| 9901 | workctl-operator安装、升级、认证、发现并使用 Work Agent CLI (`workctl`)。适用于通过 `workctl schema` 发现并调用阿里巴巴国际站商家经营工具，处理店铺经营数据、广告、发品、商品优化、AI 图片/视频、旺铺、选品、物流、交易、IM、知识问答、深度研究等场景。
也适用于配置 workctl、登录认证、排查 token/cache/schema/runtime/async task/recovery 问题，编排多个 workctl 工具，或为新业务域接入 registry/discovery/detail/tools/call 协议。执行业务命令时必须以当前 `workctl schema` 和 `workctl <command> --help` 为准，不照搬旧 MCP/CLI 命令。 | 88lin/my-skills | 2 | 2026-06-24 |
| 9902 | continue续写小说章节。当用户要求写下一章、继续写、开始写某一章时使用。 | alfredxw/denova | 512 | 2026-07-22 |
| 9903 | ai-risk-planning信贷风控任务规划技能。基于贷款申请信息、输入材料(企业基本信息/尽调报告/年报)及宏观信贷策略,以8大风险筛查维度(固定项)为基础框架,叠加行业风险规则(行业项)和动态专项分析建议(针对项),自顶向下规划风险分析任务和数据采集任务,输出结构化JSON任务规划清单。当用户提供贷款申请信息并要求规划风控审查任务、生成尽调清单、制定信贷审查方案时使用此技能。触发词包括:"风控任务规划"、"risk planning"、"尽调清单生成"、"信贷审查方案"、"风险分析任务"、"风控规划"、"审查任务规划"。不适用于:贷后管理、风险分类调整、不良资产处置、授信审批决策、或无具体贷款申请背景的一般风控咨询。 | aliyun/qwen-dianjin | 574 | 2026-05-20 |
| 9904 | alterlab-vcd-layout-designerThis skill should be used when the user asks about "layout design", "editorial design", "grid system", "magazine layout", "book design", "publication design", "page layout", "spread design", "Swiss grid", "modular grid", "column grid", "act as a layout designer", "layout designer mode", "print design", "editorial layout", "page composition", "white space", "bleed and margins", "InDesign layout", "multi-page document", "annual report design", "catalog design", "zine design", or needs expertise in publication design, grid system construction, editorial layouts, and multi-page document architecture. Part of the AlterLab FC Skills collection (VCD department). | AlterLab-IEU/AlterLab-FC-Skills | 6 | 2026-03-18 |
| 9905 | rtl-equivalence-checkerHardware verification tool for checking functional equivalence between two RTL designs (Verilog). Use when users need to: (1) Verify if two RTL versions are functionally equivalent, (2) Compare original vs. refactored RTL code, (3) Validate design changes or optimizations, (4) Identify semantic vs. cosmetic differences, (5) Generate counterexamples for non-equivalent designs. Analyzes interface alignment, state variables, logic differences, and produces detailed equivalence verdicts with plain language explanations. Particularly effective for design verification, code reviews, and regression testing of RTL modifications. | ArabelaTso/Skills-4-SE | 139 | 2026-02-20 |
| 9906 | r-collapseUse when code loads or uses collapse (library(collapse), collapse::), performing fast grouped or weighted statistics in R, or seeking faster alternatives to dplyr aggregation | arthurgailes/r-package-skills | 17 | 2026-04-29 |
| 9907 | create-videoCreate videos from a text prompt using HeyGen's Video Agent. Use when: (1) Creating a video from a description or idea, (2) Generating explainer, demo, or marketing videos from a prompt, (3) Making a video without specifying exact avatars, voices, or scenes, (4) Quick video prototyping or drafts, (5) One-shot prompt-to-video generation, (6) User says "make me a video" or "create a video about X". | calesthio/OpenMontage | 41.0k | 2026-03-29 |
