debug
Use for a reproducible failure or unexpected behavior; reproduce, isolate, and verify the cause.
38,472 Skills
Search uses this published catalog; rankings and counts are snapshots.
Use for a reproducible failure or unexpected behavior; reproduce, isolate, and verify the cause.
Use only for an explicitly requested scoped UI change with existing design constraints.
Use only for an explicit Git operation with scoped status, diff, and transport discipline.
Use for concrete implementation authorized by the user's request or an accepted plan, with focused verification.
Use only when the user explicitly requests language-server setup or diagnostics.
Use only when the user explicitly asks to change, review, or persist reusable development philosophy.
Use after product and technical inputs are concrete enough to choose a bounded delivery plan.
Use only when the user explicitly asks for an adversarial review of a high-risk delivery plan.
Use only for an explicitly requested behavior-preserving structural improvement.
Use to review a scoped implementation and report evidence-based findings before suggesting changes.
Use after an approved delivery boundary to define a focused failing behavior test before implementation.
Use after an approved product brief to collect project facts that materially affect delivery.
Use only when the user explicitly requests visual verification and a compatible host can render the UI.
Design, audit, or correct an electronic circuit from a product brief, native schematic, netlist, block diagram, or circuit description. Use for architecture and component-function review, power and logic-domain checks, reset and boot sequencing, bus ownership, ratings, timing, pr
Turn an electronic product idea, behavior description, reverse-engineering note, or incomplete circuit concept into a decision-ready engineering brief and architecture. Use before schematic design or audit when functions, operating states, power, interfaces, mechanics, production
OMK(Observe. Measure. Know.)让 AI 应用的知识改动有据可依。观测真实表现,受控测量 prompt / RAG / skill / agent / workflow 的版本差异,判断改动是否有效、版本能否发布,并支持自动迭代改进。 Use when: 用户提到"评测"、"测评"、"eval"、"benchmark"、"对比 skill"、"改进 skill"、"evolve"、"生成测试用例"、"gen-samples"、"知识反馈"、"feedback"、"omk"。
Catalog captured:2026-11-21