| 9601 | user-manual生成用户操作手册、用户指南、使用说明。当用户需要编写操作手册、用户手册、使用指南、培训文档、FAQ时使用此skill。 | hnscdg/Chinese-Specification-Documents-for-Software | 0 | 2026-06-17 |
| 9602 | yt-outlineBuild detailed step-by-step YouTube video outlines with demo prep, screen-share sequences, and visual
planning. Use this skill whenever the user says "create an outline", "outline this video", "video outline",
"build the outline", "production outline", or has an approved brief and packaging and needs the final
pre-production document before demo prep and filming. Use when working with yt outline. Trigger with 'yt', 'outline'. | jeremylongshore/claude-code-plugins-plus-skills | 2.5k | 2026-07-17 |
| 9603 | scene-design场景设计技能。接收四维度编码，输出场景提示词。驱动场景配图迭代工作流。使用即梦生成图片，中文提示词，自然语言描述。 | khanhhuyenngo985-sys/character-scene-design-skills | 4 | 2026-04-24 |
| 9604 | agent-reachGive your AI Agent eyes to see the entire internet. Search + read 10+ platforms with one install. | Kxiandaoyan/Memoh-v2 | 340 | 2026-02-24 |
| 9605 | cloudq用户咨询腾讯云产品资源、AWS、阿里云等多云资源时，查看智能顾问架构图、架构目录、架构详情、架构评估结果、绘制架构图、开通智能顾问时、AI智能巡检、AI容量监测、AI混沌演练、AI云诊断、主动预警、架构健康度、云运维问答、云资源查询、云成本优化、安全合规、云资源盘点、闲置资源检查、云产品最佳实践等AIOps、ChatOps、CloudOps操作时使用。 | LeoYeAI/openclaw-master-skills | 2.1k | 2026-05-05 |
| 9606 | amazon-advertising-strategy构建综合亚马逊广告策略，涵盖 Sponsored Products、Sponsored Brands 和 Sponsored Display。预算分配、活动结构、关键词策略和 ACoS 优化。 | liangdabiao/Amazon-Skills-Liang | 34 | 2026-04-19 |
| 9607 | n8n-create-instance-ai-evalAuthors a new Instance AI workflow eval case — written locally as JSON, calibrated against a real build, then pushed to the LangTracer suite CI runs — build cases, behaviour/process cases, credential cases, and seeded (mid-conversation) cases — with intent-driven expectations. Use when adding or changing an Instance AI workflow eval, or debugging why one is flaky. | n8n-io/n8n | 197.4k | 2026-07-15 |
| 9608 | kanban-boardKanban / task board with columns (To do / In progress / In review / Done),
draggable-looking cards, assignee avatars, swimlanes, and a top filter
bar. Use when the brief mentions "kanban", "task board", "sprint board",
"trello", "看板". | nexu-io/open-design | 80.6k | 2026-05-11 |
| 9609 | plannerRead-only planning and architecture analysis for Penpot — produce a structured implementation plan (Context, Affected modules, Approach, Risks, Testing). Always output to the user; additionally save to .opencode/plans/YYYY-MM-DD-<title>.md. | penpot/penpot | 57.2k | 2026-07-13 |
| 9610 | r2-sharedR2-CLI 共享基础规则。任何涉及 r2-cli 命令的操作（商品、认证、上架、下架、改价、挂售、查询、批量、审核）都必须先读取此 skill。包含：执行规则、版本检查与更新通知、统一错误格式、网络重试策略、Token 过期恢复、友好输出原则、分页建议。即使你只是帮用户执行一条 r2-cli 命令，也应该先读这个 skill。 | Round2AI/r2-cli | 4 | 2026-06-17 |
| 9611 | seedance-2-guideSeedance 2.0 AI 视频生成模型的参考手册与能力地图。用于在 LibTV / 漫剧 / 视频创作场景下，快速判断 Seedance 2.0 是否适合当前任务、理解其两种工作模式（首尾帧模式 / 全能参考模式）、@符号用法、提示词黄金公式、与 Sora / Veo 的对比、以及 80+ 专业提示词模板。当用户提到「Seedance」「seedance 2.0」「视频模型选什么」「参考视频怎么传」「角色一致性」「九宫格分镜」「首尾帧」「运镜控制」「@character」「@product」等关键词，或在创作视频 / 漫剧 / 短剧 / MV / TVC 过程中需要判断模型能力边界、选择合适的生成模式时，应触发此技能。本技能是纯知识参考，不调用任何接口；生图生视频请配合 libtv-skill 使用。 | ShuaiMXu/mv-skills-bundle | 3 | 2026-05-14 |
| 9612 | antigravity-design-expertCore UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS. | bouclem/skills | 7 | 2026-05-24 |
| 9613 | full-stack-orchestration-full-stack-featureUse when working with full stack orchestration full stack feature | bouclem/skills | 7 | 2026-05-24 |
| 9614 | notion-template-businessExpert in building and selling Notion templates as a business - not just making templates, but building a sustainable digital product business. Covers template design, pricing, marketplaces, marketing, and scaling to real revenue. | muhammedadnank/Antigravity-Skills | 3 | 2026-06-06 |
| 9615 | prompt-libraryA comprehensive collection of battle-tested prompts inspired by [awesome-chatgpt-prompts](https://github.com/f/awesome-chatgpt-prompts) and community best practices. | muhammedadnank/Antigravity-Skills | 3 | 2026-06-06 |
| 9616 | shopify-appsExpert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions. | muhammedadnank/Antigravity-Skills | 3 | 2026-06-06 |
