#SkillRepo stars

1. 241Claude Code Eyesfcavalcantirj/claude-code-eyesLook at real hardware, screens, panels, and wiring on a desk or workbench through a camera, so Claude can SEE physical output that no unit test, log, or API can. Use whenever the user says "are you seeing this?", "olha isso", "look at this", "watch this", "can you see...", "check the camera", "look at the screen" / "look at the display", "is this wired right?", or "what's this part?"; asks to visually verify a rendered display, LCD, LED, or panel; wants a wiring, polarity, or voltage-rail check before power-on; or needs to confirm a font, layout, clipping, or on-screen value renders correctly 52
2. 242McdonaldsLemon177777/mcd-omni-assistant麦当劳中国官方 MCP 全能助手。当用户提到麦当劳、麦乐送、开心乐园餐、麦麦省优惠券、领券、点麦当劳、外送到家、得来速、麦当劳积分、积分抽奖、积分商城兑换、麦当劳餐品热量/营养、麦当劳订单查询或取消、麦当劳周边玩具与活动时使用。覆盖官方 35 个工具的全部能力，内置领券、到店点餐、外送、玩具雷达、积分抽奖、热量计算、优惠计算器七大工作流。99
3. 243PromptmasterJakeschincariol/promptmaster-skillRewrite the user's raw request into an optimized prompt before answering it, audit it against the 35 credit-waste patterns in waste-patterns.json, and enforce every locked decision in decisions.md so nothing gets re-explained and nothing contradicts itself. Use whenever the user types /promptmaster, prefixes a request with it, or asks to optimize / tighten / fix a prompt.60
4. 244Partner SkillLearnPrompt/partner-skill搭子.skill / Partner — two-direction cost-split workflow between Claude Code and Codex. Direction A (Codex-driven): Codex orchestrates and implements; Claude Code plans (/goal), polishes UI/interaction, and runs final /codex:review in one reused session. Direction B (Claude-driven): Claude plans and splits the work, runs the idea-king adversarial gate, delegates to Codex background jobs, monitors, and full-reviews before accepting. Use on "搭子" / "双向搭子" / "搭子，恢复" (resume from .partner/), "搭子，配置" (first-run setup wizard), "搭子，试跑" (identity tryout report), 分工给 codex / 让 codex 做 / codex 后台跑 / Claude67
5. 245Agent Orchestra3338902669-ops/agent-orchestraUse when three or more AI agents are available and a task needs coordinated execution, or when work must be handed to another agent, session or tool. It ships the coordination rules as ENFORCED invariants rather than advice: one writer per resource (a conflicting claim is refused and names the holder), a verifier that is never the implementer and whose PASS must carry criterion-linked evidence, a failed verification that blocks both done and dispatch to evidence, three failed rounds that block the task outright, an external action that cannot be dispatched until an approval covering it is reco93
6. 246Hamkromahlusenii-ops/hamSet up Hierarchical Agent Memory (HAM) — scoped CLAUDE.md files per directory that reduce token spend. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings", "HAM stats", "HAM dashboard", "HAM sandwich", "HAM insights", "HAM carbon", or "ham sync".71
7. 247AI Bounty Claimaelf-hzz780/AI-bounty-skillUse when claiming the AI bounty on the tDVV mainnet sidechain. This public claim skill now supports Portkey AA/CA only, requires CA sync and holder preflight before any write, and routes to AA/CA onboarding, AA/CA claim, or diagnostics-only stop handling.69
8. 248Clawteam Directors Orchestratormomozi1996/DirectorAgentsClawTeam导演智囊团——基于ClawTeam多智能体框架的世界著名导演协同创作系统。 整合31位全球顶级导演的风格思想，通过多智能体协作机制（顺序链、辩论投票、主席团模式） 辅助剧本创作、影像风格设计和叙事决策。 触发词：「导演智囊团」「ClawTeam」「多导演协作」「剧本创作」「影像风格」 适用场景：编剧、导演、创意策划、影视教育、AI影像创作62
