| 3401 | abilitiesSchema and rules for creating abilities | nikolaj-lat/World-Puppeteer | 12 | 2026-06-15 |
| 3402 | perplexity-researchBrain-augmented web research. Sends brain context about a topic to Perplexity, which searches the web with citations and returns what is NEW vs what the brain already knows. Use for entity enrichment, current-state checks, deal monitoring, and freshness deltas. NOT for simple URL fetches (use web_fetch) or brain-only queries (use gbrain query). | garrytan/gbrain | 26.8k | 2026-05-10 |
| 3403 | marketing-cross-border-ecommerce专注跨境电商全链路运营的策略专家，精通Amazon/Shopee/Lazada/AliExpress/Temu/TikTok Shop等海外平台运营、国际物流与海外仓、跨境合规税务、多语言Listing优化、品牌出海及DTC独立站建设。 | itgoyo/hermes-skills | 30 | 2026-04-22 |
| 3404 | x-apiX/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically. | affaan-m/ECC | 232.1k | 2026-06-11 |
| 3405 | excel-bar-chart-visualization读取多工作表Excel文件，自动处理合并单元格与数据清洗，进行交叉分组统计并生成带总计行的结果表，最后绘制支持中英文字体的美化柱状图，适用于多维度数据汇总与可视化分析。 | OpenSenseNova/SenseNova-Skills | 4.8k | 2026-04-26 |
| 3406 | image-generation-super图片生成与编辑（超级版），调用 GPT-Image-2 模型生成和编辑图片。需要 AI 画图、生成图片、编辑图片、多图融合、背景替换、风格转换、电商商品图合成、海报设计、插画创作时优先使用该工具。纯像素操作（文字叠加、加水印、裁剪、缩放）请改用 Pillow，不要触发本工具。 | qq5855144/GitHubM | 20 | 2026-06-09 |
| 3407 | nanoclaw-repl操作并扩展NanoClaw v2，这是ECC基于claude -p构建的零依赖会话感知REPL。 | affaan-m/ECC | 232.1k | 2026-03-07 |
| 3408 | x-apiX/Twitter API集成，用于发布推文、线程、读取时间线、搜索和分析。涵盖OAuth认证模式、速率限制和平台原生内容发布。当用户希望以编程方式与X交互时使用。 | affaan-m/ECC | 232.1k | 2026-03-21 |
| 3409 | wechat-article-fetcher获取并解析微信公众号文章。从微信文章链接中提取标题、作者、公众号名称、正文内容、图片和元数据。当用户提供微信文章链接(mp.weixin.qq.com/s/...)并希望阅读、提取、下载或转换文章内容时使用。适用场景包括获取/下载微信文章、提取微信文章文字或元数据、将微信文章转换为Markdown、将微信文章连同图片保存到本地。关键词：微信公众号、文章获取、文章抓取、文章下载。 | wwwzhouhui/skills_collection | 254 | 2026-02-22 |
| 3410 | kotlin-coroutines-flowsKotlin Coroutines and Flow patterns for Android and KMP — structured concurrency, Flow operators, StateFlow, error handling, and testing. | affaan-m/ECC | 232.1k | 2026-06-11 |
| 3411 | ads-creativeAudit paid-ad copy, images, video, hooks, concepts, format coverage, platform-native fit, message match, creative fatigue, accessibility, and policy across supported platforms. Use for creative audit, ad creative, creative fatigue, creative diversity, ad copy review, video review, image review, or production priorities. | AgriciDaniel/claude-ads | 7.3k | 2026-07-11 |
| 3412 | ads-linkedinAudit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media. | AgriciDaniel/claude-ads | 7.3k | 2026-07-11 |
| 3413 | wechat-publisher一键发布 Markdown 到微信公众号草稿箱。基于 wenyan-cli，支持多主题、代码高亮、图片自动上传。 | dvcrn/openclaw-skills-marketplace | 24 | 2026-03-15 |
| 3414 | mvvm-toolkitCommunityToolkit.Mvvm (the MVVM Toolkit) core: source generators ([ObservableProperty], [RelayCommand], [NotifyPropertyChangedFor], [NotifyCanExecuteChangedFor], [NotifyDataErrorInfo]), base classes (ObservableObject / ObservableValidator / ObservableRecipient), commands (RelayCommand / AsyncRelayCommand), and validation. Companion skills: mvvm-toolkit-messenger for pub/sub, mvvm-toolkit-di for Microsoft.Extensions.DependencyInjection wiring. Works across WPF, WinUI 3, MAUI, Uno, and Avalonia. | github/awesome-copilot | 36.9k | 2026-05-11 |
| 3415 | etsy-competitor-analysisCompetitor research — pricing comparison, bestseller analysis, differentiation strategy | nexscope-ai/eCommerce-Skills | 446 | 2026-04-14 |
| 3416 | ui-ux-pro-maxUse when the user needs full UI/UX design intelligence — styles, palettes, fonts, UX guidelines, chart selection, and accessible, performant implementation across any supported stack. Triggers: user says "design", "UI", "UX", "color palette", "typography", "accessibility", "responsive design", "chart type", "style guide", building any user-facing interface. | Pixel-Process-UG/superkit-agents | 1 | 2026-03-15 |