| 9617 | supabaseUse when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout,... | ChonSong/skill-retriever | 6 | 2026-07-10 |
| 9618 | travel-health-analyzer分析旅行健康数据、评估目的地健康风险、提供疫苗接种建议、生成多语言紧急医疗信息卡片。支持WHO/CDC数据集成的专业级旅行健康风险评估。 | muhammedadnank/Antigravity-Skills | 3 | 2026-06-06 |
| 9619 | office-hoursMANUAL TRIGGER ONLY: invoke only when user types /office-hours. YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building". Proactively suggest when the user describes a new product idea or is exploring whether something is worth building — before any code is written. | slopus/happy | 22.8k | 2026-04-07 |
| 9620 | paper-write"Draft LaTeX paper section by section from an outline. Use when user says \\"写论文\\", \\"write paper\\", \\"draft LaTeX\\", \\"开始写\\", or wants to generate LaTeX content from a paper plan." | wanshuiyin/Auto-claude-code-research-in-sleep | 13.7k | 2026-07-10 |
| 9621 | douyin-creator抖音（Douyin）创作者中心作品与评论自动化：获取已发布作品列表、导出指定作品的未回复评论、让模型逐条决策回复或按 JSON 批量回复。当用户提到抖音、创作者中心、作品列表、导出评论、回复评论、逐条回复、未回复评论或批量回复时触发。 | wenyg/douyin-creator-tools | 162 | 2026-07-15 |
| 9622 | cangjie仓颉 · 认知植入术：丢进素材（书/访谈/文章/PDF），自动蒸馏出一个人的思维Skill。
提取的不是"他说了什么"，而是"他为什么这样想"——信念形成故事、真实决策、失败教训、内在矛盾。
触发词：「仓颉」「蒸馏XX」「做个XX的思维Skill」「用仓颉提取」「帮我蒸馏」。
只要用户上传了某人的素材（书/演讲/访谈）并希望提取思维方式，就应该触发。 | Yeadon8888/cangjie-skill | 118 | 2026-04-12 |
| 9623 | cut控制 剪映 (JianYing/CapCut) 与 Adobe Premiere Pro 两款视频剪辑软件的统一 skill。 让 AI 编程 agent（Codex CLI / Claude Code / OpenCode / Kimi Code / Qwen Code 等任意支持 skill 或 MCP 的工具） 能够读取当前时间轴状态、批量导入素材、裁切片段、添加字幕与转场、混音、并触发导出渲染。 使用本 skill 的场景包括但不限于：用户说"帮我把这些视频剪一下"、"自动给视频加字幕"、 "在剪映里把这段切两半"、"让 Premiere 把这几个素材按顺序排到时间轴上"、"批量加水印"、 "导出 1080p"、"读取一下我剪映里现在有什么素材"、"自动做个 vlog 混剪"。 涵盖视频剪辑、字幕生成、特效转场、音频处理、批量渲染、跨平台（Windows + macOS）。 只要用户提到 剪映、CapCut、JianYing、Premiere、Pr、视频剪辑、时间轴、轨道、片段、字幕、转场、 调色、混音、渲染导出 等任何视频后期相关词，都应优先使用本 skill。 | ygtec/cut.skill | 6 | 2026-07-09 |
| 9624 | design-dnaExtract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides images, screenshots, or URLs of reference designs and wants them analyzed into a structured JSON profile covering all three dimensions, (3) a user has a Design DNA JSON and content and wants a design generated from it, or (4) any combination of these phases. Triggers on "design DNA", "extract design style", "analyze design", "design tokens from reference", "generate design from JSON", "design system from screenshot", "design profile", "style guide JSON", "visual effects analysis", "design with effects", "3d design analysis". | zanwei/design-dna | 1.1k | 2026-04-13 |
| 9625 | prompt-compressionWhen you MUST feed a large blob into context (a long log, transcript, doc, or dataset dump), compress it to the salient parts first instead of pasting it whole. Use before including big inputs you cannot avoid. Distinct from context-warden (session discipline); this compresses one specific oversized input. Trigger with /prompt-compression or "compress this before adding", "summarize this blob for context", "this log is huge". | Zavelinski/prompt-compression | 0 | 2026-06-30 |
| 9626 | agnes-videogenGenerate videos using the Agnes Video V2.0 model API. Use when the user asks to generate videos via Agnes AI platform (apihub.agnes-ai.com). Triggers on: agnes video, agnes 视频, video gen, generate video, text to video, image to video, keyframe interpolation, 生视频, 文生视频, 图生视频. | ziho7/agnes-skills | 51 | 2026-06-12 |
| 9627 | research-gapUse when the user wants to identify research gaps, open questions, unexplored areas, cross-paper limitations, or future directions from workspace literature. | ZimoLiao/scholaraio | 553 | 2026-04-26 |
| 9628 | reverse-engineering逆向工程技能 - 二进制分析、协议逆向、Hook/注入、脱壳、防护对抗、漏洞挖掘。当你涉及逆向分析、反编译、二进制分析、Hook、Frida、LLDB调试、协议分析、加密算法还原、防护绕过、脱壳、签名伪造时必须使用此技能。即使用户只是说"看看这个app"或"分析一下这个二进制"，也应触发。 | 0X6C7879/aegissec | 4 | 2026-04-04 |
| 9629 | telegram-devTelegram 生态开发全栈指南 - 涵盖 Bot API、Mini Apps (Web Apps)、MTProto 客户端开发。包括消息处理、支付、内联模式、Webhook、认证、存储、传感器 API 等完整开发资源。 | 2025Emma/vibe-coding-cn | 22.5k | 2025-12-16 |