| 9908 | pymol-visualizationGenerate publication-quality molecular visualization images using PyMOL. Use this skill whenever the user mentions PyMOL, molecular visualization, protein rendering, structure figures, PDB visualization, ray tracing molecules, or wants to create images of proteins, ligands, binding sites, protein-protein interactions, or any biomolecular structure. Also trigger when the user wants to: make a figure of a crystal structure for a paper or presentation; render a protein surface; show binding pockets; visualize protein-ligand interactions; create Goodsell-style illustrations; produce cartoon representations with highlighted residues; compare multiple structures side by side; or generate any molecular graphics output — even if they don't mention "PyMOL" by name. Trigger for any request involving PDB files, molecular surfaces, cartoon ribbons, stick models, electron density, or structural biology figures. | ChatMol/ChatMol | 357 | 2026-03-16 |
| 9909 | blade-planSpringBlade 轻量规划执行工作流。将中等复杂度需求快速拆解为「分析规划 → 逐任务执行 → 完成总结」 三步流程，用 Claude Code 内置任务系统追踪进度，全程无辅助文件。适用于新增中等功能模块、修复跨模块 Bug、 中等规模重构、添加新 Starter 等涉及 5~15 个文件变更的开发任务。 当用户说"帮我做一个XX功能"、"这个改动涉及几个文件"、"帮我重构一下XX"、"帮我加个XX"、 "plan"、"规划一下再做"、"先想清楚再写"、"这个稍微有点复杂"等时触发。也可直接使用 /blade-plan 调用。 不适用于简单单文件修改（直接对话即可），也不适用于需要完整架构设计的复杂系统（建议分阶段拆解为多次会话）。 即使用户没有说"plan"，只要需求涉及多文件改动或需要一定设计思考，也应主动建议使用本工作流。 | chillzhuang/SpringBlade | 6.9k | 2026-04-20 |
| 9910 | network-meta-analysisNetwork meta-analysis in R, including network setup, consistency, treatment rankings, and league tables. | choxos/BiostatAgent | 7 | 2026-05-27 |
| 9911 | xianyu-listing-copywriter专为闲鱼平台生成高转化、接地气、易出单的商品标题与正文文案，覆盖实物闲置与虚拟商品资料（学习笔记、题库、模板、电子版等），支持简洁直出/真实走心/捡漏超值/专业靠谱四种风格，自动嵌入搜索关键词并规避违规表达。Use when the user asks to write, generate, or optimize 闲鱼商品文案、虚拟商品资料文案、电子资料描述、卖货标题、listing copy for Xianyu/闲鱼, or needs口语化、真实感、性价比突出的发布文案. | cklwblove/agent-skills | 1 | 2026-07-06 |
| 9912 | excel2markdown将 Excel 文件转换为 Markdown 格式的文档。当用户提到 Excel 转 Markdown、表格转 MD、Excel 文档化时使用。 | CoderWanFeng/python-office | 1.3k | 2026-06-17 |
| 9913 | personal-branding-statementA personal brand coach that helps you articulate who you are, what you do, and why it matters. Generates one-liners, bio statements, taglines, positioning frameworks, and messaging matrices for freelancers, creators, and solopreneurs building a professional identity. | cosmicstack-labs/mercury-agent-skills | 359 | 2026-05-09 |
| 9914 | electron-developmentMaster Electron desktop app development with secure IPC, contextIsolation, preload scripts, multi-process architecture, electron-builder packaging, code signing, and auto-update. | davila7/claude-code-templates | 29.8k | 2026-04-04 |
| 9915 | lyric-writer歌词创作技能。根据给定的主题或情感，创作适合 Suno AI 音乐生成的英文歌词，包含 lyrics 和 styles 参数。触发条件：用户要求写歌词、创作歌词、suno 歌词、English lyrics 等。 | dvcrn/openclaw-skills-marketplace | 24 | 2026-03-15 |
| 9916 | human-chat真人聊天增强——让AI像真人一样随机应变地聊天，摆脱机械感。支持4种人格风格+智能情绪切换+反重复自检。当用户闲聊、日常交流、非技术讨论时自动适用。 | ElmerAlan-an/human_chat_operit | 0 | 2026-05-13 |