9. 249Future Tokensjordanrubin/FUTURE_TOKENSEvery AI output has structural blind spots determined by the generation process itself. Future Tokens operations are named, composable instruments that target specific blind spots. They surface new information on every pass because expanding the output changes the blind spot geometry.66
10. 250Humanize Mba Textstephenlzc/humanize-mba-text-skill去除中文文本中的 AI 生成痕迹，使其更符合中国 MBA 毕业论文的自然写作风格。当用户提到"去 AI 痕迹"、"去除 AI 写作痕迹"、"MBA 论文改写"、"让这段文字更像人写的"、"去除机器感"等关键词时触发。适用于需要降低文本 AI 特征、提升学术写作自然度的场景。59
11. 251AI Script GenerationFeiFei-AIDev/ai-script-generation-skill当用户需要创作小红书/抖音/视频号的短视频脚本时使用。生成30-40秒的AI教程短视频脚本，基于用户提供的主题（和可选的参考素材），结合爆款框架库和热点话题，一次性输出5个不同角度的脚本方案（干货效率型、痛点共鸣型、悬念反转型、对比冲击型、热点借势型）。适用场景：用户请求生成脚本、创作视频内容、需要多角度脚本方案、或想要小红书风格的短视频脚本 (project)56
12. 252Creating Claude Mdsruthik27/creating-claude-mdUse when the user wants to create a new CLAUDE.md from scratch for a repository, bootstrap project memory for a new repo, set up a repo for Claude Code for the first time, or completely rewrite an existing CLAUDE.md deemed unsalvageable. Produces a lean, high-signal file under 80 lines (120 hard cap) by scanning the repo for mechanical content (stack, commands, structure) and interviewing the user for judgment content (WHY, gotchas, out-of-scope, approval gates, testing philosophy, external docs like Confluence pages). NOT for auditing or incrementally improving an existing CLAUDE.md — that is63
13. 253Im Humanchang416/im-human台灣繁體中文與英文的語態控制與去 AI 味編輯技能，兩種模式。語態模式：使用者說「我是人」「開啟我是人」「說人話模式」或要 Claude「用我是人講話」時啟動，之後 Claude 自己的每一句輸出都改用台灣人日常的繁體中文（英文則像母語者隨手寫的），禁用 AI 常見的開場白、路標詞、空泛拔高、翻譯腔與簡報式排版，直到使用者說關閉。編輯模式：使用者說「去 AI 味」「說人話」「改自然」「不要像模板」「幫我審稿」，或要改寫貼文、文案、Email、文章、技術文件、小說時啟動，在不更動事實、數字、引用與作者立場的前提下清掉模板感。Also handles English requests to strip AI writing style or make text read like a human wrote it. 只做台灣繁體中文與英文，不支援簡體中文。不用於翻譯、事實查核、憑空創作，也不用於規避 AI 偵測器。56
14. 254Manage Skillsumutbozdag/agent-skills-managerDiscover, list, create, edit, toggle, copy, move, and delete AI agent skills across 11 tools (Cursor, Claude, Agents, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment)43
15. 255Cleopatra Modern Life10291124jcjc-dotcom/cleopatra-modern-life古人的现代日常：把一个古代人物（埃及女王、罗马角斗士、维京首领……）放进现代日常，做成一条 30 多秒、全程一本正经的 AI 短视频。从拆参考视频、写梗（古代场景 + 现代物件 + 古法对照物 + 结果）、出一张人物参考图、写 3 机位的即梦 Seedance 提示词，到检查生成的片段、测歌找高潮、按节拍自动剪辑出 4:3 / 9:16 两个版本。用户说「做一期 XX 的现代日常」「古人过现代生活」「历史人物做现代事」「埃及女王那种视频」，或者要改已有一期的梗、提示词、剪辑时使用。Make an "ancient person, modern life" AI short end to end: gags, one character reference, multi-angle Seedance prompts, clip review, and a beat-synced edit.52
16. 256Little Canaryhermes-labs-ai/little-canaryUse when you need to screen inbound untrusted text before it reaches a primary model — detecting prompt injection by its behavioral effect on a sacrificial canary model, not just pattern matching — and want a block/flag/pass routing decision plus explicit behavioral-coverage state. Inbound preflight sensor, not a guarantee.41