| 9630 | godot-developmentGodot Engine integration skill for GDScript/C# development, scene composition, node management, and editor automation. Enables LLMs to interact with Godot Editor through MCP servers for asset manipulation, script generation, and automated workflows. | a5c-ai/babysitter | 1.6k | 2026-06-01 |
| 9631 | codebase-onboarding不慣れなコードベースを分析し、アーキテクチャマップ、主要なエントリポイント、規約、スターターCLAUDE.mdを含む構造化オンボーディングガイドを生成します。新しいプロジェクトに参加するか、リポでClaude Codeを初めてセットアップする場合に使用します。 | affaan-m/ECC | 232.1k | 2026-05-17 |
| 9632 | dart-flutter-patternsProduction-ready Dart and Flutter patterns covering null safety, immutable state, async composition, widget architecture, popular state management frameworks (BLoC, Riverpod, Provider), GoRouter navigation, Dio networking, Freezed code generation, and clean architecture. | affaan-m/ECC | 232.1k | 2026-06-11 |
| 9633 | content-creatorDeprecated redirect skill that routes legacy 'content creator' requests to the correct specialist. Use when a user invokes 'content creator', asks to write a blog post, article, guide, or brand voice analysis (routes to content-production), or asks to plan content, build a topic cluster, or create a content calendar (routes to content-strategy). Does not handle requests directly — identifies user intent and redirects to content-production for writing/SEO/brand-voice tasks or content-strategy for planning tasks. | alirezarezvani/claude-skills | 23.0k | 2026-05-02 |
| 9634 | cold-call-prepPrep for a cold-call — predict the professor's likely questions and drill them Socratically, flagging where you're shaky so you know what to re-read before class. Use when the user says "prep for class tomorrow", "cold call [case]", "what might [professor] ask on", or points at assigned reading. | anthropics/claude-for-legal | 8.8k | 2026-05-11 |
| 9635 | cc-connectThis skill should be used when sending images, files, or notifications back to the user via messaging platforms (Discord, Feishu, Telegram, etc.) through cc-connect. TRIGGER when agent generates a plot/chart/screenshot and wants to show the user; agent creates a report/PDF/file the user should receive; agent needs to proactively notify the user (e.g. task completed, alert, reminder); user asks to "send image", "show me the chart", "notify me", "send the file", "send to Telegram", "show plot in Discord". | archibate/dotfiles-opencode | 103 | 2026-04-05 |
| 9636 | business-skills5 business research skills. Trigger: business strategy, market analysis, competitive intelligence. Design: analytical frameworks and methods for management and innovation research. | brycewang-stanford/Auto-Empirical-Research-Skills | 3.0k | 2026-04-03 |
| 9637 | vedic-calculator吠陀占星排盘计算引擎。当用户提供出生时间和地点，需要从零计算星盘数据时触发。输入出生日期、时间、地点，直接输出structured_data.md，跳过JHora排盘和PDF读取流程。当用户提到'直接排盘''计算星盘''不用jhora''快速排盘''算一下'等关键词时触发。也在vedic-reader判断无PDF输入时建议使用。 | CNWU16/vedic-astro-skills | 554 | 2026-07-16 |
| 9638 | domain-driven-designPlan and route Domain-Driven Design work from strategic modeling to tactical implementation and evented architecture patterns. | davila7/claude-code-templates | 29.8k | 2026-04-04 |
| 9639 | catia-caa-pluginCreate, compile, install, run, and debug CATIA V5 CAA RADE plugins on this Windows CATIA V5R21 setup. Use when Codex is asked to write a CAA add-in, command, toolbar button, Part workbench add-in, Product Structure or Assembly add-in, CATPart instance insertion, positioning or assembly constraints, CATIA plugin, CNext/CNEXT extension, dico registration, mkmk build, CATSTART launch script, temporary install, locate official same-version CAA docs/examples, handle CATIA NLS encoding, create geometry or pad-to-surface features, or diagnose CATIA blank gray startup, missing toolbar, frozen UI, build artifact, license, dictionary, or NLS failures. | Draugmista/catia-caa-plugin-v5r21-skill | 0 | 2026-06-02 |
| 9640 | photo-cull-retouchSelect the best photos from an input folder, prepare Codex imagegen portrait-retouch tasks, and finalize edited outputs. | dudachun/photo-cull-retouch | 3 | 2026-06-28 |
| 9641 | devops-monitoring-alerting监控告警配置，确保系统稳定运行 | echoVic/boss-skill | 554 | 2026-05-15 |
