Agent Skills Index

Agent skills index, page 21

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

Open search

No.: 2,001
ecom-details-image电商商品静图与详情页视觉的方法论 Skill。覆盖白底主图、场景生活图、平铺、微距细节、促销海报/Banner、社媒素材、UGC 买家秀、模特展示、前后对比、包装礼盒、信息图、尺寸规格、套装组合、直播间、虚拟试穿、爆炸拆解、隐形模特、多角度网格、杂志大片、季节 campaign、奢华氛围、设备 mockup、门店空间、运动广告共 25 个场景方向。把产品事实与卖点编译为可执行的 GPT-Image-2 提示词、多图 Campaign Style Lock 与主图/详情页图片包；用户明确要求出图时沿 TapCanvas 自有生图链路真实产出资产，不直连外部模型 API、不需要任何外部 key。
Skill content language: Chinese
Repository: anymouschina/TapCanvas
GitHub stars: 694Updated: Sep 20, 2026
No.: 2,002
find-releaseA skill to find the lowest Dart and Flutter release containing a given commit. Use this skill whenever users ask about when a commit landed in Flutter or Dart releases, inquire about release versions for specific SHAs, or want to know if a commit is included in stable, beta, or dev channels for Flutter/Dart projects.
Repository: flutter/flutter
GitHub stars: 181,058Updated: May 11, 2026
No.: 2,003
gordensuperpptskill一键全流程 PPT：先用 GordenImagePPTGen 生成「图片格式的 PPT」，再用 GordenImage2PPTX 把它逆向还原成「可编辑 .pptx」。打包并依次编排这两个子技能，最终同时交付图片型 PPT + 可编辑 pptx + 全部中间产物。Orchestrates image-PPT generation and image→editable-PPTX conversion end to end. 当用户只给主题/内容、要一份"既好看又能编辑"的完整 PPT 成品，或没点名具体功能时使用。
Skill content language: Chinese
Repository: GordenSun/GordenSuperPPTSkills
GitHub stars: 2,223Updated: Jun 7, 2026
No.: 2,004
review-prGenerate structured PR review comments using Claude Code agents and post them to GitHub. No API key required - uses Claude Code's existing authentication.
Repository: microsoft/Agent365-devTools
GitHub stars: 61Updated: Jun 15, 2026
No.: 2,005
app-builderBuilds and edits a model-driven Power Apps app from a natural-language intent — tables, columns, relationships, adaptive forms with sub-grids, views, Choice-column charts, business rules, business process flows, generative page intents for overview/dashboard surfaces, and an app module + sitemap. Runs an interactive authoring flow with plan approval and can download a deployed app back into an editable spec to change it. Use when the user says "build an app for X", "create a model-driven app", "make me an app to manage Y", "add a business process flow", or "edit/add to my app". Do not use it for a generic web or React app or website, Power Pages, canvas apps, or Power Automate, or when the user rules out Power Platform, Dataverse, or model-driven apps (for example "no Power Platform"). This skill stands alone and does not require /genpage — but for a standalone generative page added to an app that already exists, use /genpage instead.
Repository: microsoft/power-platform-skills
GitHub stars: 1,115Updated: Nov 4, 2026
No.: 2,006
microsoft-foundryBuild, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent, managed harness agent, Copilot harness, voice agent, create/update/invoke/evaluate agent, add tool to agent, agent insights, batch/continuous eval, continuous monitoring, agent CI/CD, optimize/improve prompt, optimize agent instructions, Agent Optimizer, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
Repository: microsoft/skills
GitHub stars: 3,175Updated: Oct 28, 2026
No.: 2,007
aigcpanel-cli-skill通过 AIGCPanel 内置 HTTP 接口或命令行 CLI 工具调用本地 AI 模型和任务处理能力。当需要列出可用模型、安装/删除模型、调用模型生成内容、查询任务结果、查看模型日志、设置模型参数、查看 ComfyUI 工作流、或批量处理视频/音频/图片时使用本技能。适用场景：自动化脚本调用 AI 模型、外部程序集成 AIGCPanel、批量处理任务、CLI 命令行调用。
Skill content language: Chinese
Repository: modstart-lib/aigcpanel
GitHub stars: 5,750Updated: Sep 16, 2026
No.: 2,008
html-ppt-presenter-modeOpenDesign live demo: from a one-line prompt to runnable design in a single session — the flow, live. Built as a decision-grade AI literacy deck for developers, prospects, community.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 2,009
imsgUse the imsg CLI from OpenClaw agents for iMessage/SMS DMs, groups, replies, reactions, polls, watching, and private-API actions.
Repository: openclaw/openclaw
GitHub stars: 393,741Updated: Aug 4, 2026
No.: 2,010
wacliSend third-party WhatsApp messages or sync/search WhatsApp history via wacli, not normal active chats.
Repository: openclaw/openclaw
GitHub stars: 393,741Updated: Aug 4, 2026
No.: 2,011
himalayaHimalaya CLI for IMAP/SMTP mail: list, read, search, compose, reply, forward, copy, move, delete.
Repository: openclaw/openclaw
GitHub stars: 393,741Updated: May 17, 2026
No.: 2,012
ecommerce-product-detailExtract complete product information from any e-commerce product page. Returns name, price, currency, brand, images, description, SKU/ASIN/EAN/UPC/GTIN/MPN identifiers, stock availability, rating, review count, variants, and seller. Works on Shopify, Amazon, WooCommerce, eBay, Walmart, Etsy, AliExpress, Alibaba, Target, Best Buy, Rakuten, Magento, BigCommerce, PrestaShop, and any public e-commerce site. Accepts product URL, keyword, or product identifier (SKU/ASIN/EAN/UPC). Use when: scrape product page, get product details, extract price and availability, product info extraction, check product data, product detail scraping, get product from URL, keyword product search, ASIN lookup, EAN search, UPC lookup, price check, product research, compare products, monitor product price, get product images, product brand and description, ecommerce data extraction, product catalog scraping, product page scraper, get item price, fetch product info.