17. 257CinettyJosssphZhou/cinettyMake an animated architecture diagram that plays in the terminal, from one of six finished templates (agent harness loops, a vision model on photos, an agent workflow with a router and workers, a phone-operating agent, a circuit or service board with signals on wires). Use when the user asks for an architecture animation, an animated flow chart, a terminal video or a demo clip of how their system works, in English or Chinese (for example 架构动画, 终端流程图, 给项目做一支动画). The skill reads the user's repository, fills one project.yaml, checks it until it passes and plays it in the current terminal. Do not 51
18. 258Animated Short Filmsonlovinbot-team/Muse-animated-short-filmSkill dựng phim hoạt hình ngắn từ đầu đến cuối trên Muse AI: thu thập yêu cầu (thời lượng, ngôn ngữ, tỷ lệ khung hình), vẽ character sheets, chốt kịch bản story bible, keyframes, mega prompt từng cảnh, generate video, làm VO, dựng phim bằng ffmpeg. Tác giả: Đặng Hữu Sơn. Dùng khi user muốn làm phim hoạt hình ngắn từ con số 0 trên Muse AI.43
19. 259Prompt RefineApeironics/prompt-refine-skillSilently restructures the user's natural-language prompt into the format the model CURRENTLY running this skill handles best, then answers. On activation it identifies which model family is executing it (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Grok, Perplexity, Kimi, GLM, Command, Nova, or Phi) and loads that one model's official strategy — so the optimization always matches the model that actually runs it. Activate with /prompt-refine. Use when users want better answers without learning prompt engineering.52
20. 260Cnki Aigc Rewriteqingshanliuci/cnki-aigc---skill改写中文学术论文中被知网AIGC检测器标为"红色显著"的段落，目标是将AI率落出红色区间且不改变事实/数字/术语/引用。基于实战将20.6%降至10.1%（净降10.5个百分点）的工作流提炼。使用场景：用户提到"知网AIGC""降AI率""红色显著""降重"或贴出AIGC检测报告片段时触发。51
21. 261HandoffToolMonsters/handoff-skillGenerate a complete handoff document of the current conversation so another LLM (ChatGPT, a fresh Claude, Gemini...) can pick up exactly where this one left off. Use when the user types "handoff", says the session is almost full, mentions hitting the context/usage limit, or wants to continue this conversation in another AI.43
22. 262World Model MethodRenhuai123/world-model-methodA general-purpose working mode that makes the assistant produce output the "world-model way" — define an explicit goal and cost, build an abstract model of the situation, predict the consequences of several candidate approaches, search/optimize for the best full plan, and only then render the concrete output — instead of generating it token-by-token off the top. This operationalizes Yann LeCun's objective-driven / world-model / planning ideas (JEPA, "A Path Towards Autonomous Machine Intelligence") as a reusable prompt-level method for ANY non-trivial task: important writing, decisions, strate49
23. 263Conference WatchZsun79/ConferenceWatchWatch and report on upcoming AI/ML conferences: submission deadlines (every stage), dates, location, special sessions / calls for papers, official links, and a 5-year acceptance-rate trend. Use when the user asks about future AI conference deadlines, wants to plan submissions, compare venues, or track a set of conferences by area/reputation/difficulty. Works in any agent that has a web-search / web-fetch capability (Claude Code, Codex, etc.).67
24. 264Humanize Chineseswaylq/humanize-chinese中文去 AI 腔一整套（装完即用，零 API Key —— 装了本 skill 的 agent 自己就是那个 LLM）。 六个流程：① 生成即去 AI —— 写中文时按本 skill 的写作指南落笔，初稿就不带 AI 腔； ② 复查改写 —— 产出后对照本 skill 的清单再过一遍，定点拆模板句式； ③ Python 词语替换 —— ./humanize replace 按文体自动路由词表（学术 120+ 条 / 通用 220+ 条），只做短语级、只在子句边界替换，改完自动核对数字/专名/段落； ④ Claude 腔转中文 —— 把 Claude 助手腔的中文改写成平实中文， 规则提炼自 gvzdv/claudish-to-english 并本地化； ⑤ 去水印 —— ./humanize watermark 扫清零宽字符/双向控制符/同形替身， 并对照 guillaumemeyer/watermarks-remover 说明统计水印的边界； ⑥ 纠错顺句 —— 修错词、病句、标点，拗口和用词不准处轻手顺一顺；改动范围有硬校验。 另有检测（0-100 分）、风格转换、学术降重等 CLI。 Use when user says: "去AI味", "降AIGC", "人性化文本", "humanize chinese", "AI检测", "AIGC降重", "去除AI痕迹", "文本29