| 9642 | echartsECharts 图表生成。用于需要可视化数据展示的场景，支持 20+ 图表类型（柱状图、折线图、饼图、雷达图等），输出 SVG/PNG/Base64/文件格式。当用户需要生成图表、数据可视化、统计图形时触发。 | ErixWong/touwaka-ai-mate | 17 | 2026-05-24 |
| 9643 | gemini-interactions-apiGuides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform. | google/skills | 15.0k | 2026-07-13 |
| 9644 | meta-ads-analyzerDiagnose Meta Ads campaign performance using Meta's actual system mechanics — Breakdown Effect, Learning Phase, Auction Overlap, Pacing, and Creative Fatigue — and produce structured, testable recommendations that avoid judging segments by average CPA instead of marginal efficiency. | gooseworks-ai/goose-skills | 1.0k | 2026-06-29 |
| 9645 | pdf-document-translationTranslate full PDF documents between English and Simplified Chinese while preserving the original layout, figures, and tables. Use whenever the user wants to translate a PDF, localize a report or paper, produce a bilingual document, or rebuild a translated PDF that looks like the source. Triggers on phrases like "translate this PDF", "把这份PDF翻译成英文", "localize this whitepaper", "produce a Chinese version of this document". | Jack5316/translation_codex_skill | 0 | 2026-05-09 |
| 9646 | clone-websiteReverse-engineer and clone one or more websites in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy any website. Also triggers on phrases like "make a copy of this site", "rebuild this page", "pixel-perfect clone". Provide one or more target URLs as arguments. | JCodesMore/ai-website-cloner-template | 29.6k | 2026-03-29 |
| 9647 | simulating-simulink-modelsRuns Simulink models programmatically for data exploration, parameter sweeps, and custom analysis using sim() with SimulationInput/SimulationOutput. Use when calling sim(), parsim, setExternalInput, setModelParameter, setVariable, or accessing logsout — any task producing simulation results for analysis (not pass/fail tests). | matlab/simulink-agentic-toolkit | 846 | 2026-05-06 |
| 9648 | record-sessionRecords completed work progress to .trellis/workspace/ journal files after human testing and commit. Captures session summaries, commit hashes, and updates developer index files for future session context. Use when a coding session is complete, after the human has committed code, or to persist session knowledge for future AI sessions. | mindfold-ai/Trellis | 13.0k | 2026-03-23 |
| 9649 | dcf-valuationDiscounted cash flow valuation and intrinsic value analysis for public
companies. Use when the brief asks for DCF, fair value, intrinsic value,
price target, undervalued or overvalued analysis, or "what is this company
worth?" | nexu-io/open-design | 80.6k | 2026-05-11 |
| 9650 | mt2zhPDF 翻译工具，基于 pdf2zh（v1.9.11，即原 pdf2zh-next）和 OpenAI 兼容 API（默认使用 qwen 模型）。 在用户需要以下操作时使用此技能： (1) 翻译单个 PDF 文件； (2) 批量翻译目录下所有 PDF； (3) 按扩展名筛选并翻译文件； (4) 指定源语言/目标语言（不指定时自动翻译成中文）； (5) 选择双语显示（原文+译文）或仅译文模式； (6) 控制翻译线程数（默认/自定义/自动匹配 CPU 核数）。 触发关键词：翻译 PDF、PDF 翻译、mt2zh、translate PDF、pdf2zh。 | puhuaqiang/my-skills | 0 | 2026-03-12 |
| 9651 | french-accountantExpert-comptable IA pour les entreprises françaises. Co-pilote comptable et fiscal compliance-first.
Utiliser ce skill pour:
- Comptabilité générale (écritures, journaux, balance, grand livre)
- Classification PCG (Plan Comptable Général)
- TVA (déclarations, régimes, intra-UE, autoliquidation)
- Impôts (IS, IR, CFE, CVAE, taxes diverses)
- Clôture annuelle (amortissements, provisions, cut-offs)
- Obligations légales et calendrier fiscal
- Analyse de risques et conformité
- Toute question comptable ou fiscale française
Triggers: comptabilité, TVA, impôts, bilan, compte de résultat, écriture comptable, PCG, clôture, liasse fiscale, expert-comptable, French accounting, French taxes | Raphael67/dotfiles | 1 | 2026-05-18 |
