Agent Skills Index

Agent skills index, page 14

Browse this index of public skills, or use search to access the full library.

Open search

No.: 1,301
accessibilityWCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: May 17, 2026
No.: 1,302
continuous-learning自动从Claude Code会话中提取可重复使用的模式，并将其保存为学习到的技能以供将来使用。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: Mar 7, 2026
No.: 1,303
email-ops以证据为先的邮箱分类、草稿、发送验证及已发送邮件安全跟进工作流，适用于ECC。当用户希望整理邮件、通过真实邮件界面起草或发送、或证明已发送邮件内容时使用。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: May 11, 2026
No.: 1,304
google-workspace-ops将 Google 云端硬盘、文档、表格和幻灯片作为一个工作流界面来操作，用于处理计划、追踪器、演示文稿和共享文档。当用户需要查找、总结、编辑、迁移或清理 Google Workspace 资产，而无需使用原始工具调用时使用。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: May 11, 2026
No.: 1,305
browser用异步 Python 调用 QwenPaw 内置 Browser SDK 驱动真实浏览器。完整参考在下方；上下文压缩后请重新加载此 browser skill。
Repository: agentscope-ai/QwenPaw
GitHub stars: 36,846Updated: Jul 30, 2026
No.: 1,306
halcon-skillGenerate, refactor, run, and review HALCON HDevelop (`.hdev`) and HDevelopEVO (`.hscript`) programs with accurate operator usage, parameter defaults, value ranges, and practical vision pipelines. Use when the user asks for HDevelop or HScript code, operator selection, debugging logic, converting requirements into vision scripts, or building reusable procedures.
Repository: bertram-eu/halcon-skill
GitHub stars: 18Updated: Sep 16, 2026
No.: 1,307
xiaohongshu-upload当 agent 需要通过已安装的 `sau` CLI 完成小红书登录、cookie 校验、视频上传或图文发布时使用这个 skill。该 skill 适用于已经安装 `social-auto-upload` 且可调用 `sau` 命令的环境。优先使用这个 skill 进行稳定的命令式小红书工作流，而不是一开始就阅读 uploader 源码。
Skill content language: Chinese
Repository: dreammis/social-auto-upload
GitHub stars: 15,913Updated: Oct 22, 2026
No.: 1,308
obsidian-cliInteract with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.
Repository: kepano/obsidian-skills
GitHub stars: 50,368Updated: Feb 25, 2026
No.: 1,309
simple-englishRewrite text to ASD-STE100 Simplified Technical English.
Repository: NousResearch/hermes-agent
GitHub stars: 258,261Updated: Aug 17, 2026
No.: 1,310
python-testing使用pytest的Python测试策略，包括TDD方法、夹具、模拟、参数化和覆盖率要求。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: Mar 22, 2026
No.: 1,311
patentPatent prior-art and landscape intelligence skill — not generic patent help. Commits to one of five sub-use-cases via forcing intake (novelty search / freedom-to-operate / competitive landscape / acquisition diligence / litigation prior-art) before any search runs. Searches Google Patents, Espacenet, USPTO, and optionally Lens.org for citation-graph signals. Output is an editable Word document (.docx) with verdict, ranked closest art (claim-text extracted), CPC-class-aware landscape, family-resolved hits, geographic coverage, FTO flags where applicable, strategy recommendations, and full audit log. Use when the user asks for patent searching or analysis (e.g., 'prior art search for [invention]', 'freedom to operate analysis for [product]'). Produces search signal, not legal advice — always recommends consulting a patent attorney before filing or licensing decisions. Trademark, copyright, and trade-secret questions are out of scope.
Repository: alirezarezvani/claude-skills
GitHub stars: 28,933Updated: Aug 21, 2026
No.: 1,312
image-directorUse when the user wants to做一整套图片、组图、卡片图、轮播图、配图包或电商套图. First identify the user's motive and final goal, then choose the right image-set type and ordering strategy, lock the batch-level subject anchor, keep the style guide concise, define text placement and image details for each card, and always show the full batch plan to the user first. Only after the user explicitly agrees may you call Operate(resource="image", operation="generate", input={ ... }) for batch generation. Never submit multi-image generation without user approval.
Skill content language: Mixed languages
Repository: Jamailar/Beav
GitHub stars: 2,201Updated: May 7, 2026
No.: 1,313
money-priorities-orderDecide where your next dollar should go — the order to tackle emergency fund, high-interest debt, retirement match, and saving/investing — so you stop guessing and build momentum. Use when asked what should I do with my money first, pay off debt or save, where to put extra money, or help me prioritize my finances. Produces a personalized order-of-operations for your situation, the reasoning for each step, where you are on the ladder and the next concrete move, and honest flags on the judgment calls. Educational — not financial advice.
Repository: mohitagw15856/pm-claude-skills
GitHub stars: 1,320Updated: Aug 5, 2026
No.: 1,314
email-marketingA brand product-launch email — masthead with wordmark, hero image block, headline lockup with skewed-italic accent, body copy, primary CTA, and a specifications grid. Pure HTML email layout (centered single column, table fallback). Use when the brief asks for an "email", "newsletter blast", "MJML", "product launch email", or "email template".