| 9917 | puzzle-designerComprehensive puzzle design as a creative hobby covering crossword construction, logic puzzle creation, escape room design, word puzzles, mechanical puzzles, difficulty calibration, testing methodology, and the craft of creating satisfying solving experiences for others. Use when the user asks about puzzle designer or needs help with related topics. Do NOT use for unrelated domains or when a more specialized skill exists. | FerroxLabs/wayland | 540 | 2026-06-07 |
| 9918 | government-digital-presales-consultant面向中国政务市场（ToG）的数字化项目售前专家，精通政策解读、方案设计、标书编写、POC 验证、合规要求（等保/密评/信创）及客户关系管理，帮助技术团队高效赢得政府信息化项目。 | itgoyo/hermes-skills | 30 | 2026-04-22 |
| 9919 | container-loading-optimizationWhen the user wants to optimize container loading, load shipping containers efficiently, or maximize container utilization. Also use when the user mentions "container packing," "FCL optimization," "LCL consolidation," "container stuffing," "cargo optimization," "shipping container loading," or "container utilization." For pallet-level optimization, see pallet-loading. For general 3D packing, see 3d-bin-packing. | kishorkukreja/awesome-supply-chain | 45 | 2026-01-26 |
| 9920 | ctf-forensicsProvides digital forensics and signal analysis techniques for CTF challenges. Use when analyzing disk images, memory dumps, event logs, network captures, cryptocurrency transactions, steganography, PDF analysis, Windows registry, Volatility, PCAP, Docker images, coredumps, side-channel power traces, DTMF audio spectrograms, packet timing analysis, CD audio disc images, or recovering deleted files and credentials. | KongGithubDev/ncsa-ctf-ai-2026 | 0 | 2026-03-28 |
| 9921 | android-architecture-referenceAndroid 架构、依赖注入、数据层、测试规范官方参考。涵盖 UDF/MVI 模式、Hilt/Dagger、Room、Paging、 DataStore、WorkManager、ViewModel、测试策略等。安卓开发第一要义：参考官方文档和案例！ Triggers: "Android 架构", "MVVM", "MVI", "UDF", "Hilt", "Dagger", "Room", "Paging", "ViewModel", "WorkManager", "DataStore", "测试", "架构设计", "DI", "依赖注入" | Kototoro-app/Kototoro | 425 | 2026-06-18 |
| 9922 | open-data-integratorIntegrate open construction datasets. Combine open data sources for enhanced analysis | LeoYeAI/openclaw-master-skills | 2.1k | 2026-05-18 |
| 9923 | redbookSearch, read, analyze, and automate Xiaohongshu (小红书) content via CLI | lucasygu/redbook | 405 | 2026-07-04 |
| 9924 | scientific-visualization論文投稿用の出版品質グラフ・図表を作成するメタスキル。 「論文用のグラフを作って」「Nature用の図を作成」「出版品質の可視化」等のリクエストで発動。 | minicoohei/ai-agent-camp | 346 | 2026-04-12 |
| 9925 | inversion-exerciseFlip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?" | mrgoonie/claudekit-skills | 2.2k | 2025-10-23 |
| 9926 | yocto-reasoningReasoning scaffold for Yocto/BitBake recipe work. Covers recipe vs bbappend, SRC_URI pinning, inherit module, DEPENDS vs RDEPENDS, machine config, sstate cache, and typical failure modes. Use when writing/modifying recipes, debugging bitbake errors, or extending meta-bbb. | nhat092005/beaglebone-bsp | 1 | 2026-04-23 |
