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…
demo good plugin
Use when creating, scaffolding, or linting a Claude Code plugin — generate a grammar-conformant plugin skeleton, or validate a plugin / whole marketplace against house invariants (manifest, frontmatter, stdlib-only, hook protocol, test harness). ｜ 要新建 /…
Use when checking a record / dataset / GMP document for ALCOA+ data integrity — attribution, contemporaneity (backdating), completeness, accuracy (recompute / in-spec), consistency — before a human approves. DEGRADED mode lints any CSV/JSON record against a…
Use when asked to get a second opinion on a finished DRAFT, fact-check or double-check a report's claims against its evidence, sanity-check before sign-off, or red-team an output for fabrication / overreach / invented IDs — even without the word "honesty".…
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…
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?' — even without the word 'audit'. ｜ 要檢視／review／稽核既有 agent 或…
Use to compute summary statistics (count/sum/mean/min/max) from a readings artifact, preserving the upstream source trace. Single tool. Reusable standalone.