Explorar skills

Layering workflow for building a knowledge base, CMS, documentation site, or structured content platform from scratch. Builds the data model first (content-modelling), adds a formal knowledge-graph layer if needed (ontology-design), establishes naming and taxonomy conventions (consistency-standards), designs information architecture (navigation-design), fine-tunes voice and microcopy (ux-writing),

[TODO: Write comprehensive description in third-person. Start with "This skill provides..." or "This skill should be used when..."] [TODO: Add "Use when" scenarios - specific situations where Claude should use this skill] [TODO: Add keywords - technologies, use cases, error messages that should trigger this skill]

Generates comprehensive documentation for any Claude Code plugin by fetching and analyzing all source files. Use when you need to document a Claude plugin, write a plugin README, explain how a plugin works, generate plugin usage guides, create plugin tutorials, analyze a plugin architecture for documentation, or produce installation and setup instructions. Takes a GitHub URL or local path, fetches

Designs a complete Retrieval-Augmented Generation (RAG) pipeline for a given use case, including chunking strategy, embedding model selection, and retrieval approach.

工具版本检查与更新，扫描 npm/brew/pip/uv/GitHub/plugins/skills 逐项对比已装和最新版本，生成带编号报告，确认后才执行更新。Use when 用户说"检查更新""工具版本""看看哪些该更新了""brew有没有过期的""opencli是不是该更新了"或提到工具版本/环境更新。

Design ad-hoc personas for niche domains when the canonical 12 brainstorm- swarm personas don't fit. Covers: when a custom persona is justified (vs forcing canonical to fit), the persona-design template (voice, contribution shape, output format), anti-patterns (too-narrow personas, redundant personas, sock-puppet personas), and how to invoke a custom persona inline via Task() with a tailored promp

Structure long-form technical articles around the hook → promise → setup → development → payoff contract. Pick from canonical templates (deep-dive, tutorial, opinion, case study, whitepaper, technical narrative). Engineer section transitions and signposting. Match length to ambition (when 800 vs 1500 vs 3000 vs 5000+ words is right). Use when the user asks to outline a technical article, structure

Build and debug Pydantic AI agents using best practices for dependencies, dynamic system prompts, tools, and structured output validation. Use when the user wants to: (1) Create a new Pydantic AI agent, (2) Debug or fix an existing agent, (3) Add features like tools, validators, or dynamic prompts, (4) Integrate OpenRouter for multi-model access, (5) Add Logfire for debugging/observability, (6) St

Conduct deep OSINT research on individuals — from name or handle to a scored dossier with psychoprofile (MBTI/Big Five), career map, and confidence-graded facts. Phased pipeline (0→6): tooling check, seed collection, internal intelligence, platform extraction, cross-reference, psychoprofile, completeness evaluation, dossier output. Swarm mode: 3-5 parallel Sonnet sub-agents. 55+ Apify actors. 7 se

Reviews web forms for usability issues — field ordering, validation messages, error states, and accessibility.

Use when the user wants test-driven development, asks to write tests first, or mentions TDD.

Use when reverse engineering tools are missing, not working, or need configuration. Installation guides for radare2 (r2), Ghidra, GDB, QEMU, Frida, binutils, and cross-compilation toolchains. Keywords - "install radare2", "setup ghidra", "r2 not found", "qemu missing", "tool not installed", "configure gdb", "cross-compiler"