菜单
Run an Agent Review Council over a product, workflow, codebase, architecture, prompt, agent package, or GTM artifact. Produces evidence-backed structured findings, scorecard, risks, decision record, and validation plan.
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
Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.
Use when changing artifact identity, versioning, manifests, search/matching, content resolution, repository interfaces, or the local/enterprise DB split in the SkillMeat codebase (skillmeat/core/, skillmeat/cache/, skillmeat/storage/, skillmeat/sources/) — i.e. the informal "Registry Core" kernel this AOS has not yet named as a literal module. Trigger keywords: registry core, artifact identity, repository interface, IArtifactRepository, ICollectionRepository, RepositoryFactory, cache.db, SKILLMEAT_EDITION, alembic multi-head, schema drift, cli_snapshot.json, deprecation window, backward compatibility, breaking change to core. Do NOT use for CLI-surface/agent-facing command routing (use `skillmeat-cli`), for BOM/attestation authoring (use `asdlc-skillbom-builder`), or for bundle/deployment-set packaging (use `asdlc-sam-artifact-packager`).
Use when packaging SkillMeat artifacts (skills, agents, commands, context entities, bundles, deployment sets, or project-starter templates) for deployment or distribution — creating a bundle (`skillmeat bundle create`/`add-member`), building and publishing a `.skillmeat-pack` round-trip (`bundle build-pack`/`publish-pack`/`export`/`import`), assembling a deployment set (`deployment-set create`/`add-member`/`deploy`), registering a project-starter scaffold template (`template create`), deploying a single artifact (`skillmeat add`, `skillmeat deploy`), or taking a safety snapshot before a risky change (`skillmeat snapshot`/`rollback`). Covers local-collection vs enterprise-edition packaging differences and post-deploy verification. Do NOT use for generating BOM/attestation provenance — use `asdlc-skillbom-builder` first. Do NOT use for pre-packaging quality review — use `asdlc-skill-review-board` first.
Use when an agent needs to produce SkillBOM provenance for skills, agents, commands, or other SkillMeat artifacts — generating a BOM snapshot (`skillmeat bom generate`), signing or verifying it with Ed25519 (`skillmeat bom sign|verify|keygen`), wiring git hooks that link commits to BOM state (`skillmeat bom hook install`), inspecting materialization sidecars for parameterized deploys (`skillmeat bom materializations`), or recording an owner-scoped attestation (`skillmeat attest create|list|show`). Covers exactly what fields a SkillBOM entry carries, how BOM ties into git history, and the honest gaps in promotion/approval status and policy enforcement. Do NOT use this skill for packaging artifacts into bundles/deployment-sets/templates — use `asdlc-sam-artifact-packager` instead. Do NOT use for pre-packaging quality review — use `asdlc-skill-review-board` first.
Answer CCDash project-intelligence questions using the shipped MCP tools when available and the in-repo `ccdash` CLI otherwise. Use when the operator or another agent asks about project status, feature forensics, workflow failure patterns, after-action reports, session intelligence (transcripts, search, detail), runtime validation posture, CLI timeout or caching behavior, container project onboarding, watcher binding, or how to troubleshoot the shipped CCDash API/worker/MCP surfaces. Keep routing aligned with the current shipped runtime contract and repo docs.
Audits CHANGELOG coverage for a git commit range; read-only — surfaces gaps for human remediation. Use this skill before a version bump, in CI, or ad-hoc to verify that all non-trivial commits are reflected in the changelog. Co-loaded with the release skill on every /release:bump invocation. Does not write or modify any files; outputs structured gap reports and exit codes only.
| name | council-review |
| description | Run an Agent Review Council over a product, workflow, codebase, architecture, prompt, agent package, or GTM artifact. Produces evidence-backed structured findings, scorecard, risks, decision record, and validation plan. |
| allowed-tools | Read, Grep, Glob, Bash |
Use this skill for full ARC runs that need coordinated evidence collection, independent reviewer passes, adjudication, and schema-valid outputs.
references/run-workflow.md for the end-to-end council procedure.references/output-contract.md before creating or validating run artifacts.references/external-reviewers.md only when the run includes Codex, GitHub, Copilot, LangGraph, or other non-Claude reviewers.runs/<date>-<slug>/.uv run arc validate runs/<date>-<slug>.