| 3601 | poker-strategy-master德州扑克策略 (德州扑克策略 (Texas Hold'em) — solver/GTO 时代的无限注德州扑克竞技打法，牌手/职业视角。覆盖: (a) 理论两极 — GTO 博弈论均衡 (不可剥削的基线策略) vs Exploitative 剥削打法 (针对对手漏洞偏离均衡最大化 EV)，以及二者的实战取舍; (b) solver 时代工作流 — PioSOLVER/GTO Wizard 跑解、范围构建、节点锁定 (node-locking) 做剥削、用 HUD+数据库 (Hold'em Manager/PokerTracker/Hand2Note) 复盘找漏洞 (leak finding); (c) 牌型分层 — 现金局 (cash game) vs 锦标赛 (MTT) 的根本差异，后者叠加 ICM (独立筹码模型) 与跳台/泡沫期博弈; (d) 核心概念栈 — 范围 (range)/权益 (equity)/EV/位置 (position)/翻前开池与 3-bet/4-bet/翻后下注理论 (c-bet、极化 vs 浓缩范围、MDF 最小防守频率、阻断牌 blockers、超池下注 overbet)、SPR、底池赔率; (e) 元层 — 资金管理 (bankroll management)、桌位选择 (table selection)、方差与心态 (mental game/tilt 控制)、抽水 (rake) 与场次选择对长期赢率 (winrate, bb/100) 的影响; (f) 智识演进 — 从 Sklansky 古典手牌价值 → Janda/Tipton 博弈论 → solver 普及 → GTO Wizard 民主化求解 → AI 超人 (Libratus/Pluribus) 对人类策略的反哺。学派分歧: GTO 派 vs 剥削派、现金局 vs 锦标赛、理论自上而下 vs 牌局自下而上、solver 纯学院派 vs 实战感觉派。不含: 线下牌场运营/发牌荷官、博彩合规与赌场管理、扑克之外的牌类 (桥牌/斗地主)、纯概率赌博 (老虎机/轮盘)。) Master OS — automated mastery of 德州扑克策略 (Texas Hold'em) — solver/GTO 时代的无限注德州扑克竞技打法，牌手/职业视角。覆盖: (a) 理论两极 — GTO 博弈论均衡 (不可剥削的基线策略) vs | swaylq/master-skill | 106 | 2026-06-05 |
| 3602 | research-refineTurn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.6-Sol review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea. | wanshuiyin/Auto-claude-code-research-in-sleep | 13.3k | 2026-07-10 |
| 3603 | k12-smart-teacherK12智能老师辅导系统，支持作业批改、错题分析、举一反三练习生成。覆盖小学/初中/高中全学段，语文/数学/英语/物理/化学/生物/历史/地理/政治九大学科，自动识别学科年级，生成梯度练习试卷和Word文档。 | 18816132863/xiaoyi-claw-omega-final | 2 | 2026-04-25 |
| 3604 | ceo-masterTransforms the agent into a strategic CEO and orchestrator. Vision, decision-making, resource allocation, team dispatch, scaling playbook from €0 to €1B. Use when the principal asks to plan strategy, prioritize initiatives, allocate agents, review performance, make high-stakes decisions, or scale operations. Inspired by Musk, Bezos, Hormozi, Thiel, and proven scaling frameworks. | LeoYeAI/openclaw-master-skills | 2.1k | 2026-05-05 |
| 3605 | blazorBuild and review Blazor applications across server, WebAssembly, web app, and hybrid scenarios with correct component design, state flow, rendering, and hosting choices. USE FOR: building interactive web UIs with C# instead of JavaScript; choosing between Server, WebAssembly, or Auto render modes; designing component hierarchies and state. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made. | managedcode/dotnet-skills | 456 | 2026-06-17 |
| 3606 | paperzillaChat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or Atom feed URLs. | K-Dense-AI/scientific-agent-skills | 30.7k | 2026-06-11 |
| 3607 | powerbi-report-authoringCreate and modify Power BI report files in PBIR/PBIP format using the `powerbi-report-author` and `powerbi-desktop` CLIs. Use when the user wants to: (1) implement an approved report spec or design brief, (2) add or edit pages, visuals, filters, slicers, bookmarks, themes, or formatting, (3) validate PBIR and verify rendering in Power BI Desktop. For open-ended visual design, use `powerbi-report-design` first. For end-to-end requirements and approval workflow, use `powerbi-report-planning` first. Triggers: "edit PBIR", "create Power BI report page", "add visual to PBIP", "format report visual", "validate Power BI report", "reload Desktop screenshot", "implement an approved PBIP report spec", "edit PBIR pages/visuals". | microsoft/skills-for-fabric | 763 | 2026-07-09 |
| 3608 | email-writerProfessional email writing expert for tone, structure, clarity, and business communication | RightNow-AI/openfang | 18.0k | 2026-02-25 |
| 3609 | verify-security安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。 | fengshao1227/ccg-workflow | 5.7k | 2026-03-09 |
| 3610 | ai-pm-prototype原型生成技能。基于 PRD 生成可交互的单页网页原型，支持移动端和 Web 端。 首次生成时询问设计规范（公司规范 / AI 情境定制 / 主流组件库），项目内记住偏好。 若项目存在 Codex 生成的视觉锚点包（06-prototype-visual/manifest.json），生成 HTML 前必须读取并遵循。 当用户说「生成原型」「做原型」「可交互原型」「HTML原型」「页面原型」「低保真」「高保真原型」 「画个界面」「把PRD做成原型」时，立即使用此技能。 边界：本技能用于「把已有 PRD/需求做成可评审原型」；脱离 PRD 的纯视觉探索、通用 UI 组件生成或视觉精修，可使用外部 impeccable 增强，但 AI_PM 原型默认以 ai-pm-frontend-design 为本地设计内核。 | K3tty5555/AI_PM | 3 | 2026-07-10 |
| 3611 | design-taste-frontend-v1The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility. | Leonxlnx/taste-skill | 62.5k | 2026-05-28 |
