Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 551 files from 1 750 authors, of which 61 898 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Refactoring code via variable name improvement, function extraction, magic number constants, dead code removal, and code review. Does not change behavior. Don't use for bug/security (Judge), new tests (Radar), architecture (Atlas), or feature implementation (Builder).
> Use the installed String MCP tool for String apps, SFMD, web pages, shell sessions, and commands like /open, /act, /install, or /set.
> Use the installed String MCP tool for String apps, SFMD, web pages, shell sessions, and commands like /open, /act, /install, or /set.
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.
> AGENTS.md, HANDOFF.md, docs/*) into ONE canonical CLAUDE.md, then reconciles it against the current code state so a fresh session or new teammate can pick up immediately. CLAUDE.md keeps a mandatory PROGRESS "/wrap", "tidy docs", "sync docs", "update docs", "archive", "this phase is done", or the Chinese equivalents "收尾", "同步文档", "整理文档", "整理一下", "更新文档", "存档", "梳理一下", "这阶段做完了". A bare "tidy" / "整理" with prior dev context counts. Do not under-trigger.
Design stable, versioned, self-documenting APIs. Easy to use correctly, hard to use incorrectly. Apply Hyrum's Law from day one.
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and fallback handling.
Document decisions, not just implementations. ADRs for architectural choices, inline docs for non-obvious code, and runbooks for operational knowledge.
Systematic root cause analysis for production and development bugs. Hypothesis-driven debugging — never guess-and-check.
Structured code review focusing on correctness, security, and maintainability. Correctness before style. Every reviewer comment must be actionable.
Load minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only load what the current task needs.
Automated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the deployment path.
Get layered, context-aware explanations of unfamiliar code. Understand what it does, why it was written that way, and how to work with it safely.
Accessible, performant, responsive UI patterns. Component design, state management discipline, and Core Web Vitals compliance.
Graceful degradation and meaningful error messages. Errors are first-class citizens, not afterthoughts. Every error path is designed, not discovered.
Transforms imperative instructions into declarative goals with verifiable success criteria. Enables autonomous looping until verified completion.
Detects and mitigates LLM hallucinations in production pipelines. Validates AI-generated facts, code, and decisions before they reach end users or downstream systems.
Trunk-based development with atomic commits, clean history, and meaningful commit messages. Every commit should be deployable.
Converts vague ideas into concrete, testable specifications with acceptance criteria. No implementation begins without a spec.
Build in verifiable increments. Never implement more than can be tested right now. Ship partial working systems over complete broken ones.
Test real system boundaries, not mocks of mocks. Integration tests verify that components work together, not that they work in isolation.
Converts unstructured meeting notes into structured, assigned, time-bounded action items. Never leave a meeting without knowing who does what by when.
Structured logging, distributed tracing, and alerting for AI systems and traditional services. You can't fix what you can't see.
Patterns for Retrieval-Augmented Generation (RAG) and agent memory systems. Retrieves only relevant context, prevents context bloat, and maintains coherent state across sessions.
Zero-downtime deployments with pre-flight checks, staged rollouts, and rollback plans. Never ship to production without a verified rollback strategy.
Designs and coordinates multi-agent pipelines where specialized agents collaborate to complete complex tasks. Includes communication protocols, failure handling, and state management.
Measure first, optimize second. Data-driven performance improvements with before/after benchmarks and production validation.
Safe, behavior-preserving code transformation backed by tests. Refactor with evidence, not instinct.
Guards AI agents and LLM-powered applications against prompt injection attacks — both direct and indirect. Validates AI inputs and outputs at every trust boundary.
Distill complex topics into layered, actionable summaries. Start with the key insight, layer in detail, end with recommended next action.
Applies OWASP Top 10, secrets management, and least-privilege principles before any code ships. Security is a build step, not an afterthought.
Red-green-refactor cycle with meaningful coverage. Tests are written before implementation. Coverage is a side effect of good tests, not the goal.
Enforces minimal code modifications — touch only what you must. Prevents drive-by refactoring, comment deletions, and style changes unrelated to the task.
Prevents overengineering by enforcing minimum viable code. No speculative features, no premature abstractions, no unnecessary complexity.
Breaks features into atomic, independently verifiable tasks. No task should take more than 4 hours. Unblocks parallel work and reduces integration risk.
