Design e Frontend

Use when you have a spec or requirements for a multi-step task, before touching code

Run adversarial audit pipeline against shipped code

Query, browse, and manage the project capability index

Audit whether a product experiment was designed and run in a way that makes the result trustworthy. Use this skill when the user wants to check for issues such as peeking, invalid stopping logic, traffic imbalance, contamination, or other threats to validity.

Comprehensive Claude Code plugin for yFiles for HTML development - includes skills for initialization, graph building, layouts, custom styling, and interactive features

This skill should be used when the user is scaffolding a new project, reorganizing file structure, or discussing directory layout conventions. It provides language-specific best practices for Python, Node/TypeScript, Go, and general projects. Enforces the ./tmp/ intermediary workflow and .claude/CLAUDE.md convention. Triggers on: project init, directory layout, file organization, scaffolding, repo

Create polished PDF deliverables, fill PDF forms, inspect fillable PDF fields, or reformat existing text/Markdown/PDF content into a designed PDF. Use when final output is PDF and visual quality, form fields, cover pages, or print-ready layout matter. Do not use for knowledge extraction or casual PDF reading; use docling-skill or lightweight pdf tooling for those.

Rastreie ações dos EUA por valor e qualidade de dividendos usando pontuação multifatorial em P/L, P/B, rendimento de dividendos e sustentabilidade de pagamento via API Finskills.

Um loop de agente mínimo e reutilizável para construir agentes LLM.

Reviews product specs, requirements docs, RFCs, PRDs, and policy documents from text, markdown, or Figma. Use for completeness, consistency, edge-case coverage, ambiguity, policy conflicts, or compliance gaps. Triggers on "이 기획서 검토해줘", "스펙 리뷰", "정책 검토", "review this PRD", "is this complete?", "이 기획대로 구현하면 빠진게 뭐가 있을까", "스펙 갭", "요구사항 누락", or whenever a Figma URL is shared in a planning context. Trig

Use when abandoning a current approach / experiment / task / project, regardless of what triggered it (not just chengyu-skill or skill-driven contexts). Three retreat levels — L1 stop work (safe, no operator confirmation needed), L2 remove occupied resources (REQUIRES operator confirmation per-item — irrevocable loss is bad), L3 update memory with "don't try this next time" (operator confirms what

Use when you have a spec or requirements for a multi-step task, before touching code