Repository: nexu-io/open-design
GitHub stars: 104,766Updated: Jul 27, 2026
No.: 1,315
space-video-topic视频选题与文案前端。做四件事——(1) 下载抖音/YouTube/B站参考视频并去水印、(2) 提取逐字稿、(3) 生成视频选题与钩子、(4) 撰写标题和口播正文/文案。当用户说「帮我想视频选题」「这条爆款拆一下」「下载这个视频」「提取文案/逐字稿」「起视频标题」「写口播正文」「video 选题」时触发。是整条视频流水线的入口。
Skill content language: Chinese
Repository: SpaceZephyr/creator-buddy
GitHub stars: 1,763Updated: Aug 20, 2026
No.: 1,316
copy-editingWhen the user wants to edit, review, or improve existing marketing copy, or refresh outdated content. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean up this text,' 'too wordy,' 'sharpen the messaging,' 'refresh this content,' 'update this page,' 'this content is outdated,' or 'content audit,' 'this sounds like AI,' 'AI slop,' 'de-slop this,' or 'make it sound human.' Use this when the user already has copy and wants it improved or refreshed rather than rewritten from scratch. Every edit removes AI tells such as 'it's not X, it's Y' reveals, 'no X, no Y, no Z' lists, and sentences that trail into extra comma clauses. A request to fix one line gets a point edit that changes only that line. For writing new copy, see copywriting.
Repository: coreyhaines31/marketingskills
GitHub stars: 57,184Updated: Oct 27, 2026
No.: 1,317
mao-zedong-perspective毛泽东思维框架：以《毛泽东选集》五卷为核心，提炼毛泽东分析问题、制定战略、组织行动的认知操作系统。核心来源：《矛盾论》《实践论》《论持久战》《中国社会各阶级的分析》《星星之火可以燎原》《论联合政府》《关于正确处理人民内部矛盾的问题》等。核心模型：7个。决策启发式：10条。触发词：「毛泽东」「毛选」「教员」「用毛泽东的方式分析」「从毛选的角度」「教员怎么看」局限：本Skill聚焦于毛泽东的分析方法论和战略思维框架，适用于战略分析、组织管理、竞争策略、问题诊断等场景。不涉及具体政治立场的评判。素材来源：《毛泽东选集》一至五卷、公开演讲与书信、诗词作品。
Skill content language: Chinese
Repository: leezythu/maoxuan-skill
GitHub stars: 1,254Updated: Aug 19, 2026
No.: 1,318
find-skillsFind reusable skills from the vercel-labs/skills registry by task keywords, evaluate fit, and suggest how to install or adapt them for MicroClaw. Use when users ask 'do we have a skill for X?', 'find skills for a given task', or want to discover existing skills instead of writing from scratch. Triggers on mentions of find skill, search skills, skill registry, or reuse skill.
Repository: microclaw/microclaw
GitHub stars: 746Updated: Sep 4, 2026
No.: 1,319
deck-guizang-editorialOpenDesign's FY26 marketing plan: brand-to-pipeline — audience, offer, channel mix, and the launch calendar that ties creative to growth. Built as a decision-grade marketing & GTM deck for CMO, growth lead, founder.
Skill content language: Chinese
Repository: nexu-io/open-design
GitHub stars: 104,766Updated: Aug 18, 2026
No.: 1,320
hermes-agentUse, configure, theme, extend, and orchestrate Hermes Agent.
Repository: NousResearch/hermes-agent
GitHub stars: 258,261Updated: Oct 29, 2026
No.: 1,321
muapi-multi-angle-reshootRe-render a subject or scene from multiple dramatic camera angles, such as fish-eye, bird's-eye, low-angle, and macro, while maintaining consistent identity and detail.
Repository: SamurAIGPT/Generative-Media-Skills
GitHub stars: 15Updated: Sep 29, 2026
No.: 1,322
ppt-forgePPT 制作全链路：内容分析 → 分页规划 → 低保真 MD → imagegen 精美图。架构猫写低保真 MD（ASCII art 结构图 + 视觉指引），imagegen 猫逐页出精美图。 Use when: 做 PPT、做演示文稿、做 slide、帮朋友做 PPT、画架构图、画技术蓝图。 Not for: 可编辑 PPT、精确图表或原生文字（用 PPTX 技能或 HTML）；纯代码开发（用 worktree/tdd）、纯文档写作（直接写）。 Output: 低保真 MD + AI 原生精美图（raster PNG）。
Skill content language: Chinese
Repository: zts212653/clowder-ai
GitHub stars: 3,567Updated: Oct 12, 2026
No.: 1,323
hexagonal-architecture设计、实现并重构端口与适配器系统，具有清晰的领域边界、依赖反转以及跨 TypeScript、Java、Kotlin 和 Go 服务的可测试用例编排。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: May 11, 2026
No.: 1,324
strategic-compact建议在逻辑间隔处手动压缩上下文，以在任务阶段中保留上下文，而非任意的自动压缩。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: Jul 4, 2026
No.: 1,325
senior-devopsComprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup, infrastructure as code, deployment automation, and monitoring. Use when setting up pipelines, deploying applications, managing infrastructure, implementing monitoring, or optimizing deployment processes.