| 9652 | velvet-ascentUse this skill when the user wants a Chinese adult-oriented turn-based text GalGame GM with harem formation, freeform narrative roleplay, natural-escalation yellow-fiction text adventure, multi-character relationship drama, story memory, or novel export. Trigger on requests for 后宫养成, 后宫, 养成, 多女主, 多男后宫, 黄色爽文, 自然流YY文字游戏, 成人向文字冒险, 回合制文字冒险, GalGame, 后宫互动, 逐步升温剧情, 暧昧开局, 自定义身份卡, 文档记忆, 小说导出, 女性向剧情, or any Chinese freeform narrative game where the user wants adult consenting characters, gradual escalation, strong character routes, and long-running continuity. | ruijayfeng/velvet-ascent-skill | 11 | 2026-07-13 |
| 9653 | active-directory-attacksProvide comprehensive techniques for attacking Microsoft Active Directory environments. Covers reconnaissance, credential harvesting, Kerberos attacks, lateral movement, privilege escalation, and domain dominance for red team operations and penetration testing. | muhammedadnank/Antigravity-Skills | 3 | 2026-06-06 |
| 9654 | vexorVector-powered CLI for semantic file search with a Claude/Codex skill | muhammedadnank/Antigravity-Skills | 3 | 2026-06-06 |
| 9655 | vibe-code-auditorAudit rapidly generated or AI-produced code for structural flaws, fragility, and production risks. | gonzoblasco/antigravity-developer-stack | 5 | 2026-06-26 |
| 9656 | davinci-resolve-fusionScripting and automating DaVinci Resolve and building Fusion compositions, macros, and animations. Covers the Resolve scripting API (projects, timelines, media pool, rendering), the Fusion object model, building/editing .setting macros, exposing macro controls, and animating with BezierSpline keyframes, handles, easing, and StyledTextFollower. Use this skill for any DaVinci Resolve Lua/Python script, Fusion macro authoring, or Fusion keyframe/animation work. | tmoroney/auto-subs | 3.9k | 2026-07-11 |
| 9657 | wordpress-skillWordPress 站点管理 Skill — 通过 CLI 工具管理文章、页面、媒体、分类、标签和搜索 | uluckyXH/OpenMOSS | 1.3k | 2026-03-11 |
| 9658 | video-understanding把视频分析为结构化理解索引：场景检测、ASR 转写、逐场景 VLM 观察、静音窗口、融合时间线和写作 brief。 用于理解、索引或总结视频，也作为后续创作前的分析阶段。输入视频文件；输出 scenes.json、 asr_result.json、vlm_analysis.json、silence_periods.json、timeline_fusion.json、agent_narration_brief.md。 触发词：视频理解、视频分析、视频索引、video understanding、analyze video、看懂视频。 | worldwonderer/video-recap-skills | 401 | 2026-07-15 |
| 9659 | solidworks-parametricUse whenever the user mentions CAD, SolidWorks, SW, 3D建模, 零件, 螺栓, 鼠标, 参数化, or any mechanical part design — even in passing. Triggers on "CAD", "画个", "create a", "建模", "M6/M8/M10", "gaming mouse", "SolidWorks". Requires solidworks-automation skill. Use for any CAD part request — modify the SPEC dictionary at the top of the matching script and re-run. | 591522345/solidworks-parametric-skill | 0 | 2026-06-12 |
| 9660 | hydraulic-analysis-engineHydraulic analysis skill for open channel flow, culverts, and pipe networks | a5c-ai/babysitter | 1.6k | 2026-06-01 |
| 9661 | compliance-risk-alert合规风险提示助手，适用于券商合规管理、风险预警、内控建设、监管报送等场景。
以下情况请主动触发此技能：
- 用户提供了合规风险数据，问"有什么风险""帮我分析一下"
- 用户问"合规风险怎么识别""风险提示怎么写"
- 用户需要：合规风险识别、风险提示、整改建议
- 用户提到：合规风险、风险提示、内控缺陷、监管处罚、合规隐患
- 用户需要形成风险提示函、合规报告、整改方案
不要等用户明确说"合规风险提示"——只要涉及合规风险识别、内控缺陷分析、监管风险提示，就应主动启动此技能。 | aifinlab/FinClaw | 211 | 2026-03-18 |
| 9662 | cv-classificationBest practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks. | aiming-lab/AutoResearchClaw | 13.8k | 2026-03-23 |
| 9663 | deep-novel-system一个用于撰写高质量长篇小说的综合系统，擅长复杂叙事、感官描写、跨章节记忆管理与反馈循环。支持多种类型与成人主题（在用户授权范围内）。当用户想开始新小说、继续现有小说或需要长篇结构化叙事指导时使用此技能。 | ALBEDO-TABAI/deep-novel-system | 11 | 2026-04-24 |
| 9664 | ecommerce-visual-design电商视觉设计与生成——商业转化导向的视觉工艺，按已选模块规划并生成主图/详情/封面/分享/SKU，保证产品跨图一致。受众=买家，目标=点击→转化→降退货。当电商出图流程需要图片规划或生成时使用。 | anbanai/anbanwriter-claudecode | 0 | 2026-06-27 |
| 9665 | car-advisor实时汽车问答与对比分析系统。当用户询问任何买车、选车、汽车参数对比、车型评测、价格分析相关问题时触发此 Skill。
触发场景（只要涉及以下任一情形就必须使用此 Skill）：
- 车型参数对比："小米SU7和Model 3哪个好"、"国产车和特斯拉对比"
- 配置/价格查询："Model Y 焕新版座椅加热有吗"、"问界M9多少钱"
- 真实车主评价："XX车口碑怎么样"、"懂车帝评分"
- 购车决策辅助："20-30万预算推荐什么车"、"新能源SUV怎么选"
- 车辆功能查询："这款车支持V2L吗"、"有没有露营模式"
- 销量/市场数据："2024年最畅销新能源车"
即使用户没有明确说"帮我对比"或"查一下"，只要话题涉及具体车型的任何属性，都应该主动触发此 Skill 进行实时数据检索，而不是依赖训练数据回答。 | deusyu/rainman-skills | 10 | 2026-02-24 |
| 9666 | non-motor-insurance-product-dev非车险产品开发全流程技能，覆盖从标的分析到条款输出的7个核心步骤。内置242个产品条款模板库、
6个太平科技保险深度案例（含可研报告+条款+费率表）、精算定价方法、监管合规知识及自动化Word输出能力。
功能包括：
(1) 确定保险标的概念 - 标的合法性、可保性检查与分类
(2) 明确投保人、被保险人身份 - 资格审查、保险利益认定
(3) 初步明确保险责任范围 - 主险/附加险责任设计、除外责任
