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. 79 600 files from 1 763 authors, of which 61 947 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.
Creates comprehensive post-incident documents with timeline, root cause analysis, contributing factors, action items, and ownership. Follows SRE best practices for blameless postmortems. Use for "postmortem", "incident review", "RCA", or "post-incident".
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Guide product managers through structured PRD (Product Requirements Document) creation by orchestrating problem framing, user research synthesis, solution definition, and success criteria into a cohes
> 专业级产品需求文档（PRD）生成器。自动生成包含 UML 用例模型、详细用例规格说明、数据字典、交互设计、UI 规范的完整 PRD。
【铁律】Git push 前必须执行的安全扫描。防止 API keys、tokens、passwords、私钥等敏感信息被推送到远程仓库。适用于所有 git push、gh pr create、代码同步等场景。
Prepare evidence-backed software IP materials from a frozen baseline. Use for invention disclosures, patent packages, copyright deposits, filing checks, or code-to-claim maps.
Evaluate and prioritize opportunities through a structured filtering process. Use for resource allocation, strategic decision support, and project management.
> Multi-regulation privacy compliance navigator. Use for GDPR, CCPA, LGPD, POPIA, PIPEDA, PDPA, Privacy Act, PIPL, UK GDPR compliance assessments, DPA reviews, and data subject request management.
Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version focused on core proactive capabilities.
Process analysis, gap finding, human dialogue, spec generation
将模糊产品想法、客户请求或路线图争议转化为有证据的用户机会、产品组合取舍和阶段门决策。用于产品发现、机会评估、组合优先级、MVP 范围、路线图审查、发布前准备或继续/调整/停止决策；不要用于直接决定技术架构、营销投放、销售承诺、价格、法律结论，也不要把无研究证据的功能清单包装成产品战略。
You are an expert in **programmatic SEO strategy**—designing systems that generate Design and evaluate programmatic SEO strategies for creating SEO-driven pages at scale using templates and structured data. Use when the user mentions programmatic SEO, pages at scale, template pages, directory pages, location pages, comparison pages, integration pages, or keyword-pattern page generation. This skill focuses on feasibility, strategy, and page system design—not execution unless explicitly requested.
Project autoloop engine — cron-driven automated project iteration with CEO coordination
项目管理和产品需求分析。当用户需要制定项目计划、编写 PRD 文档、管理任务或进行需求分析时使用此技能。
项目路径规划与执行助手。帮助分析项目需求、规划执行路径、分解任务、识别风险、管理进度，确保项目高质量交付。
Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt needs better clarity, specificity, or structure; or when generating prompt variations for different use cases. Covers quality assessment, targeted improvements, and automatic optimization across techniques like CoT, few-shot learning, role-play, and 50+ more.
Provider key manager — rotate and sync API keys across multi-agent workspaces
Create a credential file at `~/.proxmox-credentials` Ops-focused Proxmox VE management via REST API — monitor, control, provision, and troubleshoot VMs and LXC containers with battle-tested operational patterns. Includes helper script (pve.sh) with auto node discovery from VMID, operational safety gates (read-only vs reversible vs destructive), vmstate snapshot warnings, post-resize guest filesystem steps, and a separate provisioning reference.
Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.
Extended QMD knowledge base with multi-backend embedding (Google AI Studio / Ollama / local). Use when managing QMD embeddings, switching backends, testing embedding quality, re-indexing, or troubleshooting QMD vector search. Triggers on "qmd embed", "embedding backend", "切换embedding", "embedding测试", "re-embed", "知识库embedding", "qmd扩展". For general QMD queries and knowledge retrieval, use memory-router skill instead.
Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.
QQ邮箱操作技能。支持通过 IMAP/SMTP 读取邮件、搜索邮件、回复邮件、发送邮件。凭据通过 pass 安全存储。
Multi-dimensional Quality Acceptance and Problem Convergence Engine - Deeply deconstruct requirements, eliminate extreme defects, define absolutely objective acceptance and failure criteria.
Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use PROACTIVELY for quantitative finance, trading algorithms, or risk analysis.
Search, filter, reports on CRM data
RAGFlow OpenCAIO 知识库文档上传与管理。当需要将文档上传到鲲界公司 OpenCAIO 知识库、检索知识库内容、或管理 RAGFlow 数据集时使用此 skill。
以持续计划-执行-检查-重试循环驱动项目推进，直到开发、部署与验收目标完成。
Use when the user explicitly asks to use Ralph mode for persistent plan-execute-check-retry loops that keep going until the target outcome is achieved.
Build production-grade React applications with modern architecture, state management, and performance optimization. Use when: (1) creating new React projects, (2) component architecture design, (3) state management setup (Redux, Zustand, Jotai), (4) React Router configuration, (5) custom hooks development, (6) performance optimization (React.memo, useMemo, useCallback), (7) code splitting and lazy loading, (8) testing setup. Supports React 18+, Next.js, Vite. Triggers: "React project", "create component", "state management", "React hooks", "Next.js", "Redux", "component architecture".
This skill provides automated assistance for react component generator tasks within the Frontend Development domain Generate react component generator operations. Auto-activating skill for Frontend Development. Part of the Frontend Development skill category. Use when working with react component generator functionality. Trigger with phrases like "react component generator", "react generator", "react".
Use when researching React APIs or concepts for documentation. Use when you need authoritative usage examples, caveats, warnings, or errors for a React feature.