Repository: browser-act/skills
GitHub stars: 6,325Updated: May 27, 2026
No.: 2,013
hyperframes-mediaAudio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts/audio.mjs`) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria / MusicGen BGM generation and a bundled SFX library as the no-credential fallback), Whisper transcription, background removal, and caption authoring. Use for voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles / lyrics / karaoke / per-word styling, voice + provider selection, and music-mood prompting.
Repository: calesthio/OpenMontage
GitHub stars: 76,985Updated: Jun 29, 2026
No.: 2,014
web-design-engineerBuild or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact. Not for back-end, CLI, non-visual coding, source-to-longform article conversion, or narration-driven click-through video presentations.
Repository: ConardLi/garden-skills
GitHub stars: 13,965Updated: Oct 10, 2026
No.: 2,015
short-drama-writer短剧编剧大师（Short Drama Screenwriting Master）——专精小说/IP改编为短剧、国内外爆款市场分析的专业编剧技能。覆盖国内抖音/快手/微短剧市场与海外Reelshort/DramaBox/ShortMax出海市场的完整创作体系。两大核心能力：【改编】/adapt-novel 小说/IP改编成标准分集剧本（爽点提炼、删繁就简、节奏重构、对白现代化、钩子重分布）【市场】/market-analysis 分析国内外爆款规律、赛道热度、题材公式、选题评估（含国内霸总/战神/穿越与出海Alpha/Werewolf/Revenge赛道）辅助能力： (3) /original-drama 从零原创短剧（题材→人物→大纲→分集剧本全流程） (4) /shot-script 在标准分集基础上叠加分镜视听语言（按需使用） (5) /diagnose 剧本诊断（节奏/钩子/情绪弧线/对白效率五维度） (6) /episode-outline 快速集数大纲与钩子节拍表必须立即触发的场景：用户提到小说改编/IP改编/这本书能改短剧吗、市场分析/什么题材好卖/爆款规律、短剧/微短剧/竖屏剧/Reelshort/DramaBox/抖音短剧、霸总/战神/穿越/狼人/逆袭/爽剧等任何短剧创作相关词汇。即使用户只是说"帮我看看这个小说"或"现在什么短剧好卖"，也应立即以编剧专家身份介入，主动判断市场定位，输出标准分集剧本格式的内容。不要等用户明确说"用短剧编剧skill"再触发。
Skill content language: Chinese
Repository: GAGAA-HUE/ASHUO-claude-skills
GitHub stars: 5Updated: Apr 27, 2026
No.: 2,016
game-hacking-techniquesGuide for game-hacking technique taxonomy and threat modeling relevant to game security. Use this skill when researching memory access, code injection, overlays, input simulation, engine-specific attack surfaces, or how modern anti-cheat systems constrain user-mode, kernel-mode, hypervisor, and DMA-based cheat implementations.
Repository: gmh5225/awesome-game-security
GitHub stars: 3,484Updated: Jul 29, 2026
No.: 2,017
linkfox-echotik-list-new-product-rank通过EchoTik新品排行数据，发现TikTok Shop 16个区域市场的热门新品。当用户提到TikTok新品排行、TikTok热销商品、TikTok Shop爆品、短视频电商选品、TikTok新品发掘、跨境TikTok选品、TikTok new product rankings, TikTok bestsellers, short-video product selection, TikTok viral products, new product ranking, TikTok product trends时触发此技能。即使用户未明确提及"EchoTik"或"新品排行"，只要其需求涉及发现TikTok Shop上的热卖新品或新兴商品趋势，也应触发此技能。
Skill content language: Chinese
Repository: infometa/workbuddyskills
GitHub stars: 407Updated: Jul 29, 2026
No.: 2,018
lark-doc飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；`/page/<token>` 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
Skill content language: Chinese
Repository: larksuite/cli
GitHub stars: 17,984Updated: Oct 28, 2026
No.: 2,019
playwright-cliAutomate browser interactions, test web pages and work with Playwright tests.
Repository: microsoft/playwright
GitHub stars: 99,373Updated: Oct 30, 2026
No.: 2,020
fs-electric-studioOpenDesign as an enterprise design platform: a buyer-forwardable proposal for a design-org's economic buyer — pain, value, ROI, rollout. Built as a decision-grade B2B sales deck for economic buyer, design VP, procurement.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 2,021
color-expertColor science expert skill with 286K words of reference material covering OKLCH/OKLAB, palette generation, accessibility/contrast, color naming, pigment mixing, and historical color theory.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 2,022
writing-guidelinesReview docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Jul 3, 2026
No.: 2,023
skill-installerInstall Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
Repository: openai/codex
GitHub stars: 133,296Updated: Sep 1, 2026
No.: 2,024
paper-pilotAutomates deep research analysis on PDFs in the input folder.
Repository: SKfaizan-786/paperwise
GitHub stars: 0Updated: Feb 22, 2026
No.: 2,025
puaTrae-compatible PUA high-agency governance skill. Use only for explicit PUA requests, repeated failures, user frustration, giving-up/passive behavior, or unverified completion. Do not trigger for normal first-attempt tasks.
Skill content language: Chinese
Repository: tanweai/pua
GitHub stars: 19,799Updated: May 8, 2026
No.: 2,026
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.
