菜单
Produce a prioritized, read-only audit of the workspace's health and coherence (code, docs, integrity, standards) as a dated report. Use periodically or after big changes to surface what to improve. Read-only — it reports and recommends, never fixes.
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
Configure or re-configure this AI workspace: analyze an existing repo (or set up a new one) and propose a workspace.config.yaml + skill set. Trigger: when the user wants to set up, configure, or re-detect the workspace.
Assess feasibility and security of version bumps/migrations before touching anything. Trigger: when asked to update dependencies, migrate, or resolve version conflicts.
Keep the living docs (project status) current so the AI always has fresh project context. Trigger: after finishing a task or when project state changed.
Implement the tasks in order, keeping the code aligned with the spec and design, checking each off as it lands. Use to execute an agreed plan — if reality diverges from the spec, stop and update the spec first.
Fold a verified change's delta into the stable specs and move its folder to the archive. Use only after verify passes: ADDED requirements are appended, MODIFIED replace, REMOVED delete; then the change is archived with its full history.
Surface and resolve ambiguity before the spec is written: ask targeted questions about underspecified behaviour, edge cases and decisions, and record the answers. Use between proposal and spec whenever the proposal leaves choices open.
| name | aiws-audit |
| description | Produce a prioritized, read-only audit of the workspace's health and coherence (code, docs, integrity, standards) as a dated report. Use periodically or after big changes to surface what to improve. Read-only — it reports and recommends, never fixes. |
| license | Apache-2.0 |
| metadata | {"author":"ai-workspace","source":"aiws@0.53.0","version":"1.0"} |
Produce a periodic, read-only self-audit of this workspace and write it as a dated report, so the project improves from its own state over time. It reports and recommends — it never fixes.
ai-workspace doctor — token budget, orphaned blocks, dangling doc references, orphan docs, stack/MCP registry.ai-workspace verify — integrity of base artifacts vs the manifest (tampering / in-region drift).ai-workspace reconcile — company overlay vs base (only if a company overlay is configured).git status/log, the test/lint/build scripts, and the declared docs.contract.docs/development/audits/<YYYY-MM-DD>-audit.md (dated, so improvements compound across
audits). Link the previous report so progress is visible.doctor/sync for coherence) with the user's approval.file:line), not a guess