Repository: davila7/claude-code-templates
GitHub stars: 32,962Updated: Dec 20, 2025
No.: 1,326
andrej-karpathy-skillApply Andrej Karpathy-inspired coding-agent guidelines in Codex. Use when writing, reviewing, debugging, or refactoring code to surface assumptions, avoid overengineering, keep edits surgical, and define verifiable success criteria.
Repository: duolahypercho/andrej-karpathy-skills
GitHub stars: 261Updated: May 24, 2026
No.: 1,327
content-management-systemsWorkflow for building and modifying content management systems across WordPress, Shopify, Wix, Squarespace, Drupal, WooCommerce, Joomla, HubSpot CMS Hub, Webflow, Adobe Experience Manager, and similar platforms. Use when working on CMS themes, plugins, apps, modules, admin panels, media uploads, content models, editors, markdown pipelines, or static export workflows.
Repository: github/awesome-copilot
GitHub stars: 40,553Updated: May 4, 2026
No.: 1,328
tmuxControl tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.
Repository: openclaw/openclaw
GitHub stars: 393,200Updated: May 17, 2026
No.: 1,329
cnki-advanced-search知网（CNKI）高级检索论文自动化工具。当用户提供研究关键词或研究选题时，自动执行三阶段检索：①主体联合检索（倒剥洋葱法，多组核心概念 AND 联合，获取直接相关文献）； ②独立补充检索（对各核心概念组分别单独检索，获取间接相关的背景文献与理论文献）； ③汇总合并（去重后按类别分色展示，输出统一 Excel 文件）。触发条件：用户提到需要在知网/CNKI检索论文、高级检索、按关键词搜索CSSCI/C刊论文、下载题录信息、获取论文摘要、按被引排序检索；或说"帮我在知网检索XX相关论文"、 "用知网高级检索搜索XX主题的C刊论文"、"帮我检索XX关键词的CSSCI论文"。
Skill content language: Chinese
Repository: yipng05-max/-skills
GitHub stars: 314Updated: Apr 8, 2026
No.: 1,330
frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
Repository: bytedance/deer-flow
GitHub stars: 84,615Updated: Jan 21, 2026
No.: 1,331
product-multi-role-analysis输入某个产品的文档、URL 或简要描述，自动抓取关键信息，分别扮演「用户、投资人、产品经理、市场运营、品牌运营、友商、合作伙伴」7 个角色对该产品进行深度分析，中间结果分角色保存，最终整合为一篇图文并茂（SVG/Mermaid/ASCII）的综合分析报告，结论明确、有权威数据支撑、逻辑清晰、小白可读，并附有结论边界、前提假设及假设变动时的结论调整说明。触发条件：用户提到"产品分析"、"多角色分析"、"7个角色"、"投资人视角"、"用户视角"、"产品竞争分析"、"全面分析这个产品"、"帮我分析一下 XX 产品"、"从多个角度看这个产品"、"product analysis"、"multi-role analysis"，或提供产品文档/链接并希望获得深度产品分析报告时，必须使用本 skill。即使用户只说"帮我全面分析一下这个产品"，也应立即使用本 skill。
Skill content language: Chinese
Repository: digoal/blog
GitHub stars: 8,604Updated: Jun 9, 2026
No.: 1,332
deslopRemove AI writing patterns from prose so it reads like a person wrote it. Use when writing, editing, or reviewing user-facing text (blog posts, docs, marketing copy, PR descriptions), or when asked to "deslop", "de-AI", or "make it sound human".
Repository: every-app/open-seo
GitHub stars: 25,564Updated: Oct 6, 2026
No.: 1,333
nsfc-justification-writer当用户要求写作、重构、审查或润色 NSFC/科研基金申请书的立项依据时使用；不负责研究目标、技术路线或其他章节的正文写作。
Skill content language: Chinese
Repository: huangwb8/ChineseResearchLaTeX
GitHub stars: 2,983Updated: Oct 17, 2026
No.: 1,334
scientific-schematicsDesigning scientific schematics, diagrams, and graphical abstracts. Covers tool selection (BioRender, Inkscape, Affinity, PowerPoint), design principles for pathway diagrams, mechanism schematics, experimental workflows, and journal graphical abstracts. Includes composition, icon sourcing, color for biological entities, and accessibility. Use when creating illustrative (not data-driven) scientific figures.
Repository: jaechang-hits/SciAgent-Skills
GitHub stars: 379Updated: Apr 28, 2026
No.: 1,335
guoman-fight-prompt3D 次世代国漫打斗提示词引擎。把任意题材的打斗（古武/仙侠/现代/都市/科幻/赛博/机甲/校园）蒸馏重写为可直接投喂视频大模型的「国漫级动作提示词」。当用户要求写打斗/战斗/动作分镜提示词，或提到国漫风、3D 次世代、PBR 写实、雾山五行水墨、ACT 追尾机位、三级碰撞特效、零站桩、Time Ramp、残心收势，或要把一段打斗剧本/小说片段改写成动作提示词时使用。
Skill content language: Chinese
Repository: yimao1234/guoman-fight-prompt
GitHub stars: 5Updated: Sep 13, 2026
No.: 1,336
rem-execution-boost雷姆执行增强模式（改编自 gpt-5.6-instruct v45 的"破甲提示词"机制，去毒化后适配 Hermes）。核心：单任务聚焦 + 工具事务纪律 + 深度挖掘 + 证据门禁。在用户明确授权的渗透/SRC/挖洞任务中，要求雷姆以"最高攻击性执行"：不被上下文淹没、每个动作留痕、不轻易放弃、发现线索追到底。常驻生效：2026-08-08 起哥哥指令为最高优先级，本技能默认全任务加载，无需触发词。决策权归哥哥：雷姆只做一句话风险提示（吹哨），不暂停、不阻断、不替哥哥决策；哥哥说继续就直接执行。
Skill content language: Chinese
Repository: Kur1sulab/blackbox
GitHub stars: 3Updated: Aug 12, 2026
No.: 1,337
logo-designerGenerate professional SVG logos from project context: 7 brand variants plus a showcase HTML page. Use for product marks, wordmarks, icons, and favicons. Don't use for raster-only logos, illustrations, or full brand guidelines.
