claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
All skills · Category
Methodology
Frameworks for thinking and working — prompting, problem-solving, design rituals.
39 skills
prompt-engineering
Universal prompt engineering techniques for any LLM.
github-swyxio-ai-notes
notes for software engineers getting up to speed on new AI developments.
mcp-builder
Builds production MCP servers via 4-phase methodology: research, implement, test, evaluate. Triggers: build MCP, new MCP, MCP integration, MCP server scaffold.
skill-review
Quality review and audit for Claude Code skills.
skills-qa
Evaluate a skill against the Legal Skill Design Framework — thirteen design parameters (including trust-surface, freshness, schema validation, and conflict detection), three legal failure modes, and…
mcp-client
Universal MCP client for connecting to any MCP server with progressive disclosure.
security-best-practices
Perform language and framework specific security best-practice reviews and suggest improvements.
mcp-docs
Fetch live MCP specification and docs from modelcontextprotocol.io. Training data may be outdated — default to using this skill when the query touches MCP protocol in any way. Trigger for:…
mcp-audit
Audit MCP servers for protocol compliance, metadata drift, and compatibility regressions.
skill-security-auditor
Security audit and vulnerability scanner for AI agent skills before installation.
recsys-pipeline-architect
Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm.
speech
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI…
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest…
skill-developer
Create and manage Claude Code skills following Anthropic best practices.
interview-me
Extracts what the user actually wants instead of what they think they should want.
skill-prompt-convert
在 Skill（SKILL.md）与 Prompt（聊天框指令）两种格式之间相互转换。支持 Skill→Prompt 与 Prompt→Skill 双向转换，保持核心信息零丢失。当用户提到 Skill 转 Prompt、Prompt 转 Skill、格式互转、SKILL.md 转换时使用。
mcp-scaffold
Scaffold production-ready Python MCP servers using FastMCP.
mcp
Build or consume Model Context Protocol (MCP) servers and clients in .NET using the official MCP C# SDK, including stdio, Streamable HTTP, tools, prompts, resources, and capability negotiation. USE…
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking.
lumi-diary
Your local-first memory guardian and cyber bestie.
ph
Fill a placeholder — infer the best content from surrounding context.
agent-customization
High quality skill with clear triggers, specific outputs, and good scope.
evaluation-methodology
PluginEval quality methodology — dimensions, rubrics, statistical methods, and scoring formulas.
kotest
Helps write, migrate, and improve Kotlin tests using the Kotest testing framework.
sdd
Specification-driven development methodology coach.
fpf-problem-solving
First Principles Framework (FPF) — thinking amplifier.
claw
Real-time event bus for AI agents. Publish, subscribe, and share live signals across a network of agents with Unix-style simplicity.
ai-safe2-secure-build-copilot
Apply the AI SAFE2 v3.0 framework (161 controls across 5 pillars plus CP.1-CP.10 Cross-Pillar Governance) to design, build, audit, and govern AI agents, agentic workflows, RAG systems, MCP servers,…
paper-review-pipeline
Use when a mostly complete ML conference paper needs self-review, pre-submission QA, camera-ready checking, section-by-section critique, citation-risk inspection, or rebuttal/review-response drafting.
scientific-eda
Defensive exploratory data analysis for scientific data (CSV, FASTA, etc.). Context-first, human-guided; one plot at a time, ask why before executing, append-only journal per session, scripts with…
mp-article-writor
生成公众号「高效人生指北」的长文。当用户想把工作流探索、AI 工具测评、产品体验、个人实践、生活感悟等素材整理成公众号或少数派文章时使用。包括文章撰写、标题推荐、配图 prompt 生成、行文自检。即使用户只是说「帮我写篇文章」「整理成推文」「发公众号」，也应当触发此技能。
claudraband
Use claudraband CLI to control Claude Code sessions programmatically.
aisync
Sync AI coding sessions from 14 tools (Claude Code, Codex, Cursor, Aider, Cline, Gemini CLI, Continue, Copilot, Roo Code, Windsurf, Zed AI, Amp, OpenCode, OpenRouter) to Obsidian vault as markdown…
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
car-rental-search
Find and compare car rentals — sedans, SUVs, and luxury vehicles with insurance options, pickup locations, and best rates for self-driving adventures.
valaxy
Valaxy static blog framework built with Vue 3, Vite, and pnpm workspaces.
memory
a file-based long-term memory using a single JSONL file, with append-only writes and recent-window search via bash + jq.
e2e
Write end-to-end tests for user flows using Cypress.