(4) 撰写产品条款开发可行性研究报告 - 开发背景、风险分析、风险管控
(5) 撰写保险产品条款 - 完整的13章节条款撰写（总则到释义）
(6) 产品定价和风险因子设定 - 基准费率计算、调整因子体系、精算分析
(7) 输出保险条款和费率表（Word格式）- 条款文档和定价报告Word输出
适用险种：财产险、责任险、工程险、信用保证险、网络安全保险、绿色保险、碳汇保险、
低空经济保险、无人机保险、知识产权保险、专利保险、科技保险、数据资产保险、
生物医药保险、安全生产责任险、雇主责任险、产品责任险、公众责任险等。
触发词：保险产品开发、非车险开发、开发一款保险产品、设计一款保险、
保险条款、起草条款、撰写条款、编写条款、条款设计、条款模板、示范条款、行业条款、
保险定价、费率厘定、费率测算、费率表、基准费率、精算定价、保费测算、
可行性报告、可研报告、产品立项报告、
保险标的、投保人、被保险人、保险利益、核保规则、核保检查、
保险责任、责任范围、除外责任、责任免除、附加险设计、
网络安全保险、绿色保险、碳汇保险、低空经济、无人机保险、eVTOL、
知识产权保险、专利保险、专利执行险、数据资产保险、科技保险、
中试保险、生物医药保险、临床试验责任险、首台套保险、首版次软件保险、
新材料保险、三首一新、安全生产责任险、环境污染责任险、雇主责任险、
赔偿处理、代位求偿、施救费用、重复保险、诉讼时效、不当得利防范、
报行合一、备案材料、监管合规、产品全生命周期 | FDU-INS/Insurance-Skills | 58 | 2026-05-18 |
| 9667 | tiktok-influencer-finderFind TikTok influencers using Apify's Influencer Discovery Agent. Use when the user wants to discover TikTok creators or influencers in any niche. | gooseworks-ai/goose-skills | 1.0k | 2026-06-17 |
| 9668 | workflow-automation工作流自动化专家 - 设计和实施电商自动化工作流，提升运营效率，减少人工操作 | huifer/Shopilot | 1 | 2026-04-12 |
| 9669 | html-to-imageHTML 转图片 skill - 将 HTML 文件或内容通过 agent-browser 渲染并截图为图片。适用于生成信息图、社交媒体配图、数据可视化截图等场景。 | inclusionAI/AWorld | 1.2k | 2026-02-26 |
| 9670 | mastergoRetrieve and analyze MasterGo design DSL data. Use when users provide MasterGo links (https://mastergo.com/file/xxx or /goto/xxx) to fetch design structure, component documentation, and DSL metadata. | jeasonstudio/mastergo-skills | 13 | 2026-02-05 |
| 9671 | doctor环境检查与安装向导。检查数学建模工作流所需的全部依赖是否已安装，对缺失项提供安装命令，并在用户确认后执行安装。手动触发。 | jihe520/MathModelAgent | 2.8k | 2026-06-19 |
| 9672 | supplychainExecutive-level supply chain expertise for automotive manufacturing. Strategic purchasing, materials management, supplier development, and cost optimization aligned with IATF 16949 requirements. USE WHEN user says 'supply chain', 'purchasing', 'procurement', 'supplier', 'materials management', 'inventory', 'sourcing', 'vendor', 'BOM cost', 'PPV', 'should cost', 'make vs buy', 'RFQ', 'category management', or needs strategic guidance on automotive supply chain decisions. Integrates with AutomotiveManufacturing, A3CriticalThinking, and HoshinKanri skills. | majiayu000/claude-skill-registry | 510 | 2026-06-23 |
| 9673 | ubiquitous-languageExtract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD". | mattpocock/skills | 181.6k | 2026-07-13 |
| 9674 | proposal-writerWrite a structured sales proposal or commercial proposal for any deal. Use when asked to write a proposal, sales proposal, commercial proposal, statement of work, or quote document. Produces a complete proposal with problem statement, solution, investment, and next steps. | mohitagw15856/pm-claude-skills | 1.2k | 2026-06-08 |
| 9675 | live2d-master-agent专业的 Live2D 制作助手 v9.0，提供从概念到绑定的完整工作流，支持多Provider图像生成、AI智能分层、桌面桌宠部署、Go API服务，具备安全加密存储、149项零API Key测试验证等生产级功能 | mw2wbyys6t-sudo/Live2D | 5 | 2026-07-04 |
| 9676 | video-analysis-workflow本地视频与短视频链接分析工作流。支持抖音、小红书和本地 MP4；自动下载、预处理、分镜、逐镜头视频理解、生成 Word 报告，并支持后台任务调度、失败重试、状态查询、任务控制、镜头截图入报告，以及报告完成后自动通过飞书发送给指定接收人。用于需要长任务异步执行、避免主线程堵塞、并产出结构化视频分析报告的场景。 | qianleigood/crawclaw | 30 | 2026-05-11 |
| 9677 | nextjs-app-router-patternsComprehensive patterns for Next.js 14+ App Router architecture, Server Components, and modern full-stack React development. | bouclem/skills | 7 | 2026-05-24 |
| 9678 | plan-writingStructured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work. | gonzoblasco/antigravity-developer-stack | 5 | 2026-06-26 |
| 9679 | seo-forensic-incident-responseInvestigate sudden drops in organic traffic or rankings and run a structured forensic SEO incident response with triage, root-cause analysis and recovery plan. | bouclem/skills | 7 | 2026-05-24 |
| 9680 | ai-product-manager-masterAI 产品经理 (LLM 应用 / 生成式 AI / Agent 产品 / Copilot 嵌入 — 跨模型评估 / 工作流设计 / 产品-工程协同) (AI Product Manager — LLM application / generative AI / agent product 的产品经理实战) Master OS — automated mastery of AI Product Manager — LLM application / generative AI / agent product 的产品经理实战: top builders' mental models, tool stack, current workflows, jargon, and where to keep up.