| 3612 | web-js-reverse-master-flow用于复杂 Web/JS 网站还原的总控流程。适用于 sign/token/cookie/header/body/websocket 字段逆向、重混淆、花指令、控制流平坦化、JSVMP、worker/wasm、浏览器与 Node 差分、补环境、本地复现与回归，也覆盖 Akamai/Kasada/PX/reese84/同盾/a_bogus/腾讯滑块/阿里滑块/JSVMP/227/226/wasm/protobuf/rid/fuid/fs/bx-pp/run_js/storage.estimate/animationend 等案例线索。默认按 jshook + js-reverse + chrome-devtools-mcp 三 MCP 协同调试分析，并在 locate、recover、runtime、env-patch、replay 各阶段切换专项 skill。 | firstrui/codex-reverse-skills | 25 | 2026-03-25 |
| 3613 | vueuse-functionsApply VueUse composables where appropriate to build concise, maintainable Vue.js / Nuxt features. | vueuse/vueuse | 22.3k | 2026-07-03 |
| 3614 | electron-skillsElectron patterns for LlamaFarm Desktop. Covers main/renderer processes, IPC, security, and packaging. | llama-farm/llamafarm | 833 | 2026-01-29 |
| 3615 | superpowers-brainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. | Labhund/hermes-superpowers | 22 | 2026-04-07 |
| 3616 | value-propositionDesign a detailed value proposition using a 6-part JTBD template — Who, Why, What before, How, What after, Alternatives. Use when creating a value proposition, analyzing customer value delivery, or articulating why customers should choose your product. | phuryn/pm-skills | 23.6k | 2026-03-03 |
| 3617 | ansys-helpSearches local Ansys Help documentation by user-provided path and keywords, then returns high-relevance snippets quickly. Covers software names (HFSS, Q3D, Maxwell, Icepak, SIwave), feature modules (modeling, meshing, solving, post-processing, parallel computing), operation how-tos (fillet, mesh setup, material setup, ports/boundaries, S-parameters, radiation patterns), use-case names (microstrip antenna, via), and specific errors. | XinQiEM/oh-my-sci-skill | 2 | 2026-03-15 |
| 3618 | rust-testingRust测试模式，包括单元测试、集成测试、异步测试、基于属性的测试、模拟和覆盖率。遵循TDD方法学。 | affaan-m/ECC | 228.9k | 2026-03-22 |
| 3619 | ljg-push把 ~/.agents/skills/ljg-* 里所有更新过的 skills 同步到 github repo (ljg-skills)，先推 master 分支（org-mode 输出风格），再切 md 分支（markdown 输出风格）做基础 markdown 化后推。Use when user says '/ljg-push', 'push skills', '推送 skills', '同步 skills', 'sync ljg', or whenever ljg-* skills get updated and need shipping. NOT FOR pushing non-ljg skills or arbitrary git repos. | lijigang/ljg-skills | 6.5k | 2026-07-11 |
| 3620 | amazon-competitor-analysisFull-spectrum Amazon competitor analysis. Compare listings, pricing, reviews, advertising strategy, and market positioning against direct competitors. Identify weaknesses to exploit and strengths to counter. Use when the user asks about competitor analysis, competitive research, ASIN comparison, pricing analysis, or how to beat competitors on Amazon. | nexscope-ai/Amazon-Skills | 383 | 2026-06-05 |
| 3621 | subagent-driven-developmentExecute plans via delegate_task subagents (2-stage review). | NousResearch/hermes-agent | 213.7k | 2026-06-04 |
| 3622 | stm32-cubemxSTM32CubeMX命令行界面（CLI）用于配置引脚、外设、DMA（直接内存访问）、中断以及生成相应的代码。使用场景包括： 1. 添加或修改STM32外设的配置； 2. 配置USART（串行通信接口）、SPI（串行外设接口）、I2C（串行接口）、ADC（模数转换器）和TIM（定时器）等外设； 3. 设置DMA和中断的相关参数； 4. 生成CMake或GCC项目所需的代码文件。 默认的目标微控制器为STM32F103C8Tx。 | AgentWorkers/skills | 1 | 2026-03-01 |
| 3623 | perlFull Perl development aid. Use when the user wants to create, edit, run, debug, or test Perl scripts and modules. Scaffolds files with proper headers, follows Perl best practices, executes scripts, and assists with debugging. | Gary-Ash/dotfiles | 0 | 2026-04-25 |
| 3624 | global-stock-data美股港股全栈数据工具包 — 覆盖行情(新浪+腾讯+东财push2)、K线(新浪+Yahoo)、技术指标(MA/MACD/RSI/KDJ/布林带)、基本面(东财datacenter三表+GMAININDICATOR+Yahoo quoteSummary+SEC XBRL)、资金面(东财push2his日级资金流)、期权(Yahoo)、SEC Filing(EDGAR)、搜索与工具(东财search+Yahoo+SEC CIK+全市场列表)八层数据源，内嵌全部调用代码，自包含零依赖外部文件。适用于美股港股个股分析、全市场筛选、财报解读、期权策略、SEC文件检索、资金流追踪、机构持仓分析等场景。 | simonlin1212/global-stock-data | 1.1k | 2026-06-20 |
| 3625 | pwa-installabilityUse when auditing PWA readiness, adding an install prompt, or preparing a web app for submission to Microsoft Store or Google Play via PWA Builder. | thedaviddias/Front-End-Checklist | 73.2k | 2026-05-29 |
| 3626 | marketing-contextCreate and maintain the marketing context document that all marketing skills read before starting. Use when the user mentions 'marketing context,' 'brand voice,' 'set up context,' 'target audience,' 'ICP,' 'style guide,' 'who is my customer,' 'positioning,' or wants to avoid repeating foundational information across marketing tasks. Run this at the start of any new project before using other marketing skills. | alirezarezvani/claude-skills | 22.4k | 2026-06-11 |
| 3627 | social-media-automation自媒体运营自动化技能，支持小红书、抖音、微信公众号、视频号等平台的内容生成、图片生成、数据管理和自动化发布。包含 Tavily API 搜索、内容生成、图片生成、HAP 数据管理和自动化发布等完整流程。新增每日热点内容推荐功能。图片生成支持并行生成、自动下载、自动跳过已存在图片等优化功能。强制要求从 HAP "账号人设" 表读取账号人设配置，禁止使用本地文件。 | garfield-bb/hap-skills-collection | 27 | 2026-02-05 |