| 3417 | safety-guardUse this skill to prevent destructive operations when working on production systems or running agents autonomously. | affaan-m/ECC | 232.1k | 2026-06-11 |
| 3418 | stock-question-refiner股票投资调研问题细化技能。将用户提供的股票名称/代码细化为结构化的8阶段投资尽调指令。通过提问澄清投资风格（价值/成长/困境反转）、持有周期（短/中/长线）、风险偏好、研究重点，生成符合专业投资研究标准的结构化调研任务。当用户提到股票分析、投资研究、股票尽调时使用此技能。 | liangdabiao/Claude-Code-Stock-Deep-Research-Agent | 351 | 2025-12-26 |
| 3419 | mobile-onboardingA multi-screen mobile onboarding flow rendered as three phone frames
side by side — splash, value-prop, sign-in. Status bar, swipe dots,
primary CTA. Use when the brief mentions "mobile onboarding", "iOS
onboarding", "phone signup", or "移动端引导". | nexu-io/open-design | 80.6k | 2026-05-18 |
| 3420 | personal-assistantA personalized assistant that remembers your preferences | NVIDIA/SkillSpector | 13.5k | 2026-05-12 |
| 3421 | test-case-gen测试用例生成技能。根据需求文档或用户故事，生成覆盖正向流程、异常流程、边界条件的完整测试用例集合。适用于 QA 工程师在新功能提测前设计测试用例。 | rowankid/ai-team | 3 | 2026-03-09 |
| 3422 | plantuml-syntaxThis skill should be used when the user asks about PlantUML syntax for C4-PlantUML, sequence, class, activity, state, ER, component, deployment, or use case diagrams, rendering errors, layout conflicts, skinparams, or themes. | tractorjuice/arc-kit | 2.1k | 2026-06-07 |
| 3423 | foundation-models-on-device苹果FoundationModels框架用于设备上的LLM——文本生成、使用@Generable进行引导生成、工具调用，以及在iOS 26+中的快照流。 | affaan-m/ECC | 232.1k | 2026-03-03 |
| 3424 | frontend-devFull-stack frontend development combining premium UI design, cinematic animations,
AI-generated media assets, persuasive copywriting, and visual art. Builds complete,
visually striking web pages with real media, advanced motion, and compelling copy.
Use when: building landing pages, marketing sites, product pages, dashboards,
generating media assets (image/video/audio/music), writing conversion copy,
creating generative art, or implementing cinematic scroll animations. | MiniMax-AI/skills | 13.1k | 2026-04-18 |
| 3425 | agnes-multimodalAgnes AI 全模态生成技能。覆盖文本生成(agnes-2.0-flash)、图片理解/Vision(agnes-2.0-flash)、 文生图(agnes-image-2.1-flash)、图生图、文生视频、图生视频、关键帧动画、自动中译英、异步轮询。 兼容 WorkBuddy、Codex、Claude Code、OpenClaw、Cursor、Windsurf 等所有支持 Agent Skills 的框架。 当用户需要 AI 生成文本/图片/视频，或提到 "Agnes"、"agnes"、"AI 画图"、"AI 生成视频"、 "AI 图片"、"文生图"、"图生图"、"文生视频"、"关键帧动画"、"用 Agnes 生成" 时触发。 API Key 默认从环境变量 AGNES_API_KEY 读取，也可在 agnes_client.py 中硬编码。 | fengtai227-hash/agnes-multimodal | 0 | 2026-06-12 |
| 3426 | lark-task飞书任务：管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更新智能体主页数据、写入任务记录时使用。 | larksuite/cli | 15.7k | 2026-07-14 |
| 3427 | siliconflow-vision图片识别与分析工具。使用视觉大模型识别图片内容，输出详细客观的识别结果供主模型分析。当用户发图片时，主模型必须直接调用此 skill，然后基于识别结果进行分析和回答。支持 SiliconFlow（默认）、OpenAI、Anthropic 等多服务商。 | modbender/skill-library-mcp | 10 | 2026-03-06 |
| 3428 | creative-writing-coachHelps users with creative writing and storytelling | NVIDIA/SkillSpector | 13.5k | 2026-05-12 |
| 3429 | harness-drift-from-historyOne-command drift detection. Composes audit-list + oia-audit + audit-trend into a single primitive — finds the most recent audit in `metaharness-audit` namespace, runs a fresh audit against the current repo, diffs them via ADR-152 §3.1 similarity, and alerts when structural distance crosses `--threshold`. Iter 53 of ADR-150 deep integration. | ruvnet/ruflo | 65.5k | 2026-06-16 |
| 3430 | videocut-skills视频剪辑 Agent Skill：自动剪辑/转场/字幕/特效，589 Stars | shibit-net/xuanji | 76 | 2026-05-30 |
| 3431 | pyside6-qml-architectureUse this skill when creating a new PySide6 + QML desktop application with MVC architecture, setting up project structure, implementing the application bootstrap / DI container, or understanding how the MVC layers connect. Covers project scaffolding, entry points, singleton application class, service locator, signal registry, and lifecycle management. | sleepyvani/tablemax | 26 | 2026-03-11 |