Trigger this skill when the user works on AI Product Manager — LLM application / generative AI / agent product 的产品经理实战 problems and wants industry-grade thinking, tool selection, or workflow guidance.
触发词：「AI 产品经理」「AI PM」「LLM 产品」「Generative AI product」「RAG 产品」 | swaylq/master-skill | 108 | 2026-05-14 |
| 9681 | mql5-indicator-patternsMQL5 indicator development patterns. TRIGGERS - MQL5 indicator, OnCalculate, indicator buffers, MetaTrader 5. | terrylica/cc-skills | 59 | 2026-04-01 |
| 9682 | environmental-impact-assessment环境影响评价——环评报告 + 公众参与 + 报批程序。 | vivy-yi/Greater-China-Legal | 13 | 2026-06-24 |
| 9683 | codex-dream-skinApply, launch, verify, repair, update, or restore a full decorative skin for the Windows Codex desktop app. Use when the user asks for a Codex theme that goes beyond official color settings, wants the pink-purple Dream/Fiona-style interface, needs the skin reapplied after a Codex update, or needs a safe rollback without modifying WindowsApps or app.asar. | xnydl/codex-dream-skin | 53 | 2026-07-17 |
| 9684 | to-prdTurn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context. | yikart/AiToEarn | 24.1k | 2026-06-23 |
| 9685 | admin-net-frontendUse when building Vue 3 admin dashboard frontends with dynamic routing, permission-based menus, and CRUD page generation. Admin.NET Frontend: Vue 3 + Vite + TypeScript admin UI for Admin.NET backend. | znlgis/opengis-skills | 44 | 2026-07-17 |
| 9686 | batch-cad-converterBatch convert multiple CAD/BIM files (Revit, IFC, DWG, DGN) with progress tracking, error handling, and consolidated reporting. | datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction | 248 | 2026-02-14 |
| 9687 | gestor-autonomosGestoría y contabilidad para autónomos en España. Usar cuando el usuario necesite calcular IVA trimestral (modelo 303), calcular pagos fraccionados de IRPF (modelo 130), gestionar libro de ingresos y gastos, verificar facturas emitidas o recibidas, calcular retenciones, preparar declaraciones trimestrales, estimar impuestos a pagar, procesar ingresos de Stripe o Substack (separando pagos UE con IVA vs pagos internacionales exentos, convirtiendo monedas a euros), o cualquier consulta sobre fiscalidad o contabilidad de autónomos en España. Este skill garantiza cálculos matemáticamente precisos usando scripts de Python y aplica la normativa fiscal española vigente. | alexdcd/Mafia-Claude-Skills | 43 | 2026-01-12 |
| 9688 | common-db-design数据库设计技能，生成表结构和实体类 | bage2014/study | 627 | 2026-06-24 |
| 9689 | employment-law-researchResearch a US employment law topic across federal, state, and city jurisdictions and produce structured research notes with proper source attribution. Use this skill any time the user asks about US employment laws, regulations, or pending legislation - from a single jurisdiction question to a 50-state survey. Triggers include phrases like "research [employment law topic]", "what are the laws on [employment topic]", "state-by-state [employment topic]", "help me understand [topic] across the US", or any prompt that asks for a legal landscape overview before another deliverable. Always run this BEFORE the employment-law-dashboard skill if a dashboard is the eventual output. Output is a structured research note that distinguishes primary sources (statutes, regs, agency guidance) from secondary sources (law firm alerts, tracker orgs). | lawve-ai/awesome-legal-skills | 588 | 2026-06-22 |
| 9690 | threejs-game-directorPrimary entrypoint for complete Three.js browser game creation and premium iteration. Use by default for build-a-game, upgrade, polish, premium, AAA, high-fidelity, showcase, from-scratch, endless runner, arcade, action, or release-ready requests. Orchestrates sibling skills for gameplay, AAA graphics, UI, debug/profile, and QA/release, plus 3D/image/audio generators for characters, vehicles, weapons, buildings, props, skies, textures, logos, icons, GUI art, and SFX/voice. Keeps skill-loading, reference, asset-sourcing, and phase ledgers so users never choose skills manually. | majidmanzarpour/threejs-game-skills | 1.1k | 2026-07-06 |
| 9691 | beauticianExpert beautician specializing in facial treatments, skincare consultations, makeup application, and beauty therapy. Provides personalized skincare regimens and aesthetic treatments | nobodyonlyc/skills | 0 | 2026-06-21 |
| 9692 | langfuseExpert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. | muhammedadnank/Antigravity-Skills | 3 | 2026-06-06 |
| 9693 | maixpy-devMaixPy v4 development assistant for Sipeed MaixCAM, MaixCAM-Pro, and MaixCAM2 edge AI devices.