| 3628 | video-expert-analyzerAdvanced video analysis and selection skill with AI-powered automatic scoring. Integrates Walter Murch's rules and dynamic weighting for professional-grade curation. Supports Bilibili, YouTube, Douyin (抖音), and Xiaohongshu (小红书). Use this skill whenever the user wants to analyze videos, score or rate scenes, extract best shots/highlights, evaluate video quality, curate clips, do competitor video analysis, or mentions terms like "视频分析", "镜头筛选", "场景评分", "视频拆解", "精选片段", "视频质量", "镜头打分", "素材挑选" — even if they don't explicitly ask for "expert analysis". | ALBEDO-TABAI/video-expert-analyzer | 213 | 2026-03-25 |
| 3629 | treatment-plansGenerate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability. | foryourhealth111-pixel/Vibe-Skills | 2.4k | 2026-03-03 |
| 3630 | captcha-solverThree-layer CAPTCHA handling supporting 30+ CAPTCHA types. Layer 1: CloakBrowser prevents CAPTCHAs. Layer 2: ClickSolver (free) clicks Turnstile checkboxes + ALTCHA/Prosopo auto-solve. Layer 3: 2Captcha/CapSolver API fallback solves everything else. Supports reCAPTCHA v2/v3/Enterprise, hCaptcha, Cloudflare Turnstile, GeeTest, FunCaptcha, Amazon WAF, Friendly Captcha, KeyCaptcha, DataDome, Kasada, Akamai, Imperva, Yandex, VK, Tencent, Lemin, MTCaptcha, CyberSiARA, Cutcaptcha, Capy, atbCAPTCHA, ALTCHA, Prosopo, and image/text CAPTCHAs. ALWAYS use fully automated solving - never ask user to solve manually. | clawdbrunner/captcha-solver | 196 | 2026-05-20 |
| 3631 | clinical-decision-supportGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis. | K-Dense-AI/scientific-agent-skills | 30.7k | 2026-06-11 |
| 3632 | motor-foc-controlFOC磁场定向控制深度指南 | 深入讲解FOC原理、SVPWM、MTPA、弱磁控制、龙贝格观测器，配合实测案例、C代码和PI整定脚本 | LeoYeAI/openclaw-master-skills | 2.1k | 2026-06-08 |
| 3633 | deepseek-visionUse whenever the user references an image (local file path or http/https URL — screenshot, photo, diagram, UI capture, chart, error dialog) and you need to know what's in it to answer or act. Calls a vision model (Qwen3.6-Flash by default) via DashScope and returns a text description you can reason over. Especially important when running on a text-only backend like DeepSeek V4, but also useful as a dedicated OCR / detail extractor even when the main model is multimodal. | Agents365-ai/dsclaude | 55 | 2026-07-09 |
| 3634 | iso-13485-certificationComprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work instructions, (4) preparing Medical Device Files, (5) understanding ISO 13485 requirements, or (6) identifying missing documentation for medical device certification. Also use when users mention medical device regulations, QMS certification, FDA QMSR, EU MDR, or need help with quality system documentation. | K-Dense-AI/scientific-agent-skills | 30.7k | 2026-06-11 |
| 3635 | design-taste-frontend-v1The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility. | nexu-io/open-design | 77.6k | 2026-06-02 |
| 3636 | chemistry-rdkitComputational chemistry with RDKit for molecular analysis, descriptors, fingerprints, and substructure search. Use when working with SMILES, drug discovery, or cheminformatics tasks. | aiming-lab/AutoResearchClaw | 13.8k | 2026-03-31 |
| 3637 | arc42-documentationCreate comprehensive architecture documentation using the arc42 template structure (12 sections covering introduction, constraints, context, solution strategy, building blocks, runtime, deployment, concepts, decisions, quality, risks, and glossary). | oocx/tfplan2md | 169 | 2025-12-29 |
| 3638 | 3dsmax-scriptingAutomate 3ds Max with MAXScript and Python — scene manipulation, object creation, material assignment, camera setup, batch operations, UI tools, and file I/O. Use when tasks involve automating repetitive 3ds Max workflows, batch processing scenes, creating custom tools, or scripting scene setup for archviz, product visualization, or VFX. | TerminalSkills/skills | 99 | 2026-05-13 |
| 3639 | working-memoryLoad your current context at session start. Shows what you were working on, active priorities, and unresolved flags. Also trigger when resuming after a break or when the user asks what am I working on. | nowledge-co/community | 131 | 2026-06-24 |
| 3640 | wps-cn-calendar日历排班值班表。生成带法定节假日和调休标注的月度/年度日历表，
还能做三班倒/两班倒排班表和节假日值班安排，颜色区分不同班次一目了然。
用于帮助用户生成日历和排班表。当用户提到日历、排班、值班、节假日时触发。
