compute
Use to compute summary statistics (count/sum/mean/min/max) from a readings artifact, preserving the upstream source trace. Single…
Use as a terminal node that emits accepted@1 only when an upstream verdict@1 says pass, and fails loudly on a rejected draft regardless of how routing reached it. Single tool. Reusable standalone.
$ npx -y skills add s0912758806p/agentic-sop-to-work --skill accept --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/acceptContext preview
The summary Claude sees to decide when to auto-load this skill.
Use as a terminal node that emits accepted@1 only when an upstream verdict@1 says pass, and fails loudly on a rejected draft regardless of how routing reached it. Single tool. Reusable standalone.
name: accept description: Use as a terminal node that emits accepted@1 only when an upstream verdict@1 says pass, and fails loudly on a rejected draft regardless of how routing reached it. Single tool. Reusable standalone.
圖示範流程的終端節點。刻意**不信任路由**:即使編排把一份 `reject` 的判定送到這裡 (例如有人手改了 `flow.json` 的 branch 條件),這一步仍拒絕通過。 閘門查真相,不查「我是被誰叫來的」。
`data.verdict != "pass"` → **exit 3**。產出一律 DRAFT,需人覆核。
`python3 skills/accept/tool.py --in <$RUN/verdict.json> --out <$RUN/accepted.json>`
`skills/accept/` + `lib/kit.py` 可單獨抽出;只要上游給 `verdict@1` 即可運作。
Loop Engineering — make an agent's loop produce verifiable progress, stay honest, and stay bounded, by deterministic mechanism rather than vibes.
Use to compute summary statistics (count/sum/mean/min/max) from a readings artifact, preserving the upstream source trace. Single…
Use to extract numeric readings (key: value lines) from a plain-text input into a structured readings artifact with…
Use to render a DRAFT Markdown summary report from a stats artifact, including a source-trace section; output is always a DRAFT…
Use to derive a deterministic reject/pass verdict from a draft@1 artifact's open-defect count, emitting a verdict@1 artifact for…
Use when turning a human SOP or manual process into an agentic workflow, building or adding an agent tool, or starting a new…
Use when reviewing or auditing an existing agent / LLM-pipeline architecture — e.g. 'is my workflow actually decomposed or…