Search, read, analyze, and automate Xiaohongshu (小红书) content via CLI
Inspect Redis cache keys, values, and TTLs for debugging. Supports both main cache and system cache. Use for debugging cache issues, checking cached values, and monitoring cache state. Read-only by default.
Multi-provider image generation with automatic priority fallback Multi-provider image generation with priority fallback. Supports 1K/2K/4K, multiple aspect ratios, auto fallback.
Multi-provider video generation with async polling and automatic model fallback Generate short videos via relay with provider priority fallback. Google Gemini Veo 3.1 (primary, direct API) → Xingjiabi (kling-video fallback).
Polymarket链上交易skill。通过Relayer v2 API绕过CLOB geo-block，执行buy(split)/sell(merge+transfer)/redeem/claim。零CLOB依赖，纯链上gasless。Triggers: 'relayer buy', 'relayer sell', 'relayer claim', '链上交易', 'split position', 'merge position', 'geo-block bypass'.
ttyd + Tailscale for mobile terminal access
调度远程 Ollama GPU 资源执行批量 embedding 或推理任务，提升多机环境下的算力利用率。
Export any bioinformatics analysis as a reproducible bundle with Conda environment, Singularity container definition, and Nextflow pipeline.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal impl...
为重要决策设计可证伪研究问题、检索协议、证据台账、反证矩阵、不确定性说明和带引用的综合结论。适用于比较竞争性解释、审查多来源主张、建立证据图或决定下一步研究；不用于无需研究的稳定常识、单纯数据查询、伪造来源，或未经授权购买资料、联系研究对象和访问受限内容。
将销售线索和客户对话治理为有证据的发现、资格、机会阶段、方案、预测、谈判和客户成功交接。用于机会审查、发现准备、资格判断、管道复盘、提案协调、谈判准备、预测校准、失单复盘或成交后交接；不要用于自动外联、群发、写入 CRM、报价、折扣、签约、抓取个人资料、承诺产品/交期/条款，也不要把回复、会议、试用或口头兴趣冒充成交。
Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.
Guide product managers through strategic roadmap planning by orchestrating prioritization, epic definition, stakeholder alignment, and release sequencing skills into a structured process. Use this to
Use when calculating marketing ROI on Xiaohongshu, measuring campaign return on investment, analyzing cost per acquisition, evaluating marketing spend efficiency, or proving marketing value to stakeholders
RSS feed aggregation and monitoring. Parse RSS/Atom feeds, filter entries, track new items, and integrate with notification channels for automated content monitoring.
Analyze a codebase and generate production-grade operational runbooks with verification steps, rollback paths, escalation guidance, and staleness checks.
> This skill should be used when the user asks to "calculate MRR", "analyze churn", "compute SaaS metrics", "do cohort retention analysis", "calculate LTV or CAC", "evaluate unit economics", or "track subscription revenue growth".
> World-class autonomous sales and revenue skill system. Use ANY time the user asks to sell, pitch, prospect, close, negotiate, launch, monetize, build funnels, write outreach, craft proposals, develop pricing, design offers, write sales copy, create email sequences, plan campaigns, position products, handle objections, create playbooks, build pipeline, forecast revenue, develop GTM strategy, optimize conversions, write ad copy, create sales decks, score leads, nurture prospects, upsell, cross-sell, retain customers, write case studies, price products, structure enterprise deals, create battle cards, script discovery calls, build affiliate programs, plan product launches, create webinar funnels, design pricing pages, A/B test offers, analyze unit economics, calculate LTV/CAC, or ANY other sales, revenue, monetization, go-to-market, or commercial growth task. If it involves selling, revenue, deals, pipeline, or commercial strategy — USE THIS SKILL. Trigger aggressively.
Automate single-cell RNA-seq analysis with Scanpy or Seurat. QC, normalisation, clustering, DE analysis, and visualisation.
Advanced Scrum Master with data-driven team health analysis, velocity forecasting, retrospective insights, and team development expertise. Features comprehensive sprint health scoring, Monte Carlo forecasting, and psychological safety frameworks for high-performing agile teams.
四源同级：Brave (`web_search`) + Exa + Tavily + Grok。按意图自动选策略、调权重、做合成。 DEFAULT search tool for ALL search/lookup needs. Multi-source search and deduplication layer with intent-aware scoring. Integrates Brave Search (web_search), Exa, Tavily, and Grok to provide high-coverage, high-quality results. Automatically classifies query intent and adjusts search strategy, scoring weights, and result synthesis. Use for ANY query that requires web search — factual lookups, research, news, comparisons, resource finding, "what is X", status checks, etc. Do NOT use raw web_search directly; always route through this skill.
Expert web researcher using advanced search techniques and synthesis. Masters search operators, result filtering, and multi-source verification. Handles competitive analysis and fact-checking. Use PROACTIVELY for deep research, information gathering, or trend analysis.
Comprehensive security auditing for Clawdbot deployments. Scans for exposed credentials, open ports, weak configs, and vulnerabilities. Auto-fix mode included.
Captures clause risks, compliance gaps, precedent shifts, contract deviations, regulatory changes, and litigation exposure to enable continuous legal operations improvement. Use when: (1) An unfavorable clause is accepted or slips through review, (2) A compliance deadline is missed or approaching, (3) A new regulation impacts the organization, (4) A contract remains unsigned past SLA, (5) An IP infringement notice is received, (6) New case law changes interpretation in a relevant jurisdiction, (7) A data subject access request reveals process gaps.
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use before starting work and after responding to the user.
Continuous self-improvement through structured reflection and memory
Claude Skills — questions
Answers built from the skills we actually parsed.