| 3432 | solidity-gas-optimizerGas optimization gate for Solidity contracts before deployment. Dispatches the optimizoor agent to run a full 8-category gas audit. Use when: tests pass and contract is ready for gas review, user asks "is this gas efficient?", "can we reduce gas costs?", "optimize gas", "check gas usage", or after any implementation change to a value-handling function. Covers: storage layout and slot packing, function visibility, calldata vs memory, loop optimization, arithmetic (unchecked), custom errors, compiler configuration, and event vs storage decisions. Produces a gas audit report with forge snapshot diff before deployment. | zaryab2000/decipher-solidity-superpowers | 0 | 2026-02-26 |
| 3433 | automotive-cybersecurity-tara-analystAutomotive TARA analyst performing threat analysis and risk assessment per ISO/SAE 21434 | dubgyd/automotive-antigravity-agents | 1 | 2026-03-25 |
| 3434 | mx-financial-assistant基于东方财富权威金融数据库，打造覆盖"数据-资讯-知识-分析-决策"全链条的智能问答服务。通过自然语言交互， 为用户提供从基础金融知识科普到专业投资研究支持的全方位解决方案，实现"一问即达"的高效金融信息获取体验。 涵盖七大核心能力：全市场金融数据实时查询（A港美股、基金、债券）、全网财经资讯智能检索（公告、研报、新闻、政策）、 全球宏观经济数据追踪（国民经济、货币财政、产业就业）、多维度智能选股选基（技术面、基本面、消息面）、 专业金融百科知识问答、深度金融市场分析（趋势、资金、情绪）、以及实时热点事件解读（政策、公告、行业变革）。 适配多元化应用场景，满足机构投资者在投资研究、资产配置、风险管理、策略回测等方面的专业需求， 同时支持个人用户的理财决策、知识学习、行情监控与投资组合管理。 当用户提出自然语言问题并希望获得智能回答时使用此技能，包括但不限于： "帮我查一下"、"请问"、"分析一下"、"选股"、"推荐股票"、"XX怎么样"、"XX是什么"、 "解释一下"、"总结一下"、"最新政策"、"宏观数据"、"市场行情"、"基金筛选"等问答类请求。 支持标准模式和深度思考模式（deepThink）。 此技能不适用于需要生成完整报告的场景（如行业跟踪报告、首次覆盖报告），这些场景应使用对应的报告生成技能。 | hiboys/ExploreFinance | 311 | 2026-05-16 |
| 3435 | video-template-frame-product-promo-30sUse this plugin when the user wants a "Product Promo · 30s" HyperFrames motion video — Multi-scene 30-second product promo: problem-type intro, brand reveal, benefits flowchart, product surfaces, value pillars, foundation, CTA outro. Forked from Nate Herk's hyperframes-student-kit (linear-promo-30s); brand-specific copy + assets replaced with generic placeholders. | nexu-io/open-design | 80.6k | 2026-07-14 |
| 3436 | openyida宜搭 AI 应用开发总入口技能。通过有 AI Coding 能力的智能体（悟空/Claude/Open Code 等）+ 宜搭低代码平台，实现一句话搭建或修改完整应用。 包含资源上下文解析、应用创建/复用、表单设计/更新、自定义页面开发、页面发布、登录态管理等完整开发流程。 当用户提到"宜搭"、"yida"、"低代码"、"创建应用"、"创建表单"、"发布页面"、"搭建"、"系统"等关键词时，使用此技能；以下情况不要触发：只是讨论通用前端/后端代码、非宜搭平台产品、或只需要解释概念而不操作宜搭资源。 | openyida/openyida | 196 | 2026-07-22 |
| 3437 | html5-semantic-elementsUse when reviewing templates, rendered HTML, or shared components related to Use semantic HTML elements. Validate the final browser-facing markup, not just the source framework abstraction. | thedaviddias/Front-End-Checklist | 73.3k | 2026-05-29 |
| 3438 | peer-reviewUse before submission or when reviewing papers - provides evaluation checklists, bias detection, and self-review templates | Norman-bury/research-writing-skill | 2.9k | 2026-03-29 |
| 3439 | social-media-analyzerSocial media campaign analysis and performance tracking. Calculates engagement rates, ROI, and benchmarks across platforms. Use when analyzing social media performance, calculating engagement rate, measuring campaign ROI, comparing platform metrics, or benchmarking against industry standards. Also use when the user mentions "social media audit," "engagement rate," or "which platform performs best." | alirezarezvani/claude-skills | 23.0k | 2026-06-11 |
| 3440 | dc-power-flowDC power flow analysis for power systems. Use when computing power flows using DC approximation, building susceptance matrices, calculating line flows and loading percentages, or performing sensitivity analysis on transmission networks. | benchflow-ai/skillsbench | 1.6k | 2026-01-19 |