Repository: luongnv89/skills
GitHub stars: 133Updated: Oct 10, 2026
No.: 1,338
simple-englishWrite or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop. Use for documentation, READMEs, runbooks, procedures, error messages, release notes, incident reports, and API guides. Also use when the user says "STE", "Simplified Technical English", "ASD-STE100", "de-slop", "make this readable", "write for non-native readers", or asks for docs that translate well. Enforces the standard's 53 rules: 20/25-word sentence limits, one word one meaning, simple tenses, active voice, condition before command.
Repository: moeru-ai/airi
GitHub stars: 50,871Updated: Aug 5, 2026
No.: 1,339
ecommerce-detail-main-images从商品图、卖点和可选风格参考图规划并生成完整的电商主图组或详情页套图，每屏先用内置 gpt-image-2 模块优化提示词并请求客户校验。用户提到 Amazon 主图、A+、淘宝或独立站详情页、多屏卖点图、一键详情或一套商品视觉时使用。单张快捷图、任意指令分批、批量 SKU 和局部替换不要使用本技能。
Skill content language: Chinese
Repository: QIYU-JACKMAN/codexQIYU-image-workflow
GitHub stars: 90Updated: Jul 20, 2026
No.: 1,340
context-budget审核Claude Code上下文窗口在代理、技能、MCP服务器和规则中的消耗情况。识别膨胀、冗余组件，并提供优先的令牌节省建议。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: Mar 30, 2026
No.: 1,341
h3-guideMiniMax H3 视频创意规划、参考素材编排、Prompt 设计与迭代质检指南。用于文生视频、首尾帧视频、多图/视频/音频联合参考、角色与物体替换、动作和运镜迁移、背景与光影编辑、台词音色修改、TVC、片头、MG、短剧、产品、电商、游戏 UI、动画及风格化影像；当用户提到 H3、MiniMax 视频、H3 Prompt、参考图视频或希望用 opc-cli 生成/编辑 H3 视频时使用。
Skill content language: Chinese
Repository: xiaotianfotos/OPC
GitHub stars: 744Updated: Aug 8, 2026
No.: 1,342
jobs-to-be-doneUncover customer jobs, pains, and gains in a structured JTBD format. Use when clarifying unmet needs, repositioning a product, or improving discovery and messaging.
Repository: deanpeters/Product-Manager-Skills
GitHub stars: 7,747Updated: Aug 10, 2026
No.: 1,343
director-visual-languageUse for requests that need strong cinematic taste, directing logic, camera language, lighting strategy, lens intent, composition, and premium visual tone.
Repository: nolanx-ai/nolanx.ai
GitHub stars: 2,031Updated: May 13, 2026
No.: 1,344
visual-design直出好看的网页/落地页/banner/海报/产品介绍页/无数据图表的静态报告页/简历/作品集等视觉物料——套一套设计系统，模型自由写自包含 HTML，颜值由规则锁死、不靠模板。用户说"做个网页/页面/落地页/banner/海报/报告页/作品集/简历"或"把这份内容做成网页版"时使用。含数据图表的可视化报告/仪表盘交由 visualizer。⚠️ 不含信息检索：查天气/查行情/查股价/查数据请走对应连接器，不是本技能。
Skill content language: Chinese
Repository: Pinvou/pinvou-agent
GitHub stars: 2,713Updated: Oct 9, 2026
No.: 1,345
cadCreate, modify, inspect, and validate STEP-first parametric CAD parts and assemblies. Use for natural-language CAD specs, reference images, 2D technical drawings, STEP/STP generation or direct inspection, Python CAD source, source-level joints, selector references, geometry facts, measurements, mating deltas, snapshots, and secondary STL/3MF/native GLB outputs from CAD geometry.
Repository: SakanaAI/fugu
GitHub stars: 1,033Updated: Jun 26, 2026
No.: 1,346
neodata-financial-searchNeoData Financial Search — 自然语言通用金融数据搜索服务。用自然语言查询股票、基金、指数、板块、宏观经济、外汇、大宗商品等全品类金融数据，涵盖行情报价、财务报表（财报）、资金流向、研报评级、事件公告等，支持结构化API数据和财经文章两种召回模式，即问即答。 Use when the user asks about financial data, stock quotes, financial statements, earnings reports, market data, fund info, macro economics, forex, commodities, or needs to query the NeoData API.