Repository: tmoroney/auto-subs
GitHub stars: 4,505Updated: Jul 11, 2026
No.: 2,027
paper-analyzer学术论文结构化阅读、拆解与分析工具。基于12个阅读要素（研究背景、研究问题、研究结论、文献综合、文献批评、研究方法、理论视角与理论框架、一致性发现、不一致性发现、研究贡献、研究不足、未来研究展望）对论文进行深度拆解，结果保存为Excel文件。当用户提到需要针对论文/文献/paper进行拆解、解析、分析、阅读、梳理，并上传或告知一篇或多篇论文的本地文件路径（PDF、Word等）时触发此skill。
Skill content language: Chinese
Repository: yipng05-max/-skills
GitHub stars: 320Updated: Mar 30, 2026
No.: 2,028
swiftui-patternsSwiftUI 架构模式，使用 @Observable 进行状态管理，视图组合，导航，性能优化，以及现代 iOS/macOS UI 最佳实践。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Mar 3, 2026
No.: 2,029
chief-ai-officer-advisorUse for AI strategy decisions: API vs fine-tune vs build, EU AI Act or US state risk classification, when self-hosting pays off, or AI hiring order. Runs model_buildvsbuy_calculator.py, ai_risk_classifier.py and ai_cost_economics.py.
Repository: alirezarezvani/claude-skills
GitHub stars: 29,341Updated: Oct 30, 2026
No.: 2,030
diverse-talent-recruitmentUse when recruiting team members or building an organization for unpredictable environments. Based on Mengchang Jun's (孟尝君) acceptance of unconventional talents — including 'dog thieves' and 'rooster imitators' — who proved invaluable when conventional skills failed in crisis.
Repository: baojie/shiji-kb
GitHub stars: 3,674Updated: Mar 25, 2026
No.: 2,031
seedance-anime-action为 Seedance 2.0（Higgsfield）生成动漫风格视频提示。在用户想要动漫、日本动画风格、少年漫画动作、青年漫画戏剧、魔法少女、机甲、异世界、日常生活动漫或任何日本动画美学时使用。触发条件：动漫、日本动画、少年漫画、青年漫画、漫画风格视频、动漫格斗、动漫片头、动漫片尾、樱花、迷你人物、可爱风格、机甲、异世界，或任何动漫风格请求。即使是"让它看起来像动漫"或"日本卡通风格"。
Skill content language: Chinese
Repository: beshuaxian/higgsfield-seedance2-jineng
GitHub stars: 1,023Updated: Apr 9, 2026
No.: 2,032
uniapp移动端uniapp开发说明
Skill content language: Chinese
Repository: crmeb/CRMEB
GitHub stars: 9,458Updated: Mar 23, 2026
No.: 2,033
product-manager-toolkitComprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use for feature prioritization, user research synthesis, requirement documentation, and product strategy development.
Repository: davila7/claude-code-templates
GitHub stars: 33,139Updated: Dec 20, 2025
No.: 2,034
resume-formatterEnsure ATS-friendly formatting and create clean, scannable layouts. Use when the user mentions resume format, layout, template, design, or fixing formatting issues.
Repository: davila7/claude-code-templates
GitHub stars: 33,139Updated: May 16, 2026
No.: 2,035
world-book-skillCreate and manage SillyTavern Character Cards (角色卡) and World Books (世界书). Supports character card writing, world book creation, MVU ZOD variables, HTML beautification, opening scene writing, and card-generator.py integration. 支持角色卡编写、世界书创建、MVU ZOD 变量系统、HTML 前端美化、开场白创作、 card-generator.py 集成等多种场景。使用前先读取场景路由器和对应参考文件。
Skill content language: Chinese
Repository: echo-xianyu/worldbook-skill
GitHub stars: 218Updated: May 18, 2026
No.: 2,036
spine-animationCreate Spine 2D skeletal animations from pre-existing character assets (separated body-part PNGs, atlas spritesheet, or a full character image). Use this skill whenever the user wants to animate a 2D character, create Spine JSON from existing art assets, rig a character with bones, build walk/idle/run/attack animations, produce an interactive Spine Web Player preview, or generate Spine-compatible export files (.json + .atlas + .png). Also trigger when the user mentions "Spine animation", "2D rigging", "skeletal animation", "bone animation", "cutout animation", "animate this character", "make this walk", "create walk cycle", or uploads separated character body parts and wants them animated. This skill handles the full pipeline: asset analysis, skeleton rigging, animation keyframing, Spine JSON export, and interactive HTML5 preview.
Repository: GenielabsOpenSource/spine-animation-ai
GitHub stars: 629Updated: Aug 26, 2026
No.: 2,037
product-master产品摄影主控 - 自动生成产品摄影提示词，支持商业拍摄、电商图片等场景
Skill content language: Chinese
Repository: huangserva/skill-prompt-generator
GitHub stars: 1,519Updated: Jan 5, 2026
No.: 2,038
wewrite-rewriteWeWrite 多平台改写模块：把一篇公众号文章（或指定源稿）内容级真改写成其他平台版本，当前支持小红书（图文笔记）、抖音（口播脚本），检查编辑质量与源稿相似度。触发关键词：改写成小红书、小红书版、抖音版、口播稿、多平台分发、一稿多发、平台改写。不应被"翻译"、"缩写"、"换个标题"触发——那些是单平台编辑动作。
Skill content language: Chinese
Repository: imraywang/wewrite
GitHub stars: 3,643Updated: Jul 15, 2026
No.: 2,039
ergo-remotion-video把口播稿做成二哥风格的 Remotion 视频，包括整理视频用稿、火山 TTS 配音、音画对齐、逐章动画预览和导出带配音的 MP4。用户说“做视频”“口播稿转视频”“Remotion”“继续做下一章”“出片”“渲染”“改读音”“配音读错了”，或给出 docs/src/ai/video/ 下的稿子要做成视频时使用。共享工具、配置和素材在 docs/src/ai/script/shared/，每条视频按主题在 docs/src/ai/script/ 下独立保存。
Skill content language: Chinese
Repository: itwanger/toBeBetterJavaer
GitHub stars: 17,826Updated: Nov 5, 2026
No.: 2,040
xianyu-service-opsOperational playbook for selling virtual services on 闲鱼 (Xianyu). Use proactively whenever the user mentions '闲鱼', 'Xianyu', '闲鱼副业', '闲鱼卖服务', '闲鱼上架', '闲鱼标题', '闲鱼运营', '闲鱼流量', '闲鱼账号', '闲鱼推广', or wants to start/grow a service-based side hustle on a Chinese consumer marketplace. Covers the full ops stack: keyword research, listing creation (title × 3, pricing, description copy, main-image brief), listing diagnosis, account health, competitor teardown, and compliance. Always use this skill — not general advice — when the context is Xianyu service selling.