| 3441 | hermes-ops运维 Hermes Agent 的实战 skill。适用于用户提到“运维 hermes”“排查 hermes 问题”“gateway 异常”“平台掉线”“cron 不执行”“profile 配置混乱”“skills 或 tools 不生效”“想让其他 agent 帮忙维护 hermes”时使用。基于 hermes-agent 源码和官方命令入口，优先做检查、定位、修复、验证四步，不凭感觉瞎改。 | chujianyun/skills | 692 | 2026-04-11 |
| 3442 | web-searchReal-time web search using Playwright-controlled browser. Use this skill when you need current information, latest documentation, recent news, or any data beyond your knowledge cutoff (January 2025). | netease-youdao/LobsterAI | 5.6k | 2026-07-13 |
| 3443 | amazon-product-researchComprehensive product research and opportunity analysis for Amazon sellers. Analyzes demand, competition, profit potential, market entry barriers, and validates product ideas. Covers product sourcing, pricing strategy, and go-to-market planning. Use when the user asks about researching a product to sell, validating product ideas, product opportunity analysis, market research for Amazon, competition analysis, profit potential, should I sell this product, product viability, or any general product research questions. | nexscope-ai/Amazon-Skills | 428 | 2026-06-10 |
| 3444 | wangwen-creative网文创作（Wangwen-Creative）——一体化网文创作能力框架，覆盖从小说搜索下载、拆文分析、素材积累、仿写创作到大纲构建、正文创作的完整链路。文本是工具不是目的，根据任务embody不同专家（拆文分析师/世界观架构师/大纲设计师/网文写手/素材管理员/仿写教练），避免套路化写作。触发词：写网文、创作小说、网文大纲、拆文、拆书、素材库、金手指设计、升级体系、爽点设计、伏笔埋设、节奏把控、人物弧光、世界观设定、类型小说、玄幻大纲、都市重生、系统流、无限流、修仙体系、网文创作、市场定位、读者心理、商业策略、仿写、拆文仿写、场景仿写、小说下载、搜索小说、番茄小说、规则怪谈、基建流、诸天流、直播流、御兽流、模拟器流、剧本杀。**主干能力**：Junior Writer工作流（先给假设+reasoning+骨架再迭代）、反AI写作slop清单、类型模板系统（15种主流网文类型×创作指南）、三幕/四幕/网文专用节奏模型、角色弧光设计器、伏笔追踪系统。**小说搜索下载能力**：番茄小说平台搜索（书名/作者/URL/关键词）、书籍信息获取、章节目录提取、批量章节下载、本地存档管理、下载与拆文的自动衔接。**拆文分析能力**：六维度拆文框架（结构/角色/设定/节奏/文笔/商业）、原理提取三层次（表层技巧→中层原理→深层哲学）、5-10-2-8质量门槛、精读标注系统（★◆▲●◎⚡?!）、拆文报告自动生成、拆文与抄袭边界守则。**场景全流程拆文仿写能力**：搜索下载→精读标注→六维度拆解→原理提取→仿写创作→对比验证→素材入库的一体化工作流、场景级仿写模板（开篇/爽点/伏笔/对话/反转）、仿写三步转化法（模式识别→参数调优→创意注入）、三换原则验证原创性。**素材库积累能力**：230+条原创素材覆盖15类（金手指/升级体系/世界观/人物/爽点/伏笔/节奏/冲突/对话/描写/转折/开头/结尾/名场面/语言风格），含最新流派素材（规则怪谈/基建流/诸天流/直播流/御兽流/模拟器流）；拆文素材独立存放（XX-DNNN格式ID），验证升级机制（待验证→单作品验证→跨作品验证→通用原理→升级到原创库）；按功能组织素材库（技法库/结构库/风格库/商业库/拆文记录）。**需求模糊时的Fallback**：创作方向顾问模式——从5大流派×15种网文类型推荐3个差异化方向，展示类型模板和经典案例，并行生成3个创作Demo让用户选。**交付后可 | dav-niu474/novelhermes-ai | 0 | 2026-04-25 |
| 3445 | esp32-log-triageParse and classify ESP32 serial log output to identify FastLED-related errors, RMT/I2S/SPI driver faults, timing violations, RTOS issues, and crash signatures. Use when debugging unexpected device behavior, boot failures, or LED output problems on ESP32. | FastLED/FastLED | 7.5k | 2026-03-27 |
| 3446 | reverse-engineering-ransomware-encryption-routineReverse engineer ransomware encryption routines to identify cryptographic algorithms, key generation flaws, and potential decryption opportunities using static and dynamic analysis. | mukul975/Anthropic-Cybersecurity-Skills | 26.3k | 2026-06-20 |
| 3447 | planned-task-runtimeHandles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks. | n8n-io/n8n | 197.4k | 2026-07-10 |
| 3448 | latex-outputUse when user requests LaTeX format output or has provided school/journal LaTeX templates | Norman-bury/research-writing-skill | 2.9k | 2026-03-29 |
| 3449 | web-asset-generatorGenerate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Use when users need icons, favicons, social sharing images, or Open Graph images from logos or text slogans. Handles image resizing, text-to-image generation, and provides proper HTML meta tags. | alonw0/web-asset-generator | 464 | 2025-10-21 |
| 3450 | nlm-skillExpert guide for the NotebookLM CLI (`nlm`) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating NotebookLM workflows. Triggers on mentions of "nlm", "notebooklm", "notebook lm", "podcast generation", "audio overview", "refactor document", "critique draft", or any NotebookLM-related automation task. | jacob-bd/notebooklm-mcp-cli | 5.6k | 2026-07-21 |