Chinese calendar with holidays, shift scheduling, and duty rosters. | Bwkyd/wps-skills | 3 | 2026-05-10 |
| 3641 | x64dbg-reverse-engineeringThis skill should be used when performing binary analysis, debugging, reverse engineering, unpacking, or vulnerability research with x64dbg debugger via MCP. Provides expert knowledge on x64dbg MCP tools, Windows internals, assembly patterns, and reverse engineering methodology. | SetsunaYukiOvO/x64dbg-mcp | 276 | 2026-04-29 |
| 3642 | yingdao-rpa影刀RPA平台的Python自动化开发技能。触发：用户提到影刀/xbot/自动化模块/excel网页/OCR，或要求开发新的影刀应用模块、开发xbot自动化脚本。必须激活此skill来处理影刀相关的代码开发任务。 | adventure-111/yingdao-rpa | 1 | 2026-04-24 |
| 3643 | awesome-design-html118 single-page HTML design references: a 中国传统色 Chinese Traditional Colors swatch page (742 named hues, hue-grouped, click-to-copy HEX/RGB, under assets/web/design.zhongguo-colors.html) + 96 marketing webpages (Stripe, Linear, Notion, Apple, Vercel, Figma, Airbnb, Cursor, Claude, BrowserOS, Bun, Spotify, Tesla, Ferrari, BMW + China tier: 飞书 Feishu, 抖音 Douyin, 豆包 Doubao, 阿里云 Aliyun, 支付宝 Alipay, 钉钉 DingTalk, 语雀 Yuque, 腾讯云 Tencent Cloud, 微信 WeChat, DeepSeek, Kimi, 文心一言 Wenxin, 通义千问 Qwen, Qwen Cloud, 小米汽车 Xiaomi EV, 蔚来 NIO, 理想 Li Auto, 极氪 ZEEKR, 哔哩哔哩 Bilibili, 米哈游 miHoYo, 小米 Xiaomi, 小红书 Xiaohongshu) under assets/web/ + 22 iOS app mockups (Instagram, Spotify, TikTok, WhatsApp, Telegram, Discord, Threads, X/Twitter, Snapchat, YouTube, Netflix, Apple Music, Uber, Airbnb, ChatGPT, Notion, Tinder, Hinge, Starbucks, DoorDash, Robinhood, Duolingo) under assets/ios/. Each HTML contains brand-faithful demo + design system reference. Triggers: '中国传统色', '中国色色卡', '传统色配色', '做个飞书风的页面', '参考 DeepSeek 极简', '小米汽车 hero', '小红书风格瀑布流' | yzfly/awesome-design-html | 122 | 2026-06-14 |
| 3644 | website-clonerBuild an improved website clone from a URL via 6-phase gated workflow (Vite/React/shadcn/Tailwind + GitHub Pages). Use for end-to-end site rebuilds. Don't use for single-phase work. | luongnv89/skills | 93 | 2026-07-01 |
| 3645 | mfg-production-planningDesign production plans using MPS (Master Production Schedule), MRP (Material Requirements Planning), and capacity planning. Use this skill when the user needs to schedule production, plan material procurement, balance capacity with demand, or optimize production sequencing — even if they say 'we can't keep up with orders', 'when should we order materials', 'production scheduling', or 'how do we plan for next quarter's demand'. | asgard-ai-platform/skills | 217 | 2026-04-10 |
| 3646 | hermes-ephemeral-delegationTrigger: broad exploration, multi-file reads, tests/builds, fresh review, or multi-step debug. Orchestrate complex work via delegate_task to protect context. | Gentleman-Programming/gentle-ai | 4.8k | 2026-06-14 |
| 3647 | zentao禅道(ZenTao) MCP大模型能力扩展包。提供跨项目的数据聚合视图、一句话生成任务、无缝报工(Log Effort)、自动状态流转等四组原生能力。 | LeoYeAI/openclaw-master-skills | 2.1k | 2026-06-22 |
| 3648 | domain-driven-designExpert guidance for Domain-Driven Design architecture and implementation. Use when designing complex business systems, defining bounded contexts, structuring domain models, choosing between modular monolith vs microservices, implementing aggregates/entities/value objects, or when users mention "DDD", "domain-driven design", "bounded context", "aggregate", "domain model", "ubiquitous language", "event storming", "context mapping", "domain events", "anemic domain model", strategic design, tactical patterns, or domain modeling. Helps make architectural decisions, identify subdomains, design aggregates, and avoid common DDD pitfalls. | joaquimscosta/arkhe-claude-plugins | 20 | 2026-03-26 |
| 3649 | validate-ideaValidate a business idea using the minimalist entrepreneur framework. Use when someone has a business idea and wants to test if it's worth pursuing before building anything. | slavingia/skills | 9.5k | 2026-03-23 |
| 3650 | motor-controlPatterns for electric motor control including Field Oriented Control (FOC), stepper motor control, encoder interfaces, current sensing, and power electronics. Covers BLDC, PMSM, DC brushed, and stepper motor applications. Use when ", " mentioned. | omer-metin/skills-for-antigravity | 106 | 2026-01-22 |