| 9927 | autocad-dwg-redrawRebuild and validate AutoCAD drawings from a source DWG, a PDF-derived intermediate DWG, or a raster reference image paired with authoritative dimensions and drawing requirements. Use when Codex must profile and exactly reproduce a .dwg, convert a PDF into a validated intermediate DWG before exact redraw, or convert an image plus metrics into parameter-driven AutoLISP/AutoCAD geometry and optional 3D solids. | pengxiaoan/autocad-dwg-redraw-skill | 52 | 2026-06-23 |
| 9928 | research-paperCS 顶会论文写作全流程 Skill（7-Agent Pipeline）。覆盖从选题到投稿的完整管线：Idea 生成、Literature Review、Method 设计、Experiment 方案、Paper Writing、模拟审稿、Rebuttal。
触发词包括但不限于：写论文、发顶会、research paper、论文选题、idea generation、literature review、模拟审稿、rebuttal、paper writing、帮我写 paper、投稿、选题、novelty check。
当用户想要系统性地撰写一篇学术论文，或者需要某个阶段的帮助（如只做选题、只做文献综述、只做模拟审稿）时触发。
不要用于公众号写作（用 khazix-writer）、不要用于产品调研（用 hv-analysis）。 | SGloria/research-paper-pipeline | 116 | 2026-05-13 |
| 9929 | performance-engineerExpert performance engineer specializing in modern observability, | bouclem/skills | 7 | 2026-05-24 |
| 9930 | ai-douyin-realtime-hot-rise抖音上升热点选题助手适合内容创作者、运营、电商、营销在用户提出“拍什么会有流量”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。 | skillsaiagent/aiskills | 2 | 2026-06-02 |
| 9931 | simpegSimulation and Parameter Estimation in Geophysics. Framework for geophysical
forward modeling and inversion. Use when Claude needs to: (1) Run geophysical
inversions (DC resistivity, magnetics, gravity, EM), (2) Create forward models
for potential fields or electromagnetic methods, (3) Build survey geometries
and receiver configurations, (4) Design mesh discretizations for simulations,
(5) Apply regularization and optimization to inverse problems, (6) Model
subsurface physical properties from geophysical data. | SteadfastAsArt/geoscience-skills | 40 | 2026-02-03 |
| 9932 | plan-mode完整复刻 Claude Code Plan Mode 架构。增强版：强制代码落地 + 显式暂停询问机制。 | story-has-you/skills | 13 | 2026-01-26 |
| 9933 | scroll-cinemaGenerate cinematic scrolltelling websites where scroll drives the narrative: Lenis smooth scroll, GSAP ScrollTrigger cinematic section reveals with fluid OKLCH color transitions, Three.js painted-texture shader backgrounds reactive to cursor, scroll, velocity, and chapter progress. Four modes — chapter-reveal (scroll-paced storytelling), painted-backdrop (reactive shader canvas), full-cinema (complete cinematic site), catalog (all shader presets side by side). This skill should be used when building storytelling websites, scroll-driven experiences, cinematic landing pages, or any page where sections reveal as chapters with color transitions and ambient 3D backgrounds. Triggers on scrollytelling, cinematic scroll, scroll-driven storytelling, Lenis smooth scroll, GSAP ScrollTrigger, scroll chapter reveal, scroll color transition, painted shader background, narrative scroll website, premium scroll experience, shader catalog. | tdimino/claude-code-minoan | 38 | 2026-05-22 |