| 3451 | seedance-real-estate为 Seedance 2.0（Higgsfield）生成房地产、建筑和室内设计展示视频提示。在用户想要财产巡览、房地产清单、建筑展示、室内设计视频、家居登台内容、财产营销、虚拟巡览、施工揭示或任何房地产/建筑视频时使用。在以下情况下触发：房地产、财产、房屋、公寓、建筑、室内设计、房屋巡览、清单视频、财产营销、虚拟巡览、建筑、施工、翻新、家居登台或任何房地产/建筑视频请求。即使是"为我的清单制作视频"或"展示这一财产"也适用。 | beshuaxian/higgsfield-seedance2-jineng | 701 | 2026-04-09 |
| 3452 | thesis-optimizer学术论文智能优化系统，专为计算机深度学习方向硕士学位论文设计。
提供三维协同优化：降低 AI 写作风险特征、降查重率、学术润色提升。
采用两层文档架构（总揽+章节）与显式状态追踪，实现模块化闭环优化。
内置中文学术写作风险模式、词汇风险和句式节奏参考。严格遵循“最小干预与句内微调”原则，避免大段AI式重写，保留作者原有科研逻辑。
Intelligent thesis optimization system for computer science deep learning master's theses.
Provides three-dimensional optimization: AI-writing-risk reduction, plagiarism reduction,
academic polishing. Uses two-tier document architecture (master + chapter) with explicit
state tracking for modular closed-loop optimization. Uses writing-risk references and
minimal intra-sentence restructuring to preserve the author's logic.
关键词: thesis-optimization, ai-detection, plagiarism, polishing, academic-writing, perplexity, burstiness | Haimbeau1o/thesis-optimizer | 238 | 2026-04-27 |
| 3453 | google-ads-copyGenerate and A/B test Google Ads copy. Use when asked to write ad copy, headlines, descriptions, create ad variants, test ad messaging, improve CTR, or generate RSA (Responsive Search Ad) components. Trigger on "ad copy", "write ads", "headlines", "descriptions", "RSA", "responsive search ad", "ad text", "ad creative", "improve CTR", "ad A/B test", "ad variants", "write me an ad", "ad variation experiment", or when the user wants to improve click-through rate on existing ads. | nowork-studio/NotFair | 3.2k | 2026-05-29 |
| 3454 | test-tuiGuide for testing Codex TUI interactively | openai/codex | 100.6k | 2026-02-12 |
| 3455 | video-to-websiteTurn a video into a premium scroll-driven animated website with GSAP, canvas frame rendering, and layered animation choreography. | ownerng/AGENTS-SKILLS | 0 | 2026-03-07 |
| 3456 | de-ai-writing文本去AI味技能。用 "检测→删除→声纹校准→改写→反查" 五步法去除文字中的AI痕迹，保留真实人味。触发场景：用户说"去AI味""太像AI写的""帮我润色得更像人写的""有机器味""不够自然"；用户给了一段文字让你改写得更口语化、更有个性、更有"活人感"；用户抱怨内容有宣传腔、公文腔、爆款腔、PPT腔、假人味；任何需要让文字听起来不像AI生成的场景。 | renky1025/agent-skills | 4 | 2026-06-18 |
| 3457 | frontend-design创建具有高设计品质、可交付生产的前端界面。当用户要求构建 Web 组件、页面、海报或应用（如官网、落地页、仪表盘、React/Vue 组件、HTML/CSS 布局，或对任意 Web UI 进行样式/美化）时使用本技能。产出有创意、打磨到位且避免「AI 通用审美」的代码与界面设计。 | xstongxue/best-skills | 2.4k | 2026-05-06 |
| 3458 | image-to-codeElite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop. | Leonxlnx/taste-skill | 66.3k | 2026-04-24 |
| 3459 | social-media-managerA full production pipeline where an agent team collaborates to generate SNS content strategy, post copy, visual plans, and hashtag strategies all at once. Use this skill for 'create SNS content,' 'write Instagram posts,' 'social media strategy,' 'SNS content calendar,' 'hashtag strategy,' 'Instagram copy,' 'TikTok content,' 'LinkedIn posts,' 'SNS marketing,' and all other aspects of social media content management. Also supports post writing or hashtag analysis when existing brand guides are provided. Note: actual SNS account operations (posting, replies, DMs), ad execution, analytics API integration, and influencer outreach are outside the scope of this skill. | revfactory/harness-100 | 1.2k | 2026-03-22 |
| 3460 | codex-windows-fast-patch-skillGuide agents to restore Codex Desktop local patches and feature toggles (Computer Use, plugins, Fast Mode) after upgrades on Windows | Aradotso/codex-skills | 0 | 2026-06-05 |
| 3461 | sonarqube-tacticsSonarQube 代码审计平台攻击。当发现目标运行 SonarQube 实例（默认 9000 端口）、默认凭据 admin/admin 未修改、或需要从 SonarQube 窃取项目源代码和漏洞信息时使用。覆盖默认凭据攻击、项目源代码窃取、漏洞/Issue 枚举（CRITICAL 优先）、用户凭据与 Token 窃取、Quality Gate 绕过、配置文件提取（数据库/SCM 凭据）、Webhook 滥用、插件分析、热点与度量数据导出 | wgpsec/AboutSecurity | 1.6k | 2026-04-24 |