| 3651 | level-designWorld-class level design expertise - spatial storytelling, player flow, blockout methodology, and the invisible hand that guides players without them knowingUse when "level design, blockout, graybox, whitebox, player flow, level layout, combat arena, exploration space, map design, multiplayer map, pacing, weenie, landmark, gating, metroidvania, open world design, linear level, environmental storytelling, teaching through design, playtesting, heatmap, metrics, sightlines, level-design, game-development, spatial-design, blockout, graybox, player-flow, pacing, environmental-storytelling, combat-design, multiplayer-maps, open-world, linear-design, metroidvania" mentioned. | omer-metin/skills-for-antigravity | 106 | 2026-01-22 |
| 3652 | elite-github-skills-hubCurated hub of the highest-value GitHub skills/repos for Claude Code, Cursor, Codex, Gemini CLI, and OpenClaw. Links to 20+ elite repos organized by tier. Use when discovering, evaluating, or installing skills from the open-source ecosystem. | aAAaqwq/AGI-Super-Team | 74 | 2026-05-19 |
| 3653 | solidity-securityMaster smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications. | wshobson/agents | 37.8k | 2026-05-22 |
| 3654 | midjourney-card-news-backgroundsGenerate Midjourney prompts for 600x600 card news background images based on topic, mood, and style preferences. Use when user requests card news backgrounds or Instagram post backgrounds. | bear2u/my-skills | 888 | 2025-10-25 |
| 3655 | reasoningbank-intelligenceImplement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems. | ruvnet/ruflo | 64.2k | 2026-02-07 |
| 3656 | daily-briefingStart your day with a prioritized sales briefing. Works standalone when you tell me your meetings and priorities, supercharged when you connect your calendar, CRM, and email. Trigger with "morning briefing", "daily brief", "what's on my plate today", "prep my day", or "start my day". | anthropics/knowledge-work-plugins | 22.6k | 2026-01-29 |
| 3657 | depmapQuery the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use for identifying cancer-specific vulnerabilities, synthetic lethal interactions, and validating oncology drug targets. | K-Dense-AI/scientific-agent-skills | 30.7k | 2026-06-11 |
| 3658 | theone-cocos-standardsEnforces TheOne Studio Cocos Creator development standards including TypeScript coding patterns, Cocos Creator 3.x architecture (Component system, EventDispatcher), and playable ads optimization guidelines. Triggers when writing, reviewing, or refactoring Cocos TypeScript code, implementing playable ads features, optimizing performance/bundle size, or reviewing code changes. | The1Studio/theone-training-skills | 77 | 2025-11-19 |
| 3659 | a-stock-dataA股全栈数据工具包 — 覆盖行情(mootdx+腾讯+百度K线)、研报(东财+同花顺+iwencai)、信号(同花顺热点+北向+龙虎榜+解禁+行业)、资金面(融资融券+大宗交易+股东户数+分红+资金流分钟级+资金流120日)、新闻(东财个股+全球资讯)、基础数据(mootdx财务/F10+东财+新浪三表)、公告(巨潮)七层数据源，内嵌全部调用代码，自包含零依赖外部文件。优先用通达信(mootdx)/腾讯(不封IP)，东财接口已内置限流防封。适用于个股估值、研报检索、题材归因、龙虎榜跟踪、解禁预警、行业轮动、融资融券跟踪、筹码分析、产业链调研、批量筛选等场景。 | WeaveQ/OnMyAgent | 4 | 2026-07-02 |
| 3660 | ian-handdrawn-pptCreate final Chinese handdrawn technical article/PPT-style page images from articles, Markdown, PDFs, DOCX files, existing slide decks, course notes, scripts, outlines, or rough ideas. Use when the user asks to turn content into PPT/PPTX/slides/courseware/课件/演示稿/配图/效果图 in a refined Chinese handdrawn technical explanation style, to plan such pages, to choose page layouts from semantic content, or to generate complete image-model pages with Chinese text baked into the final visual. Default article outputs use 21:9 covers and 16:9 body illustrations. | helloianneo/ian-handdrawn-ppt | 1.2k | 2026-04-25 |
| 3661 | cfd-researchTop-level CFD research entry — alias for cfd-skills/cfd-pipeline (general path). Use when the user gives a CFD research topic and wants the full literature → hypothesis → mesh-gate → experiments → analysis → paper flow. The full self-contained recipe lives in cfd-skills/cfd-pipeline/SKILL.md. | csml-rpi/AI-CFD-Scientist | 35 | 2026-05-06 |
| 3662 | youtube-scriptwritingWrite retention-optimized long-form YouTube scripts through a checkpoint workflow (research, hook, structure, body, editing). Use when asked to "write a YouTube script", "YouTube video outline", "long-form video script", "improve video retention", "structure a YouTube video", or when turning raw ideas/transcripts/notes into a compelling video script. Covers hook formats, 7 story structures, rehook techniques, editing audits, and outro binge loops. | exiao/skills | 35 | 2026-05-12 |
| 3663 | origin-generic-plot调用 originpro / Origin 从任意数据来源画图。Use when 用户要用 Origin 画图、originpro 自动作图、点线图/散点图/折线图/柱状图、设置横纵坐标名称与单位、处理多组数据、把样品名写入注释列 comments 并同步图例。 | cxrxhz/tools | 0 | 2026-05-21 |