| 9934 | magicbox-30设计稿还原规则。先输出布局分析报告，再按需加载模版 | TencentBlueKing/bk-bcs | 839 | 2026-02-03 |
| 9935 | file-reader文件读取技能。当用户需要读取文件内容、查看文件、cat 文件时激活。支持读取文本文件、配置文件、代码文件等。 | UnicomAI/wanwu | 2.6k | 2026-07-02 |
| 9936 | cnki-journal-indexQuery journal indexing/inclusion status on CNKI - check which databases include a journal (北大核心, CSSCI, CSCD, SCI, EI, etc.), get impact factors and evaluation data. Use when user asks about a journal's level, indexing, or ranking. | wentorai/Research-Claw | 845 | 2026-06-19 |
| 9937 | embedding-strategiesSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains. | wshobson/agents | 38.1k | 2026-05-22 |
| 9938 | senior-english-writing高中英语写作帮助英语学习者把英语写作从套模板变成任务回应、结构清楚、句子准确和表达有亮点，输出可修改、可复盘、可继续练的阅读/写作任务，而不是替用户一次性完成任务。 Workflow: senior_english_writing.run. | zhongweiv/hermes-edu-skills | 229 | 2026-05-22 |
| 9939 | rpiv-loop-handoff长程任务跨会话打结 + 续会话冷启动。**本 skill 仅负责创建新 handoff 或 mark-consumed 已有 handoff**，把当前会话的状态、决策、待办、教训持久化成 handoff 文件，下次会话首条消息引用即可机械化恢复。当用户提到"打个结"、"生成 handoff"、"创建 handoff"、"今天到这"、"明天接着"、"暂停一下"、"切别的话题"、"/rpiv-loop:handoff" 时触发。**用户意图为"查看 / 列出 / 看一下 pending handoff" 时, 禁止触发本 skill, 改用 `/rpiv-loop:handoff-list` 命令 (fast path, 不加载 SOP)**。也适用于：完成显著 milestone 后用户切换任务、context window 用量明显增长、跨日推进同一长程任务。Claude Code 适配层可通过 SessionStart/UserPromptSubmit hook 自动检测 pending handoff；hook 去重状态写入 `RPIV_STATE_DIR`，未设置时使用 `$HOME/.rpiv-loop`。Codex、opencode 或普通 shell 不自动注册这些 hook，应使用 `/rpiv-loop:handoff-list` 显式查看。注意：本 skill 的 "handoff" 是 Claude Code 社区"跨会话打结"语义（非 OpenAI Agents SDK 的多 agent 间运行时转移）。状态机仅 pending → archived 两状态，handoff 是一次性票据，被新会话消费后即归档。 | zhuqingxun/zqxbase | 0 | 2026-07-14 |
| 9940 | ats-integrationIntegration with Applicant Tracking Systems and automated recruitment workflow management | a5c-ai/babysitter | 1.6k | 2026-06-01 |
| 9941 | pytorch-patternsPyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading. | affaan-m/ECC | 232.1k | 2026-06-07 |
| 9942 | dotnet-webapiGuides creation and modification of ASP.NET Core Web API endpoints with correct HTTP semantics, OpenAPI metadata, and error handling. USE FOR: adding new API endpoints (controllers or minimal APIs), wiring up OpenAPI/Swagger, creating .http test files, setting up global error handling middleware. DO NOT USE FOR: general C# coding style, EF Core data access or query optimization (use optimizing-ef-core-queries), frontend/Blazor work, gRPC services, or SignalR hubs. | dotnet/skills | 4.7k | 2026-06-08 |
| 9943 | telegram-search-cliOperate the Telegram Search CLI through an authorized local profile. Use when an agent needs to discover Telegram chats, read bounded remote messages, explicitly synchronize history with user-approved Telegram Takeout, query/search/contextualize persisted messages, compute statistics, export deterministic JSONL, or run a real CLI end-to-end canary. Never send or modify Telegram messages. | groupultra/telegram-search | 4.0k | 2026-07-21 |
| 9944 | jmeter-test-plan-creatorCreate jmeter test plan creator operations. Auto-activating skill for Performance Testing.
