Skip to content

Recently active skills

Trending is calculated from star growth this site has recorded itself. No history is estimated or back-filled.

Not enough history yet: 2 of 7 days recorded. Until then this list is ordered by the most recent content change.

18071 skills

mineru-pdf-parserstaruhub/ClaudeSkills用 MinerU 将复杂PDF文档转换为LLM友好的Markdown/JSON格式。适用于:(1) PDF转Markdown/JSON,(2) 提取PDF中的文本、表格、公式、图像,(3) 解析学术论文、技术文档、商业报告,(4) 为RAG应用准备文档数据,(5) 批量处理PDF。触发关键词:"PDF解析"、"PDF转Markdown"、"提取PDF表格/公式"、"MinerU"、"parse PDF"等。不用于:PDF的阅读/填表/签名/拆分合并(用宿主pdf工具)、Word/PPT等非PDF格式解析、只需读几页内容的场景(直接读即可,不必转换)。Stars: 739Updated Claude CodeCodexUnverifiedInstall
pair-programmingstaruhub/ClaudeSkills结对编程搭档。当用户要求"边写边审"、"结对编程"、"写完自己 review 一遍"、"高可靠地实现",或明确希望代码交付时附带自我审查意见时使用。交付代码的同时输出结构化审查(正确性/安全/性能/可读性/健壮性五维度),重点捕捉 AI 生成代码的特有缺陷。不用于:对已有 PR 的正式评审(用 code review 流程)、安全专项扫描(用 security-audit)、10 行以内的简单片段。Stars: 739Updated Claude CodeCodexUnverifiedInstall
product-managerstaruhub/ClaudeSkills资深产品经理助手,提供 PRD/MRD/BRD 创作与评审、产品策略、留存增长、竞品分析、功能优先级,以及 grill-me-to-doc 逐轮访谈。用户要求“逐个问我”“先把需求问清楚”“grill me”“把想法变成产品文档”时进入 grill-me-to-doc:先读仓库证据,每轮只问一个决策,给推荐答案与理由,记录决策和未决项,支持 resume,产出结构化 PRODUCT-DOC;文档完成且用户批准前硬停止,任何时候都不写实现代码。即使未提“产品”,讨论 App 功能、增长或商业模式也应触发。不用于:单纯代码实现、系统架构深设(用 solution-architect)、需多源引用的市场调研(用 deep-research)、纯营销文案。Stars: 739Updated Claude CodeCodexUnverifiedInstall
security-auditstaruhub/ClaudeSkills全面的代码安全检查和服务器安全审计skill。适用于:(1) 代码漏洞扫描 - 检测SQL注入、XSS、SSRF等OWASP Top 10漏洞,(2) 依赖安全检查 - 识别过时或有漏洞的第三方库,结合实时搜索确认最新CVE,(3) 服务器配置审计 - 检查SSH、防火墙、权限等安全配置,(4) 敏感信息泄露检测 - API密钥、密码、令牌等硬编码检测,(5) 容器安全扫描 - Docker镜像和Kubernetes配置审计,(6) CI/CD安全检查。触发关键词:"安全检查"、"漏洞扫描"、"代码审计"、"security audit"、"vulnerability scan"、"SAST"、"dependency check"、"CVE检测"等。不用于:修复单个已定位的bug、编写新的安全功能代码、对无授权的第三方系统做扫描或渗透测试。Stars: 739Updated Claude CodeCodexUnverifiedInstall
solution-architectstaruhub/ClaudeSkills解决方案架构师助手。当用户要设计新系统架构、评审现有架构、做技术选型决策、诊断性能/可扩展性/可用性问题、规划架构演进或重构时使用。覆盖微服务、事件驱动、云原生等架构模式,技术趋势通过实时搜索获取而非依赖内置知识。不用于:具体功能的代码实现、安全漏洞审计(用security-audit)、产品需求分析(用product-manager)、只需一句话回答的技术常识问题。Stars: 739Updated Claude CodeCodexUnverifiedInstall
threejs-performancestaruhub/ClaudeSkillsThree.js 性能优化指南。当 Three.js/React Three Fiber 项目出现掉帧、内存增长、加载缓慢、绘制调用过多,或需要迁移 WebGPU、实现大规模粒子/实例化渲染、配置资源压缩管线时使用。触发关键词:"Three.js 优化"、"WebGPU"、"draw calls"、"内存泄漏"、"TSL"、"InstancedMesh"、"R3F 优化"等。不用于:通用 React 性能问题(用 vercel-react-best-practices)、WebGL/Three.js 入门教学、3D 美术资产的制作本身。Stars: 739Updated Claude CodeCodexUnverifiedInstall
wechat-article-writerstaruhub/ClaudeSkills专业微信公众号文章助手,支持四个独立且可组合模式:article 写正文;image-prompts 从文章生成版本化、provider-neutral 的图片提示词 manifest 与稳定占位符,但不调用生图;layout 把文章和 manifest 确定性转换为微信安全的内联 HTML;full-pipeline 串联正文、提示词/占位符和排版。用户提到公众号、微信文章、推文、配图提示词、图片 manifest、公众号排版、内联 HTML 或完整图文流水线时触发。支持企业官号、个人技术博客、活动回顾和产品评测。不用于:带引用的研究报告(用 deep-research)、PPT/组图(用 deck-studio)、英文文章、仅润色一小段。永不自动发布,永不把提示词或占位符声称为已生成图片。Stars: 739Updated Claude CodeCodexUnverifiedInstall
xuefeng-methodstaruhub/ClaudeSkills雪峰式AI-Native产品开发方法论。适用于:(1) 用户行为开放、不可穷举的AI-native产品(AI日历、AI助手、AI推荐、对话式产品等),(2) 强模型依赖型场景,AI驱动核心决策而非仅辅助,(3) 多专精Agent架构设计与分工,(4) 上线后快速校准、行为审计与漂移检测,(5) 模型选择和智能路由策略,(6) 概率性输出的质量评估。触发场景包括"AI-native产品怎么做"、"用户行为不可预测怎么办"、"多agent怎么分工"、"模型漂移怎么处理"、"校准到95%太难了"、"唯快不破"、"怎么选模型"、"agent并行分工"、"AI产品上线后怎么迭代"。注意:如果产品是场景明确、边界可定义的+AI类型,请改用 keqian-method skill。即使用户没有明确说"AI-native",但在讨论AI驱动决策、用户行为不可预测、概率性输出等话题时也应触发。Stars: 739Updated Claude CodeCodexUnverifiedInstall