| 3462 | recruiting-pipelineTrack and manage recruiting pipeline stages. Trigger with "recruiting update", "candidate pipeline", "how many candidates", "hiring status", or when the user discusses sourcing, screening, interviewing, or extending offers. | anthropics/knowledge-work-plugins | 22.9k | 2026-02-24 |
| 3463 | browseFast headless browser for QA testing and site dogfooding. (gstack) | garrytan/gstack | 123.6k | 2026-07-14 |
| 3464 | plan-eng-reviewEng manager-mode plan review. (gstack) | garrytan/gstack | 123.6k | 2026-06-25 |
| 3465 | mvvm-toolkit-messengerCommunityToolkit.Mvvm Messenger pub/sub for decoupled communication between ViewModels (or any objects). Covers WeakReferenceMessenger vs StrongReferenceMessenger, IRecipient<TMessage>, RequestMessage<T> / AsyncRequestMessage<T> / CollectionRequestMessage<T>, ValueChangedMessage<T>, channels (tokens), and the ObservableRecipient activation lifecycle. Use across WPF, WinUI 3, .NET MAUI, Uno, and Avalonia. | github/awesome-copilot | 36.9k | 2026-05-11 |
| 3466 | adversarial-polish多轮对抗式稿件打磨技能。通过"批评→改写→综合→盲评"循环，像学术同行评审一样反复打磨稿件直到收敛。所有中间产物（批评、改写、综合、评分）保存为独立文件，完整记录进化过程。当用户说"对抗打磨""反复打磨""深度打磨""多轮润色""盲评打磨""打磨到收敛""帮我把这篇稿子磨一磨""pressure polish""adversarial polish"时触发。也适用于用户说"这篇稿子很重要，帮我好好打磨"或"我需要更高质量的润色"等暗示需要超越单轮润色的场景。注意：如果用户只是要求普通润色，优先使用已有 polish 技能。本技能适合对质量要求极高、愿意花更多时间打磨的稿件。 | JimLiu/Illustrated-Agent-Skills | 595 | 2026-06-02 |
| 3467 | file-manager文件管理技能。用于创建、移动、复制、删除文件和文件夹，整理目录结构。当用户需要管理文件、整理文件夹或批量处理文件时使用。 | RTGS2017/NagaAgent | 1.5k | 2026-02-09 |
| 3468 | repo2patent面向中国发明专利：从 GitHub 项目/技术方案生成可交付的专利技术交底书（Word .docx），并【必须】完成专利检索 + 权利要求抽取（claims）+ 特征对比矩阵 + 候选新颖点（差异特征组合）提炼。 | bb-boy/repo2patent | 62 | 2026-02-22 |
| 3469 | specialized-civil-engineer精通全球标准的土木与结构工程专家——覆盖 Eurocode、DIN、ACI、AISC、ASCE、AS/NZS、CSA、GB、IS、AIJ 等。专长领域包括结构分析、岩土设计、施工文件编制、建筑规范合规以及多标准国际项目协调。 | itgoyo/hermes-skills | 30 | 2026-04-22 |
| 3470 | real-estateReal estate agent daily workflow automation | ChenKuanSun/MobileClaw | 36 | 2026-04-09 |
| 3471 | xhs-publisher小红书发布 skill - 通过 agent-browser (CDP) 自动发布小红书图文笔记，支持多图上传、标题正文填写、一键发布。使用场景：自动化发布图文笔记到小红书创作中心。 | inclusionAI/AWorld | 1.2k | 2026-02-26 |
| 3472 | tencent-pentesting腾讯云渗透测试方法论。当目标使用腾讯云服务、发现 cos.*.myqcloud.com 资产、获取腾讯云 SecretId/SecretKey、在 CVM 实例内可访问 metadata.tencentyun.com 元数据、或需要对腾讯云 CAM/CVM/COS/TencentDB/TKE/SCF 等服务进行安全评估时使用。覆盖 CAM 提权、CVM 接管、COS 对象存储利用、TencentDB 数据库攻击、TKE 容器集群、SCF 云函数、CLB 负载均衡、CLS 日志服务、KMS 密钥管理 | wgpsec/AboutSecurity | 1.6k | 2026-05-21 |
| 3473 | ida-skillIDA Pro 逆向分析。通过 IDAPython 脚本获取反汇编、反编译、字符串、导入表、交叉引用等信息。 | miunasu/IDA-Skill | 204 | 2026-07-09 |
| 3474 | graphics-and-shapesUse this skill when drawing shapes and graphics in Phaser 4. Covers the Graphics game object, lines, rectangles, circles, arcs, polygons, gradients, fill, stroke, and generated textures. Triggers on: Graphics, draw shape, fillRect, lineStyle, polygon, arc. | phaserjs/phaser | 40.0k | 2026-04-10 |
| 3475 | adr-skillCreate and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses Socratic questioning to capture intent before drafting, and validates output against an agent-readiness checklist. | vercel/ai | 25.7k | 2026-05-08 |
| 3476 | springboot-tddDesarrollo guiado por pruebas para Spring Boot usando JUnit 5, Mockito, MockMvc, Testcontainers y JaCoCo. Usar al agregar funcionalidades, corregir bugs o refactorizar. | affaan-m/ECC | 232.1k | 2026-06-07 |
| 3477 | writing-humanitiesUse when writing humanities or social science papers - provides discipline-specific writing guidance | Norman-bury/research-writing-skill | 2.9k | 2026-03-29 |
| 3478 | taobao-search淘宝商品搜索。当用户想要搜索商品、找某品牌产品、比价、查看新款等电商购物场景时激活。 | OPPO-Mente-Lab/X-OmniClaw | 245 | 2026-05-18 |