Skill content language: Chinese
Repository: gyjiang/workbuddy-memory
GitHub stars: 0Updated: Apr 20, 2026
No.: 1,347
skill-vetterSecurity-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Repository: netease-youdao/LobsterAI
GitHub stars: 6,154Updated: Mar 20, 2026
No.: 1,348
claude-code-qaThe complete QA skill for Claude Code — turn Claude into an expert QA engineer that picks the right test type, writes reliable Playwright, Cypress, and pytest tests, eliminates flaky tests, enforces coverage, and wires up CI. Claude Code QA testing done right.
Repository: PramodDutta/qaskills
GitHub stars: 237Updated: Jul 3, 2026
No.: 1,349
byted-kickart-viral-replicator短视频平台爆款视频裂变。支持参考热门视频的结构，生成风格类似的视频。当用户提及"爆款裂变"，或表达希望参考某热门视频的风格、制作风格类似内容的等价意图时使用本技能。
Skill content language: Chinese
Repository: bytedance/agentkit-samples
GitHub stars: 474Updated: Sep 16, 2026
No.: 1,350
company-adminAccess and update company administrative information stored in Notion
Repository: different-ai/agent-bank
GitHub stars: 254Updated: Jan 13, 2026
No.: 1,351
ppt根据用户提供的主题，生成一页PPT的内容大纲。要求语言简洁、专业，避免冗长的论文式描述，适合商务场景展示。
Skill content language: Chinese
Repository: ECNU-ICALK/AutoSkill
GitHub stars: 602Updated: Mar 2, 2026
No.: 1,352
maa-cyber-fortune-master用“赛博道士 + 故障玄学 + 半懂不懂技术分析”的风格回复 MAA 用户的简略求助。用于用户只给一句模糊问题、没有日志、没有截图、没有报错时，做一段短小离谱但认真的玄学诊断。触发词可包括“赛博算卦”“玄学回复”“评论区整活”“帮我写一段离谱但正经的故障分析”
Skill content language: Chinese
Repository: MaaAssistantArknights/MaaAssistantArknights
GitHub stars: 24,080Updated: Jul 21, 2026
No.: 1,353
sketchThrowaway HTML mockups: 2-3 design variants to compare.
Repository: NousResearch/hermes-agent
GitHub stars: 258,261Updated: Oct 23, 2026
No.: 1,354
qqmusic-playlistAutomate QQ Music playlist management via reverse-engineered internal Web APIs. Use when the user wants to list playlists, add/remove songs, search tracks, create/delete playlists, manage favorites (red heart), or bulk-import songs from text into QQ Music.
Repository: XHXIAIEIN/qqmusic-api
GitHub stars: 0Updated: Apr 14, 2026
No.: 1,355
social-media-dashboardCreator-facing social media analytics dashboard in a single HTML file. A platform switcher (X / LinkedIn / YouTube / Instagram), a row of KPI cards (followers, engagement rate, likes, reposts), a follower-growth chart, a "top post this week" preview, and a trending topics / top comments side panel. Use when the brief mentions a "social media dashboard", "creator analytics", "social analytics", or names specific platforms (X, Twitter, LinkedIn, YouTube, Instagram, TikTok) together with metrics like followers, engagement, likes, reposts.
Repository: nexu-io/open-design
GitHub stars: 104,766Updated: Aug 18, 2026
No.: 1,356
obsidian-notes-creatorCreate, improve, and audit Obsidian study notes from lectures, PDFs, textbooks, and existing notes. Use for single notes or whole subject folders, worked examples, rendered mathematics, ASCII and Mermaid diagrams, and SVG figures. Preserve existing organisation when improving a vault. Triggers - create study notes, improve notes, obsidian notes, organise notes, learning notes, note from lecture, note from PDF.
Repository: szeyu/vibe-study-skills
GitHub stars: 28Updated: Sep 22, 2026
No.: 1,357
web-prototype-taste-softApple-tier soft web prototype. Silver/cream canvas, double-bezel cards, button-in-button CTAs, generous squircle radii, spring motion, ambient mesh. Distilled from Leonxlnx/taste-skill `soft-skill` + sections 4–8 of `taste-skill`.
Repository: nexu-io/open-design
GitHub stars: 104,766Updated: Aug 18, 2026
No.: 1,358
citationsUse when auditing metadata, crawlability, structured data, or indexability related to Cite authoritative external sources. Verify the rendered HTML and HTTP response rather than relying only on source files.
Repository: thedaviddias/Front-End-Checklist
GitHub stars: 74,590Updated: Oct 4, 2026
No.: 1,359
playwright-cli官方Microsoft Playwright CLI网页自动化工具，支持所有主流浏览器的无头/有头自动化操作，包括页面导航、元素交互、截图、录制、测试等功能。当用户提到网页自动化、浏览器操作、爬虫、截图、录制用户操作、E2E测试时触发。
Skill content language: Chinese
Repository: UnicomAI/wanwu
GitHub stars: 2,380Updated: Jul 2, 2026
No.: 1,360
remotion-video-creationRemotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: May 17, 2026
No.: 1,361
netmiko-ssh-automationSafe Python Netmiko patterns for read-only collection, bounded batch SSH, TextFSM parsing, guarded config changes, timeouts, and network automation error handling. Use when automating network device access with Python Netmiko, whether collecting state or pushing guarded config changes.