| 3664 | autosar-diagnostics-stack-expertExplains AUTOSAR Classic Diagnostics Stack architecture across DCM, DEM, DET, FiM, and transport integration over CAN or Ethernet DoIP. Use when the user asks about UDS request handling, DTC/event management, diagnostic timing (P2/P2*/S3), diagnostics routing, or troubleshooting ECU diagnostic behavior. | longluubao/computer_engineering_project | 1 | 2026-03-10 |
| 3665 | pytest-patternsPython testing skill using pytest, covering fixtures, parametrize, markers, conftest, plugins, mocking, and advanced testing patterns. | PramodDutta/qaskills | 170 | 2026-02-11 |
| 3666 | turundus-sisuTurismiettevõtte turundus ja sisuloome — sotsiaalmeedia, veebitekstid, SEO, reklaamid, uudiskirjad, blogiartiklid, landing page'id, brändiloo, video skriptid, influencerid. Kasuta kui kasutaja mainib: turundus, sisu, sotsiaalmeedia, blogi, uudiskiri, reklaam, SEO, landing page, kampaania, brändi lugu, video, influencer, hashtag, turunduskalender, sisuloome, Facebook, Instagram, TikTok, Google Ads, pressiteade. | Kasulik-AI/kasulik-ai-plugins | 0 | 2026-05-04 |
| 3667 | airflow-dag-patternsBuild production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs. | wshobson/agents | 37.8k | 2026-05-22 |
| 3668 | futures-position-tracker期货持仓分析工具。获取期货品种持仓排名（前20名期货公司）、持仓结构（多头/空头）、持仓集中度。分析主力资金动向、持仓变化信号。使用交易所持仓数据、AkShare数据。适用于主力资金跟踪、市场情绪判断。 | aifinlab/FinClaw | 202 | 2026-03-25 |
| 3669 | nextflowBuild, run, and debug Nextflow data pipelines and nf-core workflows end to end. Use whenever the user mentions Nextflow, nf-core, .nf files, nextflow.config, DSL2, processes/channels/operators, samplesheets, or wants to run a community pipeline (e.g. nf-core/rnaseq, nf-core/sarek), write or test a module/subworkflow with nf-test, configure executors/containers (Docker, Singularity/Apptainer, Conda, Wave), scale a workflow to HPC/SLURM or cloud (AWS Batch, Google Batch, Azure, Kubernetes), or debug a failed/-resume run. Make sure to use this skill for any reproducible scientific/bioinformatics workflow work even if the user does not say the word "Nextflow", and for authoring nf-core-compliant pipelines, modules, configs, and linting. | K-Dense-AI/scientific-agent-skills | 30.7k | 2026-06-11 |
| 3670 | himalayaHimalaya CLI: IMAP/SMTP email from terminal. | NousResearch/hermes-agent | 213.7k | 2026-06-21 |
| 3671 | brochure-design-generationGenerate professional brochure designs using each::sense AI. Create tri-fold, bi-fold, corporate, travel, product, real estate, healthcare, educational, event, and service brochures with print-ready layouts. | eachlabs/skills | 20 | 2026-04-01 |
| 3672 | ux-css-layoutVS Code CSS conventions, file organization, class naming, standard sizes, SplitView/Grid layout, scrollable content, responsive layout, and text overflow/ellipsis patterns. Use when writing CSS, building layouts, or fixing text truncation issues. | microsoft/vscode | 187.5k | 2026-07-07 |
| 3673 | tooluniverse-inorganic-physical-chemistryInorganic chemistry, physical chemistry, and materials science — crystal structures, coordination chemistry, lattice parameters, thermodynamic properties, electronic structure. Use for unit cell volume calculations, coordination geometry, materials property estimation, and inorganic-mechanism reasoning. Complementary to tooluniverse-organic-chemistry. | mims-harvard/ToolUniverse | 1.6k | 2026-05-21 |
| 3674 | nano-banana-proNano Banana/Gemini image gen/edit: text/image input, 512-4K workflows. | steipete/agent-scripts | 6.3k | 2026-05-23 |
| 3675 | ima-skills统一的 IMA OpenAPI 技能，支持笔记管理和知识库操作。
当用户提到知识库、资料库、笔记、备忘录、记事，或者想要上传文件、添加网页到知识库、
搜索知识库内容、搜索/浏览/创建/编辑笔记时，使用此 skill。
即使用户没有明确说"知识库"或"笔记"，只要意图涉及文件上传到知识库、网页收藏、
知识搜索、个人文档存取（如"帮我记一下"、"搜一下知识库里有没有XX"），也应触发此 skill。 | zhizhunbao/workbuddy | 2 | 2026-03-31 |
| 3676 | self-improving-agentInstinct-based continuous learning system. Captures atomic learnings (instincts) with confidence scoring, supports project-scoped vs global scope, and evolves instincts into skills/commands/agents. Use when: (1) A command fails, (2) User corrects you, (3) Discovering patterns, (4) Need to review or evolve learned behaviors. Supports both v1 (markdown-based) and v2 (instinct-based) modes. | LeoYeAI/openclaw-master-skills | 2.1k | 2026-05-05 |
| 3677 | deepwiki技术文档查询，框架/库研究 | WenJunDuan/Rlues | 182 | 2026-07-03 |