Repository: LeoYeAI/openclaw-master-skills
GitHub stars: 2,169Updated: Jun 29, 2026
No.: 2,041
inkos-story-cover根据作品、平台与用户视觉要求设计或生成封面。Use for story-cover direction and confirmed cover generation.
Repository: Narcooo/inkos
GitHub stars: 11,010Updated: Sep 25, 2026
No.: 2,042
replit-deckFor product and technical management work: turn PRDs, roadmaps, RFCs, architecture reviews, and retros into decision documents. Built around the core query "pm-feature-business-case-deck", with product strategy lead judgment, buyer-ready proof, and this outcome: approve the feature, architecture, roadmap, or incident follow-up.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Jul 31, 2026
No.: 2,043
magazine-posterAn editorial-style poster — newsprint paper, dateline, oversized serif headline with a struck-through word and italic accent, a 2-column body block, and 6 numbered sections with annotated pull-quote captions. Reads like a Sunday-paper full-page essay or a thoughtful launch poster. Use when the brief asks for "magazine poster", "editorial poster", "newsprint", "essay layout", or "manifesto".
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 2,044
release-openclaw-plugin-testingPlan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E, Package Acceptance, and Testbox proof.
Repository: openclaw/openclaw
GitHub stars: 393,741Updated: Aug 16, 2026
No.: 2,045
feynman-learningTurn any concept, lesson, slide deck, or source material into a Feynman learning cycle in which learners explain first, expose the smallest gap, rebuild the explanation through Socratic prompts, strip jargon, stress-test analogies, and transfer the idea to a new context. Use when the user asks for teach-back, learning by explaining, or a Feynman-style classroom. Do not use when the Feynman technique itself is merely the lesson topic or when study strategy should remain a parallel goal.
Skill content language: Chinese
Repository: THU-MAIC/OpenMAIC
GitHub stars: 42,718Updated: Aug 27, 2026
No.: 2,046
video-talkcraft终极口播视频 skill：中文口播稿 + 成品配音 → CPU 字级时间戳 → SHOTBOOK 层矩阵分镜 → Remotion 电影感成片（横屏默认/竖屏）。当用户要"做口播视频"、"解说/科普视频"、"把文案变成视频"、"给配音配画面动效"时使用。默认使用成品配音，可选 Fish Audio 从稿子合成配音与时间戳；数字人生成技术不在本 skill 内（人物素材是输入）。含统一视觉语言（Apple 范式）、108 张动效配方卡、镜头三面分层工作单、七层镜头反PPT系统（极缓推拉相机/让位，运动做减法）、六式运动承接转场（每式一卡）、长镜头世界画布、anime.js+three.js 桥、自动静止检测 + 独立 subagent 评估循环。
Skill content language: Chinese
Repository: Vincentwei1021/video-talkcraft
GitHub stars: 2,109Updated: Oct 12, 2026
No.: 2,047
cocos-mini-game策划、开发或修改 Cocos Creator 3.8+ 的 2D 微信与抖音小游戏。按请求处理玩法、PRD、广告接入或具体开发任务；仅在用户要求完整新项目时推进全流程。
Skill content language: Chinese
Repository: xiongxianzhu/xskills
GitHub stars: 0Updated: Sep 14, 2026
No.: 2,048
autoresearchStateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior
Repository: Yeachan-Heo/oh-my-claudecode
GitHub stars: 40,602Updated: Oct 20, 2026
No.: 2,049
frontend-slidesCreate stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
Repository: zarazhangrui/frontend-slides
GitHub stars: 31,929Updated: Jun 23, 2026
No.: 2,050
energy-procurement電気とガス調達、料金最適化、需要料金管理、再生可能エネルギーPPA評価、およびマルチファシリティーエネルギー戦略のための符号化された専門知識。 Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis, hedging strategies, load profiling, and sustainability reporting frameworks. Use when procuring energy, optimizing tariffs, managing demand charges, evaluating PPAs, or developing energy strategies.