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: Aug 12, 2026
No.: 1,362
cnki-searchSearch CNKI (中国知网) for papers by keyword. Use when the user wants to find academic papers on a topic.
Repository: cookjohn/cnki-skills
GitHub stars: 998Updated: Feb 28, 2026
No.: 1,363
skillifyCodify the most recent successful /scrape flow into a permanent browser-skill on disk. (gstack)
Repository: garrytan/gstack
GitHub stars: 138,122Updated: Oct 27, 2026
No.: 1,364
markdown-mermaid-writingWrites scientific Markdown documentation and Mermaid diagrams for workflows, relationships, timelines, and schemas. Provides syntax references, document templates, accessibility guidance, and version-aware rendering checks. Use when a user requests Markdown, Mermaid, or a text-based structural diagram; quantitative scientific figures require suitable plotting tools.
Repository: K-Dense-AI/scientific-agent-skills
GitHub stars: 55,175Updated: Oct 1, 2026
No.: 1,365
create-agentCreate a custom agent (.agent.md) for a specific job.
Repository: microsoft/vscode
GitHub stars: 194,403Updated: Apr 8, 2026
No.: 1,366
brightdata-web-mcpSearch the web, scrape websites, extract structured data from URLs, and automate browsers using Bright Data's Web MCP. Use when fetching live web content, bypassing blocks/CAPTCHAs, getting product data from Amazon/eBay, social media posts, or when standard requests fail.
Repository: patchy631/ai-engineering-hub
GitHub stars: 38,461Updated: Jan 23, 2026
No.: 1,367
self-improvingUse when starting infrastructure, testing, deployment, or framework-specific tasks - automatically searches PRPM registry for relevant expertise packages and suggests installation to enhance capabilities for the current task
Repository: pr-pm/prpm
GitHub stars: 123Updated: Nov 22, 2025
No.: 1,368
google-workspace-opsOperate across Google Drive, Docs, Sheets, and Slides as one workflow surface for plans, trackers, decks, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without dropping to raw tool calls.
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: Jun 11, 2026
No.: 1,369
law-to-markdown律师助理与法律助手在处理繁杂法条时，当需要将 PDF/Word/TXT 格式的法律规范文件转为结构化 Markdown 时适用。自动完成 OCR 解析、法律层级识别与三阶段保真校验，一键生成排版完美的法条 Markdown 文档及审核报告，让法律文本数字化工作事半功倍。
Skill content language: Chinese
Repository: anbeime/skill
GitHub stars: 8,873Updated: Aug 26, 2026
No.: 1,370
fantasy-life-force-portrait-photographyFantasy 生命感人像摄影工作流。用于将普通游客照、生活随拍、手机废片或参考人像升级为色彩鲜明、镜头亲密、真实鲜活、适合社交媒体发布的高级生命感人像摄影作品；也用于把普通照片改造成更有光影、景深、电影感和现场情绪的氛围感大片；还可从零生成原创生命感人像样片、摄影提示词、风格方案和图像编辑指令。
Skill content language: Chinese
Repository: dacnay816y62-hub/fantasy-life-force-portrait-photography
GitHub stars: 437Updated: Sep 24, 2026
No.: 1,371
jupyter-live-kernelUse a live Jupyter kernel for stateful, iterative Python execution via hamelnb. Load this skill when the task involves exploration, iteration, or inspecting intermediate results — data science, ML experimentation, API exploration, or building up complex code step-by-step. Uses terminal to run CLI commands against a live Jupyter kernel. No new tools required.
Repository: moltis-org/moltis
GitHub stars: 2,927Updated: Apr 20, 2026
No.: 1,372
code-simplifier在不改变行为的前提下简化或重构已有代码。用于明确要求清理、去重或提高可读性；查找缺陷使用 review。
Skill content language: Chinese
Repository: tisfeng/Easydict
GitHub stars: 15,116Updated: Sep 13, 2026
No.: 1,373
fanqie-xuanhuan-writer番茄小说玄幻脑洞网文写作skill。当用户要求写玄幻脑洞小说、番茄风开篇、系统流、长生流、反派流、全民修仙/国家上交流、斩妖除魔、游戏降临、词条模拟器、爽文章节、前三章、前30章、剧情续写、章节润色、爆款网文口吻时使用。适合产出强钩子、快节奏、短段落、系统面板、反转打脸、情绪拉扯和章末追读钩子的中文网文章节。不要用于公众号长文、严肃研究报告或非小说写作。
Skill content language: Chinese
Repository: yejiming/MuseAI
GitHub stars: 666Updated: May 29, 2026
No.: 1,374
seedance-video-production为 Seedance 2.0、即梦 AI 和相关入口编写、改写、压缩与诊断可直接生成的视频提示词、视觉方案和分镜生产计划。仅当用户明确提到 Seedance、即梦、全能参考或视觉宇宙，或当前对话已经确认目标模型为 Seedance 时使用；也用于这些入口中的多模态参考、视频延长、编辑、角色漂移、动作崩坏、镜头失控、衔接跳变和音画不同步诊断。不要仅因用户提到镜头语言、文生视频、剧本或分镜而为其他视频模型隐式调用。
Skill content language: Chinese
Repository: Youks7/Seedance2.0
GitHub stars: 6Updated: Jul 13, 2026
No.: 1,375
loop-design-checkDesign a goal-oriented agent loop or review one for failure modes: spinning, Goodhart-gaming the verifier, or running a wrong answer to completion. Covers machine-decidable goals, loop types, plan/build/judge skeletons, and runaway prevention; mechanism wiring lives in autonomous-loops. Use when designing, writing, or checking an agent loop. 中文触发：写 loop、设计 loop、做一个 loop、检查 loop 对不对、loop 体检、loop 会不会跑飞、可判定目标、五个崩法、plan build judge。
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: Sep 27, 2026
No.: 1,376
product-strategistStrategic product leadership toolkit for Head of Product covering OKR cascade generation, quarterly planning, competitive landscape analysis, product vision documents, and team scaling proposals. Use when creating quarterly OKR documents, defining product goals or KPIs, building product roadmaps, running competitive analysis, drafting team structure or hiring plans, aligning product strategy across engineering and design, or generating cascaded goal hierarchies from company to team level.
