菜单
Move issues and external PRs through triage roles — categorise, verify, grill if needed, write agent-ready briefs.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | triage |
| description | Move issues and external PRs through triage roles — categorise, verify, grill if needed, write agent-ready briefs. |
| disable-model-invocation | true |
State machine for issues (and external PRs if configured in docs/agents/issue-tracker.md). Every tracker comment starts with:
This was generated by AI during triage.
Run /aiops-setup if triage label mapping is missing.
Category: bug | enhancement
State: needs-triage | needs-info | ready-for-agent | ready-for-human | wontfix
One category + one state per item. Label strings may differ — use docs/agents/triage-labels.md.
Brief format: AGENT-BRIEF.md. Rejections KB: OUT-OF-SCOPE.md.
Natural language: "what needs attention", "triage #42", "move #42 to ready-for-agent".
Buckets (oldest first): unlabeled, needs-triage, needs-info with new reporter activity. Tag [PR] vs [issue] when PRs are in scope.
.out-of-scope/ for prior rejections; search codebase for existing implementation./grilling + /domain-modeling, update CONTEXT/ADRs inline.ready-for-agent / ready-for-human — post briefneeds-info — triage notes (established + questions for reporter)wontfix — already implemented (point to code) | rejected bug (close) | rejected enhancement (.out-of-scope/ then close)"Move #N to ready-for-agent" — apply directly after confirm; skip grill unless brief missing.
Delivery overlay — orchestrates lean ladder, tdd, prune, review with sub-phase gates; commits only on user approval.
Flow Conductor for the aiops bundle. One entry — infers task type, shows plain-language steps, tracks journey in flow.state.yaml, dispatches skill + agent per phase.
Structured design process for the architect agent. Guides from grill conclusions to complete NOTES.md + tech-spec.md plus needed domain documentation updates through constraint gathering, module identification, interface design, alternative exploration, and risk analysis. Use when the architect needs to produce design decisions and technical specifications.
Build and query a persistent code graph for the target project. Uses graphify (Tree-sitter + Louvain clustering) for deterministic structural extraction, then the model adds semantic annotations. Use when the user says build graph, code graph, dependency graph, impact analysis, or when other skills need structured code understanding before proceeding.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. Use when the user says architecture review, codebase health, deepening, refactor suggestions, or complains about architectural friction.
Review in three modes — code (diff vs standards/spec), design (NOTES + tech-spec before planning), drift (implementation vs tech-spec before ship). Pick mode from Flow Conductor phase or user intent; do not mix artifact types.