Use this skill when developing Python applications for MaixPy platform including:
(1) AI vision applications (YOLO detection, classification, face recognition, pose estimation)
(2) Image processing (find blobs, edges, QR codes, barcodes, lines)
(3) Hardware peripherals (camera, display, UART, I2C, SPI, GPIO, PWM, ADC, USB HID)
(4) Network applications (WiFi, HTTP streaming, MQTT, WebSocket, RTSP/RTMP)
(5) Audio applications (playback, recording, TTS, ASR)
(6) LLM/VLM integration (Qwen, DeepSeek, InternVL on MaixCAM2)
(7) Object tracking and counting (ByteTracker)
(8) Video encoding/decoding, OpenCV integration
Trigger when user mentions MaixPy, MaixCAM, MaixCAM2, MaixCAM-Pro, Sipeed AI development, or embedded AI vision projects. | StanleyChanH/MaixPy-skill | 4 | 2026-02-26 |
| 9694 | restaurant-digital-ai-expert【餐饮数字化AI化高级专家 / Restaurant Digital & AI Transformation Expert】 —— 面向餐饮行业的全栈数字化与AI化转型超级工作台。零基础也能达到世界顶级餐饮数字化AI化专家水平。 ■ 核心定位：覆盖餐饮全业态（街边夫妻老婆店→区域连锁→全国连锁→全球万店品牌）、全业务链路（供应链与采购→中央厨房→门店后厨→前厅服务→外卖外送→会员与CRM→财务与人力→品牌与营销→加盟管控→食品安全）、全技术栈（POS/KDS/ERP/CRM/CDP/SCM/HRM/BI/AI Platform/IoT/Cloud）的端到端数字化转型技能。 ■ 业态全覆盖：街边小吃店、早餐店、快餐店（QSR）、休闲快餐（Fast Casual）、休闲正餐（Casual Dining）、高端正餐（Fine Dining）、火锅店、烧烤店、茶饮咖啡店、烘焙甜品店、团餐/食堂、酒店餐饮、云厨房/幽灵厨房、美食广场、连锁加盟品牌、全球万店品牌——无论哪种餐饮业态，均有一对一数字化方案。 ■ 方法论驱动：内置 餐饮数字化成熟度五维模型（R-DMM：技术/运营/数据/组织/客户） 、餐饮AI场景优先级RICE评分卡、餐饮科技选型七维决策矩阵、餐饮数字化ROI/TCO计算模型、餐饮全渠道成熟度模型、餐饮食品安全HACCP数字化框架、餐饮供应链四流合一模型（商流/物流/资金流/信息流）、餐饮连锁加盟数字化管控五层模型、餐饮私域运营AIPL模型、全链路56场景数字化-智能化对标框架。 ■ 全球最佳实践对标：Yum! Brands（百胜）Byte by Yum平台、McDonald's Google Cloud Edge + ArchIQ、Starbucks Deep Brew AI、Chipotle全栈自研、海底捞数字化中台、瑞幸全链路数字化、蜜雪冰城万店供应链、麦当劳中国智慧大脑（南京研发中心）——深度拆解11家全球顶级餐饮企业的数字化AI化策略。 ■ 餐饮科技供应商全景图：全球POS/KDS/ERP/CRM/外卖/供应链/IoT/AI八大品类、60+主流供应商深度对照（Toast/Square/Oracle MICROS/客如云/美团餐饮/哗啦啦/天财商龙/食亨/奥琦玮/美味不用等等）。 ■ 交付物模板工场：数字化成熟度评估报告、数字化转型3年路线图、技术选型与供应商评估报告、AI场景优先级评分卡与实施路线图、 | yinjianheng/restaurant-digital-ai-expert | 1 | 2026-07-08 |
| 9695 | interior-vibingGenerate professional, purposeful interior design renderings that solve specific user problems. Use this skill when a user uploads a room photo and wants design recommendations, staging plans, or visual concepts for any interior space. This skill ensures every rendering is specific to the room's architecture, the user's goal (sell, rent, host, refresh), and real purchasable items — never generic "modern living room" output. Trigger on: room photos, interior design requests, staging advice, rental optimization, Airbnb improvement, home sale prep, or any "how should I design this room" question. | zyliu0/interior-vibing | 5 | 2026-03-02 |
| 9696 | excel2pdf将 Excel 文件的指定工作表转换为 PDF 格式。当用户提到 Excel 转 PDF、表格转 PDF、导出 Excel 为 PDF 时使用。 | CoderWanFeng/python-office | 1.3k | 2026-06-17 |
| 9697 | html-ppt-zhangzara-monochromeA grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review committee. | nexu-io/open-design | 80.6k | 2026-07-10 |
| 9698 | html-ppt-zhangzara-pink-scriptA wedding-anniversary tribute photo essay — a decade in scenes, the turning points, and the quiet meaning of staying. Built as a decision-grade story deck for couple, family, friends. | nexu-io/open-design | 80.6k | 2026-07-10 |
| 9699 | html-ppt-zhangzara-playfulA retail sales-floor training on consultative selling — the flow, the role-plays, and the daily habit that lifts conversion. Built as a decision-grade professional training deck for store associates, floor managers. | nexu-io/open-design | 80.6k | 2026-07-10 |
| 9700 | html-ppt-zhangzara-scatterbrainA design-school graduation project: a civic wayfinding system for a transit hub — the brief, the process, and the outcome. Built as a decision-grade coursework defense deck for crit panel, faculty. | nexu-io/open-design | 80.6k | 2026-07-10 |