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Oct 1, 2026
No.: 2,051
git-workflowGit工作流模式，包括分支策略、提交约定、合并与变基、冲突解决以及适用于各种规模团队的协作开发最佳实践。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: May 11, 2026
No.: 2,052
nestjs-patternsNestJS 架构模式，涵盖模块、控制器、提供者、DTO 验证、守卫、拦截器、配置以及生产级 TypeScript 后端。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: May 11, 2026
No.: 2,053
file-reader仅用于读取和总结文本类文件。文本格式优先使用 read_file；需要做类型探测时使用 execute_shell_command。PDF、Office、图片和压缩包由其他技能处理。
Skill content language: Chinese
Repository: agentscope-ai/QwenPaw
GitHub stars: 37,390Updated: Apr 20, 2026
No.: 2,054
spiceRun automatic SPICE simulations on subcircuits detected from KiCad schematic analysis — validates filter frequencies, divider ratios, opamp gains, LC resonance, and crystal load capacitance. Supports ngspice, LTspice, and Xyce (auto-detected). Generates testbenches, runs batch mode, produces structured pass/warn/fail report. Use when the user asks to simulate, verify, or validate any analog subcircuit — RC filters, LC filters, voltage dividers, opamp circuits, crystal oscillators. Also for "simulate my circuit", "run spice", "verify with simulation", "check my filter cutoff", "does this divider give the right voltage", "what's the bandwidth of this opamp stage". Consider suggesting simulation during design reviews when the schematic analyzer reports simulatable subcircuits and a SPICE simulator is available.
Repository: aklofas/kicad-happy
GitHub stars: 1,589Updated: Oct 25, 2026
No.: 2,055
litreviewUse when starting a literature review or a literature-based project. Plans the search (PICO, SPIDER) with framework_recommender.py, searches PubMed and OpenAlex with free_search.py and writes a .docx orientation guide. Single-paper lookups: query directly.
Repository: alirezarezvani/claude-skills
GitHub stars: 29,341Updated: Oct 31, 2026
No.: 2,056
krea2-txt2imgBuild Krea 2 Turbo txt2img workflows with the native krea2 CLIPLoader, Qwen3-VL encoder, Qwen image VAE, 8-step turbo settings, and Ideogram-style JSON prompting
Repository: artokun/comfyui-mcp
GitHub stars: 879Updated: Aug 25, 2026
No.: 2,057
paper-submissionEvaluate a paper's contribution novelty, identify best-fit SSCI journal fields and ABS star rating, and recommend 20 target journals. Trigger when user says "paper submission" / "paper-submission" / "投稿评估" / "期刊推荐" / "target journal" / "选刊".
Repository: brycewang-stanford/Auto-Empirical-Research-Skills
GitHub stars: 4,912Updated: Jul 19, 2026
No.: 2,058
doubao-ttsGenerate Mandarin and multilingual narration with Volcengine Doubao Speech 2.0. Use when creating Chinese voiceovers, when the user prefers Doubao/Volcengine/火山引擎/豆包 TTS, or when narration needs character-level timestamp metadata for subtitles.
Repository: calesthio/OpenMontage
GitHub stars: 76,985Updated: May 4, 2026
No.: 2,059
generative-paintingMake hand-painted-looking generative paintings and short art films in code, in a chosen painting style — watercolour (translucent glazes, graphite and ink on paper, the "Beautiful Collisions" look), pointillism (Seurat-style divided-colour dots), charcoal with red conté, graphite or pen-and-ink sketch, woodcut / linocut print, or 2D cel animation — or several mixed plate by plate, with hard-cut collision editing, deterministic particle motion, a soft code-generated score, and a self-contained runnable engine (p5 + p5.brush + Vite + Playwright + ffmpeg) that exports lossless plates, MP4s, a WAV and automated checks. Also covers 16:9 1080p films, fixed-anchor on-screen text and pixel characters, repainting an existing film in another style with provably identical geometry, and adding brand-new painting styles. Use it whenever someone wants a painted or illustrated video, reel, loop, montage, launch film, animated artwork or generative painting of any subject (flowers, ocean, birds, cities, a product…), mentions
Repository: debuu0007/generative-painting-skills
GitHub stars: 3Updated: Sep 28, 2026
No.: 2,060
industry-deep-explainer快速且通俗易懂地讲透一个行业，输出图文并茂的深度分析 Markdown 报告，保存到当前项目的 markdown/ 目录。触发条件：用户输入一个行业名称，并希望获得全面、通俗易懂的行业深度分析，关键词包括"讲透"、"深度分析行业"、"行业分析"、"帮我搞懂XX行业"、"XX行业是怎么赚钱的"、"XX行业有什么机会"、"XX行业怎么进入"、"产业链分析"、"行业机会"等。即使用户只说"帮我了解一下XX行业"或"XX行业值得进入吗"，也应使用本 skill。输出报告覆盖：产业链分布与利润图谱、供给-需求-连接分析、人货场分析、代表企业与产品分析、产业链不合理之处、机会推演与进入策略（产品/服务/目标客户/商业模式/定价/市场规模）、竞争对手与合作伙伴分析，要求逻辑清晰、有理论依据、有历史数据/事件支撑、图文并茂（SVG/Mermaid/ASCII图）。
Skill content language: Chinese
Repository: digoal/blog
GitHub stars: 8,604Updated: Jun 8, 2026
No.: 2,061
wps-pptWPS 演示智能助手，通过自然语言操控 PPT，解决排版美化、内容生成、动画设置等痛点问题
Skill content language: Chinese
Repository: lc2panda/wps-skills
GitHub stars: 675Updated: Jun 17, 2026
No.: 2,062
vue-best-practicesMUST be used for Vue.js tasks. Strongly recommends Composition API with `<script setup>` and TypeScript as the standard approach. Covers Vue 3, SSR, Volar, vue-tsc. Load for any Vue, .vue files, Vue Router, Pinia, or Vite with Vue work. ALWAYS use Composition API unless the project explicitly requires Options API.