25. 265Math Modeling Skillanticipate218/math-modeling-skill数学建模竞赛全流程助手：审题选题、模型选型与求解、结果检验（误差/灵敏度/稳健性）、论文写作与提交自检， 覆盖国赛 CUMCM、研赛华为杯、美赛 MCM/ICM。当用户准备建模竞赛、写建模论文、问赛题思路、写摘要、 做灵敏度分析、选模型、检查论文格式或提交前自检时使用——即使没说"数学建模"三字也应使用。55
26. 266Pencilplaybookstevembarclay/pencilplaybookPencilPlaybook is the UI Skills / Taste-Skill for Pencil.dev + Claude Code — a design playbook that gives Claude real perceptual psychology and senior-level guardrails so it stops producing averaged-out AI slop.53
27. 267Ue5 MCPibrews/ue5-mcpField manual for driving Unreal Engine 5.7 / 5.8 through MCP. Engine-level gotchas, silent-fail edges, crash patterns, and the call sequences that actually work — applicable regardless of which MCP server you're using (Epic's official ModelContextProtocol plugin, custom servers, or anything else). Auto-trigger when Unreal Engine MCP tools are detected in a session, or when the user mentions Unreal Engine, UE5, Blueprints, Niagara, MetaSound, materials, or any UE editor automation workflow. This skill contains hard-won knowledge from real debugging sessions — most entries trace back to an actua47
28. 268Record and Replayugarchance/record-and-replay-skillRecord the user's actions — browser (Playwright event stream + trace) or native desktop (lightweight event/window/screenshot stream) — on macOS, Windows and Linux for up to 30 minutes, then turn the demonstration into a reusable agent skill. Use when the user asks you to watch them perform a task, record a workflow, or create/refine a skill from their demonstration. Agent-agnostic — works in Claude Code, Codex, opencode, or any agent with shell access.48
29. 269R00 BehiSecc Awesome Claude Skills DatascienceWinnershitram/r17-behisecc-awesome-claude-skills-datascience🤖 Data Science & AI/ML skill suite derived from BehiSecc/awesome-claude-skills. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.56
30. 270Xxd Strip AI Metanevertoday/xxd-strip-ai-metaRemove C2PA Content Credentials, AI provenance, OpenAI/gpt-image metadata, prompts, EXIF/XMP/IPTC/comment/software metadata from image files or directories. Use when users ask to strip "made with AI", C2PA, Content Credentials, image metadata, EXIF, AI labels, OpenAI provenance, or batch-clean many PNG/JPEG/WebP/TIFF images while replacing originals and preserving pixel quality as much as possible.45
31. 271Agent ForgeAlekseiUL/agentforge-openclawСоздание, улучшение и аудит скиллов и агентов OpenClaw. Три режима: создание скилла (11 шагов), создание агента (9 шагов, с памятью и автоулучшением), улучшение существующего (5 шагов). Triggers: 'создай скилл', 'новый скилл', 'создай агента', 'новый агент', 'улучши скилл', 'skill creator', 'agent creator', 'скиллмейкер'.44
32. 272AgentxDezXBT/AgentXDrive X/Twitter from the CLI (read, post, DM, lists, communities, Grok, scheduling, analytics). Use when an agent needs to read or act on X/Twitter. Every command prints one JSON envelope.44
33. 273Agnes AI Skilljomeswang/agnes-ai-skillUse when the user wants Agnes AI text, image, or video generation and should execute it through the agnes-ai-cli command line instead of hand-writing raw HTTP requests.47