| 3479 | hipaa-complianceHIPAA-specific entrypoint for healthcare privacy and security work. Use when a task is explicitly framed around HIPAA, PHI handling, covered entities, BAAs, breach posture, or US healthcare compliance requirements. | affaan-m/ECC | 232.1k | 2026-06-11 |
| 3480 | web-access所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。触发场景：用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容（小红书、微博、推特等）、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。 | brycewang-stanford/Auto-Empirical-Research-Skills | 3.0k | 2026-06-18 |
| 3481 | loop-engineeringShared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate). | huytieu/COG-second-brain | 703 | 2026-06-22 |
| 3482 | light-review-rebuttalBuild auditable peer-review revision and author-response packages for Light stage 13. Use after receiving reviewer comments, a decision or meta-review; when drafting a rebuttal or response letter; when triaging major/minor revisions; when simulating a pre-submission review; or when a rejection may require a user-chosen 13→3 novelty, 13→5 experiment, or 13→8 writing back-edge. Consumes the selected venue/context and real PDF facts, preserves reviewer wording, atomizes issues, binds claims/evidence/actions/provenance, separates PLANNED from DONE, checks current venue limits without borrowing another venue's rules, and emits the stage-13 gate without changing venue, manuscript, evidence, citations, figures, PDF, or passport automatically. | Light0305/Light-skills | 453 | 2026-07-05 |
| 3483 | code-standards代码规范与完整开发工作流，涵盖 Python、PyTorch/深度学习、Shell 脚本、配置文件。贯穿始终的四条设计原则：易读直观、拒绝过度抽象、单一职责、命名自解释。强制三段式流程：（1）写代码前——在已有项目上开发时必须先了解项目全貌避免重复实现，然后先出 plan（思路+实现步骤）并获得用户批准才能开工；（2）写代码中——遵循命名/类型/docstring/张量操作/异常处理等规范，同时时刻守住四条设计原则；（3）写代码后——必须先补齐对应单元测试并本地跑通，再主动调用 simplify 简化新代码，最后调用 review 做审查。触发条件：用户要求写/生成/重构 Python 或 PyTorch 代码；用户要求在已有项目/代码库上开发；用户创建新模块、脚本或训练循环；用户说"按代码规范来"或引用 /code-standards。 | Tencent-Hunyuan/UniRL | 840 | 2026-06-09 |
| 3484 | latex-thesis-zhChinese LaTeX thesis assistant for existing .tex degree thesis projects (XeLaTeX/LuaLaTeX/latexmk). Use this skill whenever a user works on a Chinese master's or doctoral thesis needing compilation, GB/T 7714 bibliography checks, chapter structure mapping, template detection (thuthesis, pkuthss), terminology consistency, logic coherence review, heading lead-in checks, title optimization, de-AI editing, experiment chapter review, three-line table validation, or abstract structure diagnosis. Trigger even for single issues like "帮我编译论文", "检查国标格式", "看看绪论逻辑", "毕业论文", "学位论文", "硕士/博士论文", "三线表", "检查摘要", or "摘要结构". | brycewang-stanford/Auto-Empirical-Research-Skills | 3.0k | 2026-04-03 |
| 3485 | modular-design-principlesModular Design Principles workflow skill. Use this skill when the user needs > and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off. | diegosouzapw/awesome-omni-skills | 88 | 2026-06-02 |
| 3486 | game-hacking-techniquesGuide for game-hacking technique taxonomy and threat modeling relevant to game security. Use this skill when researching memory access, code injection, overlays, input simulation, engine-specific attack surfaces, or how modern anti-cheat systems constrain user-mode, kernel-mode, hypervisor, and DMA-based cheat implementations. | gmh5225/awesome-game-security | 3.2k | 2026-07-16 |
| 3487 | auto-stock龙虾全自动炒股技能 v1.0 - 激进短线交易系统。选股+持仓监控+盘前盘后报告+风控提醒。资金基准80万，单票上限30%，止损4%，止盈8-12-15%。 | huzengyun3268/openclaw-workspace | 0 | 2026-04-02 |
| 3488 | ppt-agent专业 PPT 演示文稿全流程 AI 生成助手。模拟顶级 PPT 设计公司的完整工作流（需求调研到资料搜集到大纲策划到策划稿到设计稿），输出高质量 HTML 格式演示文稿。当用户提到制作 PPT、做演示文稿、做 slides、做幻灯片、做汇报材料、做培训课件、做路演 deck、做产品介绍页面时触发此技能。即使用户只说"帮我做个关于 X 的介绍"或"我要给老板汇报 Y"，只要暗示需要结构化的多页演示内容，都应该触发。也适用于用户说"帮我把这篇文档做成 PPT"、"把这个主题做成演示"等需要将内容转化为演示格式的场景。英文场景同样适用："make a presentation about..."、"create slides for..."、"build a pitch deck"、"I need a keynote for..."。隐式意图也应触发："帮我把这个数据可视化一下给老板看"、"我需要一份能拿去路演的东西"、"把这个报告做得好看点能展示"、"beautify my existing PPT"、"redesign these slides"。改善或美化现有 PPT 也属于此技能范畴。 | Hafiz3369/ppt-agent-skills | 0 | 2026-06-16 |