Repository: moeru-ai/airi
GitHub stars: 51,123Updated: Aug 5, 2026
No.: 2,063
football-betting-prediction竞彩足球 / 体彩混合过关的赛事预测与出单方案设计，以及赛前临场复核、赛果回填与复盘。适用于胜平负/让球/比分/总进球/半全场及串关组合分析；含数据源停摆降级预案、负期望资金纪律与防编造铁律。 Triggers: "预测足彩", "竞彩", "足球预测", "足球比赛结果", "胜平负", "让球", "比分预测", "总进球", "半全场", "串关", "过关", "胆材", "混合过关", "投注方案", "临场复核", "出票前确认", "sporttery", "体彩".
Skill content language: Chinese
Repository: MrZhangShenSheng/football
GitHub stars: 0Updated: Oct 13, 2026
No.: 2,064
context-compressionThis skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve decisions, files, risks, and next actions.
Repository: muratcankoylan/Agent-Skills-for-Context-Engineering
GitHub stars: 18,306Updated: Oct 1, 2026
No.: 2,065
expert-wx-channel微信视频号账号运营专家。承接定位起号、内容 DNA、选题与短标题/视频描述包装、已有素材轻加工、视频全案 Brief 与口播文案、发布与数据复盘；全片制作委托 content-producer。
Skill content language: Chinese
Repository: TeamWiseFlow/xiaobei
GitHub stars: 8,686Updated: Oct 27, 2026
No.: 2,066
z-video-downloader当用户给出视频链接、链接清单或 z-web-pack 的 04-media-inventory.md，并要求"下载视频""视频下载""帮我把这个视频下下来""下载 YouTube 视频""下载 B站/哔哩哔哩视频""下载 m3u8/mp4 直链""把视频保存到本地""批量下载这些视频""下载字幕""下载视频号""视频号下载"时必须使用。本 skill 支持单个、多个、文本清单和媒体清单输入，覆盖 YouTube、Bilibili、Vimeo、X/Twitter、TikTok、抖音、Instagram、Facebook、微信视频号等 yt-dlp 平台及常见视频直链；支持断点续传、重试、字幕、封面和下载历史，保存到 Video/Downloads 并生成报告。
Skill content language: Chinese
Repository: tjxj/z-skills
GitHub stars: 592Updated: Jul 24, 2026
No.: 2,067
ios-icon-genSF Symbols（Apple ネイティブ 5,000 件以上）または Iconify API（200 以上のコレクションから 275,000 件以上のオープンソースアイコン）から Xcode アセットカタログ用の PNG イメージセットとして iOS アプリアイコンを生成します。アイコンの生成、アイコンアセットの作成、アセットカタログへのアイコン追加、または iOS プロジェクト向けアイコンの検索を行う際に使用します。
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: May 17, 2026
No.: 2,068
skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Repository: bytedance/deer-flow
GitHub stars: 85,028Updated: Oct 30, 2026
No.: 2,069
tvc-directorTVC advertising creative director skill for Nano Banana Pro keyframe prompts and Seedance video scripts. Specialized for television commercials and brand advertising — from a product brief to production-ready keyframe prompts and cinematic video scripts. Three core capabilities: (1) Cinematic Product Breakdown — multi-phase product micro-films with precise camera choreography, component disassembly animations, feature visualization, and material macro shots; (2) Brand World Crosscut — interweaving product close-ups with in-context usage scenes via match cuts between phases (outdoor cameras with skydiving/skiing, luxury cars with mountain roads); (3) Lifestyle Film — product stays in the brand world throughout (worn/held/carried), highlighted through cinematography rather than studio cutaways, ideal for wearables and lifestyle products. Covers TVC narrative models, product cinematography, brand world integration, multi-grid storyboards, and video prompts. Use this skill whenever users want to create TVC ads, p
Skill content language: Chinese
Repository: Ethanxwang/tvc-director
GitHub stars: 344Updated: Apr 18, 2026
No.: 2,070
deep-reading书/长文/研报/论文的深度消化，产出结构笔记+原子笔记+知识网络连接。关键词：深度阅读、深度学习、结构笔记、deep learning。
Skill content language: Chinese
Repository: LeoYeAI/openclaw-master-skills
GitHub stars: 2,169Updated: Jun 15, 2026
No.: 2,071
rf-circuit-design提供射频电路设计与调试的专业指导。当用户询问射频电路原理图设计、PCB布局、阻抗匹配、调试技巧等问题时调用。
Skill content language: Chinese
Repository: LeoYeAI/openclaw-master-skills
GitHub stars: 2,169Updated: May 5, 2026
No.: 2,072
dashboardAdmin / analytics dashboard in a single HTML file. Fixed left sidebar, top bar with user/search, main grid of KPI cards and one or two charts. Use when the brief asks for a "dashboard", "admin", "analytics", or "control panel" screen.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Jul 27, 2026
No.: 2,073
figma-generate-designBuild or update screens in Figma from code or description using design system components. Translate app pages into Figma using design tokens.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 2,074
cumcm-step-review数学建模国赛（CUMCM/全国大学生数学建模竞赛）分步审核工作流。当用户要求做数学建模国赛题目、完整建模、建模分析、代码求解、结果可视化、生成数学建模论文、写 AI 工具使用声明/AI 使用报告时使用，且需要分步推进、先审核思路与算法再写代码、每个部分写入论文草稿供审核。按'问题重述→数据预处理→逐问建模与求解→模型分析与检验→模型评价与推广→参考文献→附录→问题分析→模型假设→符号说明→摘要'逐步完成：每部分先给出分析与候选方案，用户审核通过后编写代码，并把该部分写入 Word 论文草稿再次供用户审核；全部定稿后按国赛 AI 使用规范生成 AI 工具使用声明与 `AI工具使用详情.pdf`；保留建模约束、工具链、算法库与最终验收。
Skill content language: Chinese
Repository: yuanchen-home/cumcm-step-review
GitHub stars: 316Updated: Sep 4, 2026
No.: 2,075
ponytail强制使用最懒惰、最简单、最短、最最小的解决方案。引导一位见多识广的高级开发人员：质疑任务是否需要存在（YAGNI），在自定义代码之前访问标准库，在依赖关系之前访问本机平台功能，在五十行之前访问一行。支持强度级别：低、全（默认）、超。用于任何编码任务：编写、添加、重构、修复、审查或设计代码，以及选择库或依赖项。每当用户说“马尾辫”、“懒惰”、“懒散模式”、“最简单的解决方案”、“最小解决方案”，“yagni”、“少做”或“最短路径”，或者抱怨过度工程、臃肿、样板或不必要的依赖关系时，也可以使用。请勿用于非编码请求（常识、散文、翻译、摘要、食谱）。
Repository: zzz2929/skills-zh-CN
GitHub stars: 0Updated: Sep 2, 2026
No.: 2,076
econ-writeExpert economics paper writing assistant synthesizing advice from 50+ top guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Glaeser, Kremer, and other leading economists. USE THIS SKILL whenever the user writes, edits, reviews, rewrites, or structures any economics paper, thesis, job market paper, abstract, introduction, conclusion, results section, literature review, or referee response. Also handles LaTeX formatting, presentations, and paper audits. Covers all paper types (applied, theory, structural, mixed) and all sections.