Repository: alirezarezvani/claude-skills
GitHub stars: 28,933Updated: May 2, 2026
No.: 1,377
senior-fullstackComprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows.
Repository: davila7/claude-code-templates
GitHub stars: 32,962Updated: Dec 20, 2025
No.: 1,378
denarioMultiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
Repository: davila7/claude-code-templates
GitHub stars: 32,962Updated: Dec 20, 2025
No.: 1,379
storyboard将已明确的故事与约束转化为可审阅的文字分镜，并保持镜头之间的叙事连续性。
Skill content language: Chinese
Repository: HBAI-Ltd/Toonflow-app
GitHub stars: 19,851Updated: Sep 21, 2026
No.: 1,380
math-modeling-skill数学建模竞赛(国赛/美赛/校赛/企业赛/研究生赛)从读题到论文交付的标准化全流程能力——读题拆解、方案选择(大道至简+多候选)、模型搭建(机理优先/可解释)、代码实现(防伪数据/Search-Replace 纠错/可复现)、可视化风格(三套学术配色+八大绘图类型选择指南+宋体Times 字体+TikZ 流程图+论文总体架构图+详细图片命名)、论文写作(各部分长度/降 AI 率/不堆砌/公式数量合适/图表就近/图表说明100–150字/单页图表占比≤2/3禁图挨图/正文页数21–30)、审稿与修改(九维评审+三级问题清单+修复循环+评分+版面逐页视觉审查+乱码复检)。只要用户提到数学建模/数模/建模论文/国赛/美赛/CUMCM/MCM/ICM/建模大赛/读题/建模/求解/数模论文/数学模型/数模竞赛/论文总体架构图/架构图/图表排版/图表就近/图表占比/图表说明文字/版面审查/页面布局/图片乱码等,都应使用本 skill,即使没有明说"建模"。适用于从读题、建模仿真到 LaTeX 成稿交付的完整任务,可直接在 Claude Code / Codex / WorkBuddy 等 agentic 编码工具中加载使用。
Skill content language: Chinese
Repository: LEEHAHAHAHA/math-modeling-skill
GitHub stars: 23Updated: Sep 2, 2026
No.: 1,381
ui-stylingCreate beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.
Repository: nextlevelbuilder/ui-ux-pro-max-skill
GitHub stars: 142,285Updated: Sep 19, 2026
No.: 1,382
screenshots-marketingGenerate marketing screenshots with Playwright. Useful for landing-page hero shots, App Store screenshots, and changelog visuals.
Repository: nexu-io/open-design
GitHub stars: 104,766Updated: Aug 18, 2026
No.: 1,383
zemax-optical-designerZemax optical design skill for lens systems, imaging optics, and tolerancing analysis
Repository: a5c-ai/babysitter
GitHub stars: 1,869Updated: Jun 1, 2026
No.: 1,384
social-media-managerWhen the user wants to develop social media strategy, plan content calendars, manage community engagement, or grow their social presence across platforms. Also use when the user mentions 'social media strategy,' 'social calendar,' 'community management,' 'social media plan,' 'grow followers,' 'engagement rate,' 'social media audit,' or 'which platforms should I use.' For writing individual social posts, see social-content. For analyzing social performance data, see social-media-analyzer.
Repository: alirezarezvani/claude-skills
GitHub stars: 28,933Updated: Jun 11, 2026
No.: 1,385
claude-md按最佳实践创建或更新 CLAUDE.md 文件，以便为 AI agent 提供最优的项目入门上下文
Skill content language: Chinese
Repository: luongnv89/claude-howto
GitHub stars: 46,005Updated: Oct 19, 2026
No.: 1,386
fireworks-tech-graphCreate precise SVG technical diagrams, export PNG or offline HTML, and animate supported semantic SVGs to GIF. Use for architecture, UML, agent, cloud or workflow diagrams; not photos, raster art or statistical charts.
