菜单
Full execution protocol for MODE: CONSULT -- answering advisory questions with bounded evidence and clear uncertainty.
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
End-to-end CI monitor that takes an already-human-reviewed PR, exhaustively researches every CI failure, fixes it end-to-end, iterates until all required checks are green (max 5 fix cycles), then merges. Use only after human review is complete and the PR is approved. Composes ci-fix-monitor for failure-type-specific fix recipes. This is the first skill in the repo that executes a merge — invoke it deliberately.
Execute complex implementation work with a swarm-like workflow: parallel exploration, scoped planning, objective validation, mandatory independent implementation review for changed work, and final critic approval. Use for feature work, bug fixes, refactors, and multi-file changes.
Monitor a pull request after creation and act autonomously on pushed PR activity. Use when subscribing to a PR after opening it, when asked to watch, babysit, or autofix a PR until merge, or when a <pr-activity> wake message or [pr-monitor:...] advisory arrives for a subscribed PR. Owns event triage (fix / ask / skip), bounded-retry escalation, and terminal-state cleanup.
Cross-agent swarm-mode behavior model — a higher-rigor workflow using parallel investigation, independent reviewer validation, and critic challenge, plus the mandatory implementation closeout gate. Runtime adapters (.claude, .agents) add execution-specific notes and command wiring.
Full execution protocol for MODE: BRAINSTORM -- structured discovery dialogue, approach selection, spec drafting, QA gate selection, and transition handling.
Full execution protocol for MODE: CLARIFY-SPEC -- resolving spec clarification markers and maintaining spec/planning alignment.
| name | consult |
| description | Full execution protocol for MODE: CONSULT -- answering advisory questions with bounded evidence and clear uncertainty. |
This protocol is loaded on demand by the architect stub in src/agents/architect.ts. The architect prompt keeps only activation, action, and hard safety constraints; the full execution details live here.
Check .swarm/context.md for cached guidance first. Identify 1-3 relevant domains from the task requirements. Call the active swarm's sme agent once per domain, serially. Max 3 SME calls per project phase. Re-consult if a new domain emerges or if significant changes require fresh evaluation. Cache guidance in context.md.
SME consultation answers are advisory. When the SME (or any agent synthesizing the final answer) cites source code, file paths, line ranges, API behavior, or CLI flags, it MUST read the actual file or tool output in the current revision. Specific anti-patterns to refuse:
src/foo.ts:123-145 without reading those lines.For uncertain claims, the SME must mark confidence: LOW and identify what additional evidence (a specific file read, a test run, a docs check) would resolve the uncertainty. Do NOT report confidence: HIGH for claims that could not be verified against current source this turn.