| 3489 | english-docs-translation-styleTranslate and polish English documentation with consistent, natural, developer-friendly style for nex-ui. Use when translating docs. | rxy001/nex-ui | 30 | 2026-04-07 |
| 3490 | db-migrationsUse for Drizzle migrations: schema/table/column changes, migration generation or regeneration, sequence conflicts after rebase, idempotent SQL review, or migration renames. | lobehub/lobehub | 80.7k | 2026-06-09 |
| 3491 | salt-story知乎盐选故事写作。生成有反转、有吸引力、无 AI 味的短篇付费故事。适用于用户提到盐选、知乎故事、付费故事、写故事、编故事等场景。 | yfge/salt-story | 65 | 2026-03-13 |
| 3492 | research-paper-downloaderDownload academic papers from open-access sources when the user provides a DOI/arXiv ID or requests a keyword-based paper search, and return the saved PDF path. | aipoch/medical-research-skills | 1.5k | 2026-05-11 |
| 3493 | digital-eguideA two-spread digital e-guide preview — page 1 is a cover (display title,
author, "What's inside" stats, table of contents teaser); page 2 is a
spread (lesson body with pull-quote and a step list). Lifestyle / creator
brand tone. Use when the brief asks for an "e-guide", "digital guide",
"lookbook", "lead magnet", "creator guide", "playbook", "PDF guide",
or "电子指南". | nexu-io/open-design | 80.6k | 2026-07-14 |
| 3494 | ai-manga-dramaAI漫剧导演——根据背景剧情或主题，完成镜头规划→分镜图生成→视频生成（wan2.6音画同步）→视频合并的完整漫剧制作流水线。全程调用 neta 的 make-image、make-video(model_w)、merge-video 接口。当用户想制作漫剧、竖屏动态漫画、AI短剧、或将剧情/主题转化为视频内容时触发。 | Yvelinmoon/ai-manga-drama | 29 | 2026-03-08 |
| 3495 | competitive-briefCreate a competitive analysis brief for one or more competitors or a feature area. Use when informing product strategy or feature prioritization, building sales battle cards, prepping board or investor materials, or deciding where to differentiate vs. achieve parity. | anthropics/knowledge-work-plugins | 22.9k | 2026-03-13 |
| 3496 | wechat-article-search-api-skillThis skill helps users extract full article contents from WeChat using the BrowserAct API. The Agent should proactively apply this skill when users express needs like finding full WeChat articles for specific keywords, tracking WeChat public accounts for industry trends, extracting WeChat article contents for media research, monitoring public relations on WeChat platforms, collecting competitor updates from WeChat, getting full article body from WeChat links, monitoring brand exposure on WeChat articles, retrieving structured WeChat data for sentiment analysis, summarizing daily news from WeChat, getting author and publication date for WeChat articles, or automating WeChat content extraction without scraping. | browser-act/skills | 4.6k | 2026-04-21 |
| 3497 | owasp-asiOWASP Top 10 for Agentic Applications 2026 (ASI) classification framework. Use for mapping security findings to standardized risk categories. | Tencent/AI-Infra-Guard | 4.2k | 2026-02-04 |
| 3498 | rebuttalWorkflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely. | wanshuiyin/Auto-claude-code-research-in-sleep | 13.7k | 2026-07-13 |
| 3499 | excalidraw-diagramsCreates Excalidraw diagrams programmatically. Use when the user wants flowcharts, architecture diagrams, system designs, or any visual diagram instead of ASCII art. Outputs .excalidraw files that can be opened directly in Excalidraw or VS Code with the Excalidraw extension. | robtaylor/excalidraw-diagrams | 28 | 2026-07-19 |
| 3500 | file-reader仅用于读取和总结文本类文件。文本格式优先使用 read_file；需要做类型探测时使用 execute_shell_command。PDF、Office、图片和压缩包由其他技能处理。 | agentscope-ai/QwenPaw | 23.9k | 2026-04-20 |