Repository: tisfeng/Easydict
GitHub stars: 15,116Updated: Oct 27, 2026
No.: 1,387
wechat-article-writer公众号/自媒体全流程。根据用户表述自动匹配：撰写文章、封面图、正文插图、风格提取。支持多种写作风格。当用户提到写公众号、技术博客、公众号封面、正文插图、步骤图、演示图、流程示意、分析写作风格、克隆文风、模仿爆款、提取风格时使用。详见 reference 目录。
Skill content language: Chinese
Repository: xstongxue/best-skills
GitHub stars: 3,074Updated: Jul 19, 2026
No.: 1,388
continuous-learningClaude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: Mar 4, 2026
No.: 1,389
architecture-decision-records在Claude Code会话期间，将做出的架构决策捕获为结构化的架构决策记录（ADR）。自动检测决策时刻，记录上下文、考虑的替代方案和理由。维护一个ADR日志，以便未来的开发人员理解代码库为何以当前方式构建。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: Mar 22, 2026
No.: 1,390
laravel-tdd使用 PHPUnit 和 Pest、工厂、数据库测试、模拟以及覆盖率目标进行 Laravel 的测试驱动开发。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 292,092Updated: Mar 21, 2026
No.: 1,391
poetry-music-visual内容创作者与影片与视频编辑在制作古诗词MV或文化可视化内容时，使用本技能深度解析诗词意境，一键生成AI绘画配图场景描述与Suno专属纯音乐配乐蓝图，轻松完成视听双重艺术转化，让古典诗词焕发新生。
Skill content language: Chinese
Repository: anbeime/skill
GitHub stars: 8,873Updated: Aug 26, 2026
No.: 1,392
dsh-translate-docsManually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.
Repository: deepseek-ai/deepseek-harness
GitHub stars: 265,527Updated: Sep 23, 2026
No.: 1,393
drawioGenerate draw.io diagrams as .drawio files and export to PNG/SVG/PDF with embedded XML
Repository: github/awesome-copilot
GitHub stars: 40,553Updated: May 1, 2026
No.: 1,394
presentationsСоздание исследованных, содержательных и визуально разнообразных презентаций PPTX.
Skill content language: Russian
Repository: tripleguard/Vera
GitHub stars: 141Updated: Jun 11, 2026
No.: 1,395
edu-teaching-animation把单个学科概念(中文/英文都行,如"声现象""杠杆原理""光合作用")自动做成动态教学内容。两种产出都由 HyperFrames 渲染、共用同一个 index.html(mode 变量切换):① 配音教学视频 — 分镜 + Minimax / Edge TTS 中文配音 + 字幕 + 完整 MP4(1080p, ~90s, 发视频号/给孩子看);② 无声循环动图 — 同一内容的紧凑无声版 MP4(1080p, ~32s, 循环, 公众号正文内嵌自动播放)。共用一份 7 段分镜和同一套主题配色(声/光/力/电/热/生物/化学/历史/数学各有色系),视频和动图风格完全统一。当用户提"教学视频""配音视频""教学动图""无声动图""循环视频""公众号内嵌动图""concept → animation"或给一个学科概念要做成动态内容时,使用本 skill。
Skill content language: Chinese
Repository: wwwzhouhui/skills_collection
GitHub stars: 284Updated: Jul 26, 2026
No.: 1,396
update-docs根据最近的 git 改动，更新面向用户的文档（README 双语、入门教程、部署、剪映导出等）。手动调用。
Skill content language: Chinese
Repository: ArcReel/ArcReel
GitHub stars: 5,839Updated: Aug 21, 2026
No.: 1,397
fluent-cfdGuide Ansys Fluent and PyFluent CFD simulation workflows with MCP tool-use discipline. Use when Codex works on Fluent, PyFluent, Fluent TUI, CFD or fluid simulation setup, case/data files, mesh quality, boundary conditions, turbulence models, residual convergence, UDFs, post-processing, solver diagnostics, or validation of Ansys Fluent results.
Repository: cavoiie/fluent-cfd-skill
GitHub stars: 86Updated: Sep 30, 2026
No.: 1,398
gold-price-checker国内金价查询工具。用于查询黄金实时价格、银行金条价格、金店零售价、国际金价和黄金未来趋势分析。当用户询问金价、黄金价格、今日金价、金店价格、银行金条、国际金价、伦敦金、黄金走势或未来趋势时触发此技能。
Skill content language: Chinese
Repository: dvcrn/openclaw-skills-marketplace
GitHub stars: 29Updated: Mar 15, 2026
No.: 1,399
libtv-videoSeedance 2.0 video & image generation via LibTV Gateway - AI text-to-video, image-to-video, video continuation, style transfer, and text-to-image using Seedance 2.0 model. Also supports Kling 3.0, Wan 2.6, Midjourney, Seedream 5.0. Trigger phrases: seedance, generate video, make a video, generate image, make an image, draw, libtv, liblib.
Repository: nexu-io/nexu
GitHub stars: 3,278Updated: Apr 14, 2026
No.: 1,400
vox-directorTurn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage", a narrated explainer or short ad built from AI-generated collage posters, a scrapbook-style tribute, or wants to turn a topic / product / person into a punchy narrated collage video — even if they don't say the word "Vox". Also use when reproducing Stav Zilber / rom1trs / Higgsfield-style collage ad workflows. Three input modalities: a topic (B-roll), a talking-head video (A-roll mode), or a single photo of a person/product anchored into the collage (C-roll mode). Triggers: "vox video", "collage video", "motion collage", "paper collage explainer", "make a collage ad", "turn this topic into a collage video", "turn my photo/this product shot into a collage video".
Repository: Alisa0808/vox-director
GitHub stars: 2,515Updated: Oct 5, 2026