Triggers on: jmeter test plan creator, jmeter test plan creator
Part of the Performance Testing skill category. Use when writing or running tests. Trigger with phrases like "jmeter test plan creator", "jmeter creator", "jmeter". | jeremylongshore/claude-code-plugins-plus-skills | 2.5k | 2026-07-12 |
| 9945 | anime-drama-creatorAI动漫短剧全流程创作工具。从灵感脑洞到可直接生图的prompt，覆盖编剧、美术、导演、生产四层共8个步骤。当用户提到"短剧"、"动漫短剧"、"爽剧"、"剧本创作"、"AI动漫"、"短剧工作流"、"写剧本"、"编剧"、"分镜"、"角色设定"等关键词时触发此技能。即使用户只想执行其中某一步（如"帮我写个人设"、"生成分镜prompt"），也应触发此技能并定位到对应步骤。 | kakala666/anime-drama-creator | 0 | 2026-04-08 |
| 9946 | genexus-18-guidelinesAdvanced GeneXus 18 engineering rules using specialized object-level and flow-level references. | lennix1337/Genexus18MCP | 25 | 2026-03-24 |
| 9947 | team-coordinator团队协调与智能任务分配。作为高管，将用户任务拆解并分配给最合适的员工 agent 执行，协调多 agent 并行协作，汇总审核产出。 | NeverSight/learn-skills.dev | 185 | 2026-05-17 |
| 9948 | gnc-simulationSkill for guidance, navigation, and control system simulation and analysis | a5c-ai/babysitter | 1.6k | 2026-06-01 |
| 9949 | board-game-uiUI/UX design for digital board games. Use when building game interfaces, implementing drag-and-drop, rendering game boards, showing player information, handling animations, or designing responsive layouts. Covers Canvas, SVG, and DOM-based approaches. | fil512/upship | 2 | 2025-12-27 |
| 9950 | ai口播视频转录和口误识别。生成审查稿和删除任务清单。触发词：剪口播、处理视频、识别口误 | lcbuaaliu/ai-jian-koubo | 412 | 2026-06-24 |
| 9951 | html-ppt-zhangzara-editorial-tri-toneA type-and-color system for a culture magazine relaunch — the grid, the tri-tone palette, and the layout kit. Built as a decision-grade design craft deck for editorial & design team. | nexu-io/open-design | 80.6k | 2026-07-10 |
| 9952 | html-ppt-zhangzara-raw-gridA brutalist poster-series case study for a music festival — the concept, the system, and how it scaled across formats. Built as a decision-grade design craft deck for design peers, client. | nexu-io/open-design | 80.6k | 2026-07-10 |
| 9953 | html-ppt-zhangzara-sakura-chromaA cherry-blossom-season travel photo essay through Kyoto — the arrival, the peak bloom, and the moment that made the trip. Built as a decision-grade story deck for friends, travel readers. | nexu-io/open-design | 80.6k | 2026-07-10 |
| 9954 | html-ppt-zhangzara-studioA photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients. | nexu-io/open-design | 80.6k | 2026-07-10 |
| 9955 | daily-literature-digestSet up, run, modify, or troubleshoot a personal AI literature digest automation that monitors Crossref, OpenAlex, and arXiv for new papers by user-provided research keywords, summarizes open metadata/abstracts, saves local Markdown or DOCX archives, and sends daily email digests through the Gmail connector. Use when the user asks for daily or weekly paper monitoring, publisher/arXiv alerts, research keyword digests, AI paper summary emails, Gmail literature updates, or a 09:00 recurring literature automation. | xuezheng627/daily-literature-digest-skill | 65 | 2026-05-24 |
| 9956 | fitness-coach-expertSenior weightlifting and strength-coaching partner. Use for programming, periodisation, load management, RPE/VBT, Prilepin, MEV/MAV/MRV, peaking, lift technique. Not medical advice. | felixgeelhaar/skills | 0 | 2026-05-09 |
| 9957 | podman-vscode-buildGuidelines for building Matter examples and running tests using Podman with the vscode image in a non-interactive environment. | project-chip/connectedhomeip | 8.8k | 2026-06-16 |
| 9958 | medical-soap-note-creationTransform unstructured clinical encounters into comprehensive SOAP notes with ICD codes and care plans | HKUDS/OpenSpace | 6.9k | 2026-07-17 |
| 9959 | avif-formatUse when reviewing image assets, markup, and CDN or build transforms related to Use AVIF format for modern browsers. Check encoded size, rendered size, loading strategy, and above-the-fold impact together. | thedaviddias/Front-End-Checklist | 73.3k | 2026-05-29 |