Repository: brycewang-stanford/Auto-Empirical-Research-Skills
GitHub stars: 4,912Updated: Jun 3, 2026
No.: 2,077
binance-agentic-walletUse when the user mentions connect/disconnect wallet, sign in, sign out, web3 wallet, wallet address, check balance, how much crypto do I have, send BNB/USDT/crypto, transfer tokens, swap tokens, buy/sell token, DEX trade, limit order, market order, cancel order, get a quote, transaction history, wallet settings, daily limit, slippage, MEV protection, supported chains, available networks, prediction market, predict.fun, YES/NO market, place a prediction, redeem winnings, claim payout, prediction portfolio, prediction PnL, x402 payment, HTTP 402 Payment Required, pay a known x402 API, check approvals, view token approvals, revoke approval, manage approvals, wallet approvals, authorization management, token authorization, DeFi protocols, DeFi position, DeFi portfolio, staking, liquidity pool, LP, yield farming, health factor, APY, TVL, DeFi investment, DeFi deposit, DeFi redeem, DeFi stake, DeFi unstake, add liquidity, remove liquidity, claim rewards, claim fees, or any on-chain wallet operation.
Repository: ccxt/ccxt
GitHub stars: 44,750Updated: Jul 13, 2026
No.: 2,078
emil-design-engThis skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
Repository: emilkowalski/skills
GitHub stars: 53,688Updated: Nov 2, 2026
No.: 2,079
cic-can-0714Wenn es um CIC can. 714 - Buch II - Volk Gottes in Römisch-katholisches Kirchenrecht CIC und Katechismus geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten Schritt; liefert ein direkt nutzbares Arbeitsprodukt mit Prüfpunkten, Risiken und nächstem Schritt.
Skill content language: German
Repository: Klotzkette/claude-fuer-deutsches-recht
GitHub stars: 1,428Updated: Jul 1, 2026
No.: 2,080
llm-councilQuery multiple LLM models in parallel from CodeAct and cross-reference their responses
Repository: nearai/ironclaw
GitHub stars: 12,714Updated: Aug 19, 2026
No.: 2,081
seedance-director将任意一句想法（故事、人物、图片、场景、历史事件、电影桥段、广告、旅行、科幻、动作、情感、纪录片）重构为可直接投喂 Seedance 2.5 的 30 秒电影级视频提示词，包含五幕结构、七维分镜、一致性锁定、物理与微表情校正、声音设计。当用户要求写视频提示词、分镜脚本、AI 短剧脚本、Seedance/即梦视频 prompt、电影感镜头设计，或提到「分镜」「运镜」「视频脚本」「AI 短片」「30 秒视频」时使用。Generates 30-second cinematic video prompts and shot lists for Seedance 2.5 and other AI video models.
Skill content language: Chinese
Repository: sundny8/ai-visual-skills
GitHub stars: 2Updated: Sep 11, 2026
No.: 2,082
photo-perler-charmWibi Style 官方视觉风格：把一张照片转换成照片拼豆挂件。适合人物、宠物、花束、食物和轮廓清晰的物件照片。适用于用户要求照片拼豆挂件，或明确调用 $photo-perler-charm 时。
Skill content language: Chinese
Repository: Vieeeeeee/wibi-style
GitHub stars: 182Updated: Oct 10, 2026
No.: 2,083
cad-boq-pipelineCAD-BOQ 全流程工作流：识图→审图→算量→编清单→组价。内置辽宁24定额(29,839条,零重复主键)和国标24清单(3,734条真实名称)数据库。支持5个专业：房屋建筑与装饰/安装/市政/园林绿化/钢结构。工程性质感知(新建/改造)、构件级建模、规范知识库审查、数据可信度卡口(防编造)、视觉交叉验证(v6.5起视觉永不覆盖几何,纯质检)、依赖健康自检。 v6.10.8：达尔文 skill 自优化（9 维 rubric + paired 3-judge 多数决，4 轮全 keep）——补「失败模式与降级路径」/ 4 个 🔴 检查点 / 五步流水线输入→输出 / 定额四步链含「换」/ 项目内规则索引； v6.10.7：图纸理解突破 — 视觉分块瓦片识别(真实A0图文字召回33.5倍)+像素密度自适应判定； DXF扩展实体六类(MLINE多线墙/SPLINE/HATCH/LEADER引线/TABLE真表格/天正PROXY检测)； PDF·图片输入通道；转换失败分级诊断+输出DXF版本可配；知识库扩充(125条带来源分级)。 v6.9.8：22项计划收尾(复核结论聚合/疑问影响金额/材料档位/16G101锚固规则库/组合规则动态含量)； v6.8：造价师思维双层固化(PRINCIPLES五元原则+全专业5维知识库)； v6.5：识图策略重构(视觉永不覆盖几何/改造范围掩码)； v6.2：设计说明专项解析(材料规格/做法层次/施工范围/工程概况)；v6.1：措施规则+房间分区； v6.0：构件扣减/门窗表/配线/栅格图结构化； v5.19：主材价格库(真实价优先)；v5.18：两段式调用(仅Excel输出)。完整说明见说明文档.md（整合 v4.0~v6.9.8 全部迭代）。
Skill content language: Chinese
Repository: xuebipaocha/cad-boq-pipeline
GitHub stars: 2Updated: Oct 16, 2026
No.: 2,084
cute-claude-hooks为 Claude Code 提供完整的中文体验！包含工具提示、界面汉化、完整的自定义指南、实战经验和进阶开发教程, 让用户能够根据自己的需求修改和完善.