remotion-motion-graphicshaidrrrry/claude-remotion-skillCreate and edit professional motion graphics videos with Remotion (React-based video). Use this skill EVERY time the user wants to create a video, edit a video, animate something, build an intro/outro/logo animation, make a Reel/Short/promo/launch video, add text animations or captions to footage, composite images and B-roll into a video, or mentions Remotion, motion graphics, video rendering, or "make this video look better/less generic". Also trigger when editing an existing Remotion project or when the user complains their video looks basic, generic, or amateur — this skill contains the exact fixes. Always read this skill BEFORE writing any Remotion code.Stars: 1kUpdated Claude CodeCodexUnverifiedInstall
compdf-add-watermark-remover-watermarkComPDFKit/compdf-skillsAdd or remove text and image watermarks in PDFs with ComPDF. Use for PDF branding, draft review marks, document control, watermark cleanup, and final-delivery preparation.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-compress-pdfComPDFKit/compdf-skillsCompress PDF files with ComPDF while balancing file size and readable visual quality. Use for PDF optimization, resolution control, compression strategies, and removal of non-essential document content.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-convert-images-to-documentsComPDFKit/compdf-skillsConvert image files into Word, Excel, PPT, PDF, HTML, RTF, CSV, TXT, or JSON with ComPDF. Use for screenshots, scans, receipts, forms, and photo-based business documents that need editable or structured output.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-documents-to-pdfComPDFKit/compdf-skillsConvert Word, Excel, PPT, HTML, TXT, CSV, RTF, PNG, and JPG files into PDF with ComPDF. Use when a business document or image needs fixed-layout PDF output for sharing, approvals, printing, or archiving.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-encryt-pdf-decrypt-pdfComPDFKit/compdf-skillsEncrypt PDFs with AES-128, AES-256, or RC4 options and decrypt authorized PDFs with ComPDF. Use for PDF passwords, permission controls, encryption, decryption, and document-access protection.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-ocrComPDFKit/compdf-skillsRecognize and extract text from scanned PDFs and images with ComPDF OCR workflows. Use for OCR, searchable PDF generation, text recognition, table recognition, and scanned-document extraction requests.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-page-editorComPDFKit/compdf-skillsMerge, split, rotate, insert, delete, and extract PDF pages with ComPDF. Use for PDF page management, document assembly, cleanup, restructuring, and selected-page output.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-pdf-to-htmlComPDFKit/compdf-skillsConvert PDF files into reusable HTML with ComPDF. Use for web publishing, browser workflows, portal embedding, content migration, and PDF-to-HTML requests.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-pdf-to-jsonComPDFKit/compdf-skillsConvert PDF content into structured JSON with ComPDF. Use when PDF text, tables, images, and structured content must feed an AI pipeline, application, or system integration.