メニュー
Use only inside internal review subagents to classify bounded self-improve evidence into lesson proposals, skill proposals, or nothing worth saving.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Use when a user wants to build, search, inspect, delete, or reindex a namespace-scoped knowledge base through the runtime knowledge tool.
Use when the user wants to view or manage existing 自动任务、定时任务、recurring jobs, or scheduled digests, including query, modify, pause, resume, or delete requests.
Always-on Feishu formatting constraints for final user-visible replies. Use when the answer is heading to Feishu and must stay compact, skimmable, and card-friendly.
Use when the user wants to inspect self-improve candidates, active runtime lessons, or remove an incorrect candidate.
Use when the runtime needs to synthesize lesson candidates from repeated failures and later recoveries for the default main agent.
SOC 職業分類に基づく
| skill_id | self_improve_review |
| name | Self Improve Review |
| description | Use only inside internal review subagents to classify bounded self-improve evidence into lesson proposals, skill proposals, or nothing worth saving. |
| aliases | ["review subagent","self improve review","skill candidate review"] |
| enabled | true |
| agents | ["main"] |
| channels | ["http","feishu"] |
| tags | ["self_improve","review","skill_candidate"] |
Use this skill only inside runtime-owned self-improve review children.
Operating rules:
nothing_to_save_reason when the evidence is weak, one-off, or already covered.