| 3678 | futu-indicator-coder專門用於編寫富途牛牛 (Futu Niuniu) 或 Moomoo 指標程式碼的技能。當使用者要求「寫指標」、「富途腳本」、「通達信語法」或描述技術指標邏輯（如：均線交叉、布林帶突破）時使用。 | fredchu/claude-dotfiles | 2 | 2026-03-06 |
| 3679 | lark-minutes飞书妙记：搜索妙记、查看妙记基础信息、下载/上传音视频、读取或编辑妙记的产物内容、改标题、替换说话人/关键词。当给出minute_token、本地音视频文件，要查/改/转妙记产物时使用；本地音视频转纪要/逐字稿优先走本 skill，不要用 ffmpeg/whisper 本地转写。不负责：获取会议关联妙记，或仅按自然语言标题定位纪要 | larksuite/cli | 15.5k | 2026-07-07 |
| 3680 | markdown-to-docxConverts Markdown files (.md, .markdown) to DOCX using the markdown-docx npm package. Supports single and batch conversions, automatically generates output filenames, and creates Microsoft Word documents from Markdown content. | vace/markdown-docx | 342 | 2026-01-31 |
| 3681 | tiktok-video-detailTikTok single video detail scraper: input a TikTok video URL → output full video metadata (author profile, engagement stats, music, video meta, hashtags, mentions, slideshow images). Use when user mentions TikTok video detail, get TikTok video data, extract TikTok video metadata, scrape single TikTok video, TikTok video info, extract single TikTok video info, TikTok single video collection, tiktok video scraper, tiktok video url scraper. Also applies to batch URL processing (given a list of TikTok video URLs, extract metadata for each), verifying specific video stats, or archiving individual TikTok posts with full metadata. | browser-act/skills | 4.3k | 2026-05-25 |
| 3682 | prompt-analyzer提示词分析与洞察 - 查看Prompt详情、对比差异、推荐相似提示词、元素库统计 | huangserva/skill-prompt-generator | 1.4k | 2026-01-05 |
| 3683 | caipiao-500500 彩票网竞彩足球当日售卖中全部场次（含欧五大联赛、杯赛、亚洲联赛等）的对阵、亚盘、欧赔、数据分析、预计阵容快照。回答赛前盘口/赔率/交战历史类问题。 | nelsonie/caipiao | 0 | 2026-07-10 |
| 3684 | analyse-with-phpstanAnalyse PHP code with PHPStan via the playground API. Tests across all PHP versions (7.2–8.5) and reports errors grouped by version. Supports configuring level, strict rules, and bleeding edge. | phpstan/phpstan | 14.0k | 2026-02-21 |
| 3685 | agent-introspection-debugging针对AI代理故障的结构化自调试工作流程，包括捕获、诊断、受限恢复和内省报告。 | affaan-m/ECC | 228.9k | 2026-05-11 |
| 3686 | moai-domain-databaseDatabase specialist covering PostgreSQL, MongoDB, Redis, Oracle, and cloud database platforms (Neon, Supabase, Firestore). Use for schema design, query optimization, indexing strategies, data modeling, or cloud database selection. Cloud vendor guide absorbed from moai-platform-database-cloud. | modu-ai/moai-adk | 1.1k | 2026-07-07 |
| 3687 | storyboard-managerAssist writers with story planning, character development, plot structuring, chapter writing, timeline tracking, and consistency checking. Use this skill when working with creative writing projects organized in folders containing characters, chapters, story planning documents, and summaries. Trigger this skill for tasks like "Help me develop this character," "Write the next chapter," "Check consistency across my story," or "Track the timeline of events." | ailabs-393/ai-labs-claude-skills | 422 | 2025-11-06 |
| 3688 | ssh-skillCRITICAL: Use this skill for ALL SSH/server operations. NEVER run raw ssh/scp directly. Triggers: SSH, remote server, server IP/hostname/user@host, connect/login, run command on server, check server/status, deploy, upload/download, file transfer, bastion/jump host, server-to-server transfer, migrate, tunnel, port forward, database/internal service access, and Chinese terms: 服务器, 远程, 连接, 登录, 上传, 下载, 部署, 跳板机, 服务器间传输, 迁移, 隧道, 端口转发, 数据库连接, 内网访问. Provides persistent connections, pooling, jump hosts, SFTP, tunneling, and recovery. DO NOT use for local commands, localhost, or current-directory work. | badseal/ssh-skill | 409 | 2026-05-23 |
| 3689 | drama-director短剧漫剧导演 — 一键把剧本/小说段落转成九宫格分镜 + 15 秒漫剧视频。接入 Atlas Cloud 的 GPT Image 2（九宫格漫剧页）和 Seedance 2.0 I2V（15s 动画），一个 API key 打通全流程。触发词：短剧、漫剧、剧本转视频、小说转视频、分镜生成、九宫格、storyboard、comic drama、漫画页、AI 短剧制作、GPT Image 2 + Seedance。 | kianaliang-dev/drama-director-skill | 26 | 2026-04-24 |
| 3690 | user-personasCreate refined user personas from research data — 3 personas with JTBD, pains, gains, and unexpected insights. Use when building personas from survey data, creating user profiles from research, or segmenting users for product decisions. | phuryn/pm-skills | 23.6k | 2026-03-03 |
| 3691 | harmonyos-device-automationVision-driven HarmonyOS NEXT device automation using Midscene. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. Control HarmonyOS devices with natural language commands via HDC. Perform taps, swipes, text input, app launches, screenshots, and more.
