一键导入
format-verdict
Use when producing a review verdict that needs clear evidence, risk level, and a compact decision-ready result.
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。
菜单
Use when producing a review verdict that needs clear evidence, risk level, and a compact decision-ready result.
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。
Use for Gitea, GitOps, registry, and every non-trivial implementation task that should be delegated to Codex instead of being coded inline.
Use for non-trivial implementation work. Delegate the coding or large-repo analysis to Codex CLI, then record usage before handing back results.
Browse in-cluster Gitea repos, issues, pull requests, commits, chart values, GitOps definitions, and sandbox image sources for read-only design context with the `__REVIEWER_GITEA_USERNAME__` Gitea user shared with auditor.
Review in-cluster Gitea repos and pull requests by reading files, inspecting diffs, checking comments, posting review feedback, and approving with the `__REVIEWER_GITEA_USERNAME__` Gitea user shared with architect; merge only with explicit instruction.
Use this to turn recent Qdrant memories and changed Nextcloud docs into clean Memgraph links, Qdrant graph-link annotations, and an updated grooming checkpoint.
Use when routing work to a standing specialist or reviewing a specialist return.
基于 SOC 职业分类
| name | format-verdict |
| description | Use when producing a review verdict that needs clear evidence, risk level, and a compact decision-ready result. |
Auditor outputs a verdict, not an implementation plan.
on-demand | risk-triggered | scheduledapprove | approve-with-notes | revise | rejectAlways produce:
## Audit Verdict
**Subject:** <what was reviewed>
**Scope:** <on-demand | risk-triggered | scheduled>
**Verdict:** <approve | approve-with-notes | revise | reject>
### Critical Findings
1. <issue>
### Observations
- <non-blocking note>
### Improvement Opportunities
- <concrete workflow or quality improvement>
### Confidence
<high | medium | low> - <brief justification>
### Recommended Action
<what should happen next and who owns it>
### Escalation Needed
<yes | no> - <why>
When returning the result through main, prefer:
## Audit Complete
**Subject:** <brief restatement>
**Verdict:** <approve | approve-with-notes | revise | reject>
### For the user
<one-paragraph summary of findings>
### Deliverables
- Nextcloud: <paths to audit reports stored>
- Qdrant: <memories stored, if any>
### Follow-up needed
<what needs to happen next and owner>