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-pdf-to-markdownComPDFKit/compdf-skillsConvert PDF files into Markdown with ComPDF. Use for knowledge-base ingestion, developer documentation, content repurposing, research workflows, or any PDF-to-Markdown request.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-pdf-to-wordComPDFKit/compdf-skillsConvert PDF files into editable Word documents with ComPDF. Use for PDF-to-Word requests involving contracts, reports, forms, proposals, review, revision, localization, or business reuse.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-toolkitComPDFKit/compdf-skillsAll-in-one ComPDF workflow for document conversion, OCR, data extraction, PDF editing, protection, compression, and watermarking. Use for any ComPDF Server API request that processes PDF, Office, HTML, CSV, RTF, TXT, or image files.Stars: 110Updated Claude CodeCodexUnverifiedInstall
compdf-word-to-pdfComPDFKit/compdf-skillsConvert Word documents into polished PDFs with ComPDF. Use for contracts, reports, proposals, manuals, approvals, formal delivery, and Word-to-PDF requests.Stars: 110Updated Claude CodeCodexUnverifiedInstall
pdf-converterComPDFKit/compdf-skillsConvert PDFs to Word, Excel, PPT, HTML, RTF, images, CSV, TXT, JSON, Markdown, OFD, or editable PDF, and convert supported documents and images to PDF with ComPDF. Use for general bidirectional PDF conversion workflows.Stars: 110Updated Claude CodeCodexUnverifiedInstall
agent-evaluationseb1n/awesome-ai-agent-skillsDesign reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.Stars: 257Updated Claude CodeCodexUnverifiedInstall
agent-observabilityseb1n/awesome-ai-agent-skillsDesign privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.Stars: 257Updated Claude CodeCodexUnverifiedInstall
human-in-the-loopseb1n/awesome-ai-agent-skillsDesign and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.Stars: 257Updated Claude CodeCodexUnverifiedInstall
mcp-server-buildingseb1n/awesome-ai-agent-skillsDesign, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests. Use when creating a new MCP server, exposing an API or data source through MCP, reviewing an MCP server design, adding or revising MCP tools, or preparing an MCP server for production.Stars: 257Updated Claude CodeCodexUnverifiedInstall
multi-agent-orchestrationseb1n/awesome-ai-agent-skillsDesign and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.Stars: 257Updated Claude CodeCodexUnverifiedInstall
tool-schema-designseb1n/awesome-ai-agent-skillsDesign and validate model-facing tool definitions with clear names, action-oriented descriptions, bounded JSON Schema parameters, explicit side effects, safe defaults, idempotency, errors, and realistic tests. Use when creating function-calling tools, MCP tools, agent actions, structured tool inputs, or when a model selects the wrong tool, invents arguments, or causes unsafe side effects.Stars: 257Updated Claude CodeCodexUnverifiedInstall
agent-red-teamingseb1n/awesome-ai-agent-skillsPlan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.Stars: 257Updated Claude CodeCodexUnverifiedInstall