blocked is the one exception: it keeps its category and explicit Blocked by edges but no state label until it enters the frontier. agents/scripts/setup-labels.sh creates the vocabulary idempotently.
Interactive is the default. Recommend an outcome, wait for the maintainer, then apply it.
Controller mode exists only when an active initiative RUN.md explicitly delegates tracker decisions to a top-level controller. Inside that envelope, controller sign-off satisfies routine approval and triage may mutate labels, post briefs, split/reorder in-scope work, and advance without asking the operator. It must stop at the RUN.md boundary.
Recommendation-only gathers evidence and reports a proposed outcome without mutating the tracker. Use it for untrusted or read-only callers.
Authentication, sessions, authorization, deletion, data integrity, secrets, and production deployment require explicit acceptance criteria plus independent security/operations review. Outside a delegated goal they are ready-for-human; inside a goal that explicitly includes them, the controller owns routine approval but may not weaken review or change the governing invariant.
Show, oldest first:
needs-triage issues;needs-info issues with new reporter evidence.External requests begin as issues. Pull requests carry already-accepted work through review and are inspected only when named or when the tracker configuration explicitly admits them to triage.
ready-for-agent or ready-for-human; post precise questions for needs-info; close a rejected request with rationale and record durable product rejection when appropriate; or leave needs-triage with evidence gathered so far.Recommendation-only stops after step 3 with one consolidated report.
ready-for-agent without explicit operator authority.A ready-for-agent brief follows AGENT-BRIEF.md and includes:
For a bug, the implementation path is diagnosis → failing regression → minimal repair → targeted/full checks → independent Standards and Spec review → repair/rereview → integration.
> *This was generated by AI during triage.*
## Triage Notes
**Established**
- evidence already known
**Needed**
- one precise, answerable question
Do not re-ask a question answered in the issue history.
Review a fixed implementation diff independently for repository standards and originating specification. Use before integration and after every blocking repair.
Deliver one unblocked ticket through a bounded MWP workspace, behavioral TDD, verification, review handoff, and harvest proposal. Use only after the controller claims a frontier ticket.
Control one bounded campaign within an approved initiative, coordinating leaf implementation, review, repair, integration, evidence, and a durable completion or pause handoff.
Decompose an accepted PRD into a reviewed dependency graph of vertical tracer tickets. Use after to-spec and before autonomous implementation begins.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.