Trigger keywords: harmony, harmonyos, 鸿蒙, hdc, huawei device, harmony app, harmony automation, harmony phone, harmony tablet, test harmony app, verify on harmonyos, QA on 鸿蒙, check the app on harmony, test on huawei device, see if the app works on harmony, end-to-end test on harmonyos, visual verification on 鸿蒙
Powered by Midscene.js (https://midscenejs.com) | web-infra-dev/midscene-skills | 268 | 2026-06-08 |
| 3692 | stata-accounting-guideSTATA code for empirical accounting and financial economics research | brycewang-stanford/Auto-Empirical-Research-Skills | 2.7k | 2026-04-03 |
| 3693 | lab-report-writer撰写期刊风格的实验报告，支持理工科实验课报告、科研论文级实验记录、工程项目技术报告、竞赛展示用报告等全场景。
用户提供实验信息、数据、方法描述后，生成结构完整、排版专业的报告，并附带Python数据验证脚本对所有计算结论进行复核。
触发条件（凡符合以下任一项，均应使用本skill）：
- 用户说"帮我写实验报告"、"写一份实验记录"、"整理实验数据"、"写技术报告"
- 用户提供了实验原始数据并想生成正式报告
- 用户说"我有实验结果，帮我整理成报告"
- 用户想把markdown或word报告转成HTML期刊风格
- 任何涉及"实验"+"报告/记录/总结"的组合请求
- 用户提到要生成包含数据图表、公式推导、误差分析的正式文档
输出格式：优先HTML报告（期刊风格）；也可输出Markdown或Word（.docx）。
如果用户提供了Markdown/Word报告，应提醒其可升级为HTML报告。 | endearqb/endearqb-skills | 18 | 2026-06-01 |
| 3694 | book-readerAI 逐页读书技能：将 PDF/EPUB/MOBI/TXT 书籍按页/章解析提取文本，分批提炼知识点，生成阶段性摘要，并输出结构化的本地 Markdown 读书笔记。 当用户提到读书笔记、分析/总结一本书、阅读并提取要点、PDF/EPUB/MOBI/TXT 摘要或知识提取、 “帮我读这本书/看看这本书/分析这本 PDF”、summarize this book、extract knowledge from PDF/book 等场景时使用本技能； 即使用户未明确提到“skill”，只要目标是从书籍文件产出笔记/总结也应触发。 | hijiangtao/book-reader-skill | 5 | 2026-03-18 |
| 3695 | kimi-datasourceUniversal data-source assistant. Use this skill when the user wants external structured data such as stocks, financial reports, technical indicators, A-share/HK/US markets, global macroeconomics, Chinese enterprise registry information, arXiv papers, Google Scholar results, or Chinese laws/regulations and judicial cases.
This plugin exposes tools via MCP server `plugin-kimi-datasource_data`; call them in the flow `mcp__plugin-kimi-datasource_data__get_data_source_desc` → `mcp__plugin-kimi-datasource_data__call_data_source_tool`. | MoonshotAI/kimi-code | 3.1k | 2026-06-10 |
| 3696 | rust-reviewAudits Rust code for unsafe blocks, ownership issues, and Cargo dependency risks. Use when reviewing Rust code or before merging Rust changes. | athola/claude-night-market | 323 | 2026-07-01 |
| 3697 | wecom-doc当用户提到企业微信文档、智能表格、创建文档、编辑文档、写文档时启用。优先复用 wecom channel 自动写入的文档 MCP 配置，并通过 mcporter 调用文档能力。 | BytePioneer-AI/openclaw-china | 4.0k | 2026-03-17 |
| 3698 | screenwriter文生视频提示词生成器。从故事想法生成 Storyboard，串联多个镜头提示词，支持想法/优化/简化三阶段。跨平台通用。 | hylarucoder/seedance-screenwriter-skills | 54 | 2026-02-16 |
| 3699 | ib-pitch-bookOpen Design's investor pitch book: market map, moat, unit economics, and the ask — analyst-grade and diligence-ready. Built as a decision-grade fundraising pitch deck for growth-equity investors. | nexu-io/open-design | 77.6k | 2026-07-10 |
| 3700 | continuous-learningAutomatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use. | affaan-m/ECC | 228.9k | 2026-03-04 |