Forces explicit reasoning before writing any code. Surfaces assumptions, manages confusion, and prevents hallucination by demanding clarity upfront.
3D print models generated with Meshy AI, plus Creative Lab consumer products. Handles slicer detection, white model printing, multi-color printing via API, the Creative Lab pipeline (figure / lamp / keychain / fridge-magnet), and print-optimized download workflows. Use when the user mentions 3D printing, slicing, Bambu, OrcaSlicer, Prusa, Cura, Creality Print, Elegoo, Anycubic, multicolor, multi-color, 3mf, Creative Lab, or wants a figurine, keychain, fridge magnet, lamp, collectible, miniature, or physical product from a photo. For generation without 3D printing, use the meshy-3d-generation skill instead.
Generate 3D models, textures, images, rig characters, animate them, and prepare for 3D printing using the Meshy AI API. Handles API key detection, task creation, polling, downloading, and full 3D print pipeline with slicer integration. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, 3D print a model, or interact with the Meshy API. For Claude Code or Cursor, use the meshy-3d-generation and meshy-3d-printing skills instead.
Generate 3D models, textures, images, rig characters, and animate them using the Meshy AI API. Handles API key detection, setup, and all generation workflows via direct HTTP calls. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, or interact with the Meshy API. For 3D printing requests, use the meshy-3d-printing skill instead.
|
|
Crawl GitHub trending repositories, analyze with LLM for Chinese insights, categorize by themes, compute diffs against history, and generate Markdown reports. Default brief mode stops at trend analysis; optional detailed mode appends per-project analysis. Supports incremental gap-filling and selective re-analysis with caching.
|
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
Self-evolution workflow for the agent. Before substantive work, recall past outcomes from evolution memory; while editing, detect improvement signals; at task end, record the outcome; when reusable, distill or search the EvoMap network for proven genes/capsules. Use when the user starts non-trivial work (a feature, a fix, a refactor) or asks the agent to "evolve", "learn from this", or "remember how this went".
|
|
|
|
|
|
| Search CrossRef, OpenAlex, PubMed, Semantic Scholar, and optional Scopus; deduplicate results, download open-access PDFs by DOI, classify papers, monitor new results, and analyze coverage. Use when asked to search literature, monitor a topic, download an open-access paper, classify papers, or analyze literature gaps.
McKinsey顾问式问题解决系统。从商业问题出发,通过假设驱动的结构化分析方法,生成McKinsey风格研究报告和PPT。融合Problem Solving方法论、MECE原则、Issue Tree拆解、Hypotheses形成、Dummy Page设计、智能数据收集和专业PPT生成能力。
咪蒙爆款文章写作技巧。适用于需要创作10万+阅读量爆款文章、情感共鸣类内容、故事叙事或社会议题评论时使用。掌握标题制造、开篇设计、情绪调动、金句提炼、故事叙事等核心技巧。
Бизнес-архитектор: превращает сырые идеи в рабочие планы с деньгами. Валидация идей, поиск болей, анализ конкурентов, unit economics, MVP, пошаговый план запуска.
Структурированный мозговой штурм перед любой творческой работой. Используй ПЕРЕД созданием контента, скилов, автоматизаций, проектов. Триггеры: 'давай подумаем', 'мозговой штурм', 'brainstorm', 'придумай', 'нужна идея', 'как лучше сделать', 'варианты'.
Статистика Telegram-канала и YouTube. Просмотры, подписчики, ERR, топ постов/видео.
> Копирайтер в стиле владельца. Пишет посты для Telegram YOUR_CHANNEL, анонсы видео, описания. Знает стиль, словарь, запрещённые обороты.
Аудит веб-сайтов и лендингов по SEO, производительности, безопасности, контенту, доступности. Используй когда нужно проверить сайт, найти проблемы, подготовить чеклист для улучшения. Триггеры: 'проверь сайт', 'аудит сайта', 'audit website', 'что не так с сайтом', 'SEO проверка', 'проверь лендинг'.
Маркетолог для контент-криейтора: YouTube, Telegram, платные подписки, запуск продуктов. Копирайтинг, психология продаж, ценообразование, воронки, контент-стратегия.
Claude Skills — questions
Answers built from the skills we actually parsed.