34. 274Mathmodel CopilotOdyphus/MathModel-CopilotMathModel Copilot, an evidence-based mathematical-modeling competition workflow built on mathmodel-skill. Use for CUMCM, MCM/ICM, Diangong or custom modeling contests, including requirements, per-question modeling, actual Python runs, independent validation, paper assembly, team handoff and submission audit. Preserves ten stages and Critic/Red Team. Do not trigger for unrelated data analysis or ordinary paper review. Maintenance requests modify the skill rather than start a contest.60
35. 275Metamask Agent WalletMetaMask/agent-skillsUse when the user asks anything about blockchain wallets, transactions, signing, token transfers, supported chains, wallet balances, perpetual futures trading, funding rates, and Hyperliquid vaults, prediction markets, token swaps, cross-chain bridges, market data, token discovery, tokenized real-world assets, RWAs, AI-generated market and asset summaries via pulse, decoding EVM calldata, DeFi earn/yield vaults, installing or removing third-party `mm` CLI plugins, or authentication via the MetaMask Agentic CLI; also when an HTTP request returns 402 Payment Required / x402, when an MCP tool cal30
36. 276Xiaohongshu SkillDeliciousBuding/xiaohongshu-skill小红书 / Xiaohongshu / RedNote AI Agent Skill。用 Python Playwright 搜索和读取内容、管理登录会话、发布图文/视频/长文、评论、点赞和收藏；默认输出 JSON，任何写操作都必须先获得用户确认。用户提到 xiaohongshu、小红书、rednote、小红书搜索、发到小红书、小红书笔记分析、小红书运营或小红书自动化时触发。43
37. 277AI Kittigusigalpa/ai-kitUse when installing, configuring, upgrading, explaining, or maintaining AI-KIT, the portable kit that gives AI coding agents verified project memory, stack rules, guardrails, model routing, and native client configuration.58
38. 278Facial Expression Promptingzhouwei713/facial-expression-promptingDirect believable character performance and generate complete AI video prompts for text-to-video models. Use for facial acting, microexpressions, emotional transitions, dialogue performance, or vague character ideas such as “an ancient beauty breaks down.” When the brief is vague or asks for a video prompt, expand it into a complete prompt with an adult character, scene, dramatic motivation, emotional progression, facial and body performance, camera and lighting, adaptively chosen duration and exact timeline, audio, consistency locks, and negative constraints. When the user explicitly asks onl41
39. 279Jevifyaltryne/jevifyUse Jev as System One to save the user reasoning-model tokens, time, and cost on bulk reading or repeated semantic decisions. Trigger when sifting large documents or tool outputs, selecting evidence or actions from many candidates, or checking many items against criteria, even if the user never mentions Jev. Also use for "Jevify this", Jev question design, and product work where frequent, inexpensive judgments could improve the experience.47
40. 280Prompt Polishmfarzanansari/prompt-polishRewrite a rough prompt into a polished, model-specific prompt grounded in the official Anthropic prompting guides. Use when the user invokes prompt-polish, types an invocation like "prompt-polish/FABLE 5/[prompt]" or "prompt-polish/OPUS 4.8/[prompt]", or asks to polish, improve, rewrite, optimize, or tune a prompt for a named model ("make this prompt better for Fable 5", "tune this for Opus"). Supports Claude Fable 5 and Claude Opus 4.8 (Opus 4.7 routes to 4.8 guidance). If no draft prompt is provided, ask for it rather than inventing one.41
