agentic-sop-kit

Plugin agentic-sop-kit from marketplace agentic-sop-to-work in s0912758806p/agentic-sop-to-work. Commands read from the repo's manifest — 12 days ago.

Skills (13)

• accept

  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.

• ai_claims

  Use as the AI/LLM example step — turn an input's `source` values into `claims`, recording a trace entry per value so a trace_gate can block anything not traceable to the input (the no-fabrication pattern). Stand-in for a real LLM call. Single tool.

• be_api

  Use as the backend example step — emit an API-response artifact (`api@1`) that a schema_gate checks for required fields. Stand-in for a real HTTP call (curl / requests); the gate is what catches a malformed response. Single tool.

• compute

  Use to compute summary statistics (count/sum/mean/min/max) from a readings artifact, preserving the upstream source trace. Single tool. Reusable standalone.

• db_rows

  Use as the database example step — emit query rows plus a stated total (`rows@1`) that a recompute_gate re-derives and compares. Stand-in for a real SQL query (psql); the gate is what catches a total that does not add up. Single tool.

• draft

  Use to produce a first draft, or to revise one from an upstream verdict artifact's open-defect count, emitting a draft@1 artifact. The target node of a bounded back-edge. Single tool. Reusable standalone.

• extract

  Use to extract numeric readings (key: value lines) from a plain-text input into a structured readings artifact with source-location trace. Single tool. Reusable standalone.

• report

  Use to render a DRAFT Markdown summary report from a stats artifact, including a source-trace section; output is always a DRAFT for human review. Single tool. Reusable standalone.

• verdict

  Use to derive a deterministic reject/pass verdict from a draft@1 artifact's open-defect count, emitting a verdict@1 artifact for a branch to route on. Single tool. Reusable standalone.

• agentic-sop

  Use when turning a human SOP or manual process into an agentic workflow, building or adding an agent tool, or starting a new agent-workflow project — even if the user never says 'SOP' or 'methodology'. ｜ 要把人工流程／SOP 自動化、建立或新增 agent 工具、或開一個新的 agent 工作流專案時使用；只要意圖是把流程工程化成自動代理就觸發。不適用：稽核既有工作流是否退化成 mega ag

• agentic-workflow-audit

  Use when reviewing or auditing an existing agent / LLM-pipeline architecture — e.g. 'is my workflow actually decomposed or secretly a mega-agent?', 'are my task boundaries and success criteria right?', 'is our shared state a blackboard?', 'can this retry loop run forever?' — even without the word 'a

• six-rung-ladder

  Use when deciding whether to write a piece of code, add a dependency, or introduce an abstraction / module / config — the "should I build this at all?" filter, applied before building. ｜ 要決定「要不要寫這段 code／引這個依賴／加這層抽象或模組」時使用——「到底該不該做」的過濾網，動手之前先走一遍。不適用：把流程做成 agent workflow／建工具（改用 agentic-sop）；稽核既有架構有沒有拆

• sop-flow

  Run the agentic-sop-kit workflow (extract→compute→report, or a declared topology) and report the DRAFT result. Works out-of-the-box (bundled demo) even before a project adopts the kit.

Hooks (2)

• SessionStart

  python3

• Stop

  python3

Similar plugins