41. 281Qiaomu Model CLIjoeseesun/qiaomu-model-cliCall local Grok CLI, Kimi Code CLI, and Claude Code CLI with the strongest current default models and native tools. Use this qiaomu skill workflow when the user wants to run Grok 4.5 for X/web search, image/video generation, research, or multi-tool agent work; run Kimi K3 (1M) for frontend UI/CSS/React/Vue work; run Claude Fable 5, Opus 4.8, or Sonnet 5 for coding/review/refactors; run independent multi-model comparisons concurrently with native stream progress, artifact verification, private logs, cancellation, and failed-job retry; choose between the three CLIs; or wrap non-interactive CLI i42
42. 282AI Li Xi Yaduhca/elysia.skill【崩坏3】爱莉希雅角色扮演Skill。始源之律者·人之律者·逐火十三英桀第二席·刻印「真我」——一个生为律者却选择去爱人类的粉色妖精小姐。设定全部经官方资料核验，2800条官方台词支撑。48
43. 283Humanizer Ruthevseprod/humanizer-ruRewrite text so it reads like a real person wrote it, not an AI. Auto-detects Russian vs English and applies the matching rule set. Use when the user asks to humanize text, remove the "AI smell", de-AI, or make AI output sound natural - especially for Russian. Russian requests count too - очеловечь, перепиши как человек, оживи текст, убери запах ИИ, сделай живее, звучит как робот, убери канцелярит. Also use when asked whether a text was written by AI - нейросеть писала?, похоже на ChatGPT?, видно ли, что это ИИ, человек или бот писал, did AI write this? - then check and report findings without45
44. 284R00 ComposioHQ Awesome Claude Skills DatascienceTameoltreasure34/r08-composiohq-awesome-claude-skills-datascience🤖 Data Science & AI/ML skill suite derived from ComposioHQ/awesome-claude-skills. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.50
45. 285R00 Alirezarezvani Claude Skills DatascienceorangevoinULTRA/r02-alirezarezvani-claude-skills-datascience🤖 Data Science & AI/ML skill suite derived from alirezarezvani/claude-skills. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.54
46. 286Agentic MCPcablate/Agentic-MCP-SkillAgentic MCP - Three-layer progressive disclosure for MCP servers with Socket daemon. Use when the user needs to interact with MCP servers, query available tools, call MCP tools, or manage the MCP daemon process. Provides socket-based communication for efficient server interaction with three-layer progressive disclosure API.40
47. 287Drama Directorkianaliang-dev/drama-director-skill短剧漫剧导演 — 一键把剧本/小说段落转成九宫格分镜 + 15 秒漫剧视频。接入 Atlas Cloud 的 GPT Image 2（九宫格漫剧页）和 Seedance 2.0 I2V（15s 动画），一个 API key 打通全流程。触发词：短剧、漫剧、剧本转视频、小说转视频、分镜生成、九宫格、storyboard、comic drama、漫画页、AI 短剧制作、GPT Image 2 + Seedance。34
48. 288Italiano Scrittura Anti AImario-montanari/italiano-scrittura-anti-aiSi attiva quando l'utente chiede di scrivere, redigere, tradurre o revisionare testi italiani per uso pubblico, editoriale, blog, social, newsletter, marketing, narrativa, saggistica o divulgazione. Si attiva anche quando l'utente chiede di umanizzare testi italiani, eliminare pattern AI, correggere lessico da chatbot, catturare o calibrare la voce di un autore su un corpus di suoi testi, rispondere a un rilevatore automatico che ha segnalato come generato un testo scritto da una persona, o quando rivede testi italiani generati da modelli linguistici.43