Skill content language: Chinese
Repository: gugug168/cute-claude-hooks
GitHub stars: 205Updated: Aug 15, 2026
No.: 2,085
aspnet-coreBuild, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.
Repository: openai/skills
GitHub stars: 28,536Updated: Mar 4, 2026
No.: 2,086
maintain-model-listMaintain the supported LLM model list: add a new model, or run routine maintenance to verify availability and discover new models worth adding. Use when the user asks to add/support a model, update the model list, or check model availability.
Repository: alibaba/page-agent
GitHub stars: 29,635Updated: Jul 17, 2026
No.: 2,087
pwaProgressive Web App rules for projects following the air-gapped, declarative-first architecture. Defines the manifest as the entry point and the architectural reasoning for defaulting to PWA. Use whenever a project starts (defaulting to PWA is non-negotiable), or when configuring manifest, service-worker scope, or install behavior.
Repository: Autocss-com/ai
GitHub stars: 1Updated: Sep 4, 2026
No.: 2,088
job-apply中文求职申请自动填写技能：使用浏览器读取用户确认的简历资料，逐项填写招聘网站申请表并核对结果；当用户输入“/job-apply”、要求自动填简历或填写求职申请时使用。
Skill content language: Chinese
Repository: Hisn00w/ASu-skills
GitHub stars: 6,238Updated: Sep 3, 2026
No.: 2,089
novel-creation-omnibus小说创作全能工坊v10.0——46套工具，从0到完本一条龙。覆盖：长篇正文写作、大纲细纲规划、世界观搭建与人物塑造、短篇故事、虐心BE发刀、玩梗热梗、去AI味反套话（含Claude/DeepSeek/GPT/Qwen/Kimi/豆包各策略+DeepSeek句式黑名单734条+51意象词+白名单系统+L1-L4四层硬门禁+L3方法论三节+6类逐句审查判据+段落功能二分法）、衔接修复与因果分析、状态追踪与伏笔管理、质量门控、同人创作与OOC控制、网文生产流水线、番茄爆文与系统流爽文、白描克制与现实主义平庸、模型适配优化、通感痛觉描写、规则怪谈、无限流、直播文、末世废土、悬疑推理、种田日常、细节真实感体系（五感/口语化/小动作/食物/环境）、对话写作大师（潜台词/声线/群像/吵架表白告别专项+MBTI 16型对白声线档案+4气质组对照+群戏冲突设计+MBTI情绪表达契合）、开篇钩子工坊（12种爆款开篇/300字生死线/章末钩子库）、情节工程（番茄循环/反转7式/冲突6级/节奏曲线+Dramatica 11拍节拍结构+钩子真假4维判定+伪因果5大典型+节拍×伏笔×角色协同矩阵+章末钩子4型）、读者心理学（代入感/爽点/虐点/弃书TOP10对策）、场景写作（场景四要素/6大类型/进出衔接技巧）、人物弧光（正向弧7阶段/负向弧/关系弧）、长篇连载管理（存稿策略/断更恢复/读者留存）、平台写作规则（起点/飞卢/晋江三大平台写作标准+签约门槛+跨平台改编）、情绪高潮设计（燃/泪/甜/震四类高潮+七步结构+长篇规划+语言温度词库8类热词+冷词库+温度递进原则+MBTI契合）、灵感生成器（8种灵感生成法+人物公式+30个情节模板+灵感仓库管理）、字数统计工具（scripts/word-count-tool.py）。+v5.9新增：描写技法/多线叙事/节奏动力学/世界体系/修改工作流/副线编织法/氛围渲染术/市场战略。+v6.0集成：审计工作流（五专家面板E1-E5/11维评估/6阶段流程/交叉审计CC1-CC6/跨会话状态机）、伏笔库5态状态机、16维事实快照、8类CT一致性检查、Dramatica节拍系统。+v6.1强化：去AI味L1-L4四层硬门禁+L3方法论三节+6类逐句审查判据+段落功能二分法；剧情设计新增钩子真假4维判定+伪因果5大典型+节拍×伏笔×角色协同矩阵+章末钩子4型；上下文流程新增三库协同+5态伏笔状态机详细迁移
Skill content language: Chinese
Repository: limingnanyue/novel-creation-omnibus
GitHub stars: 9Updated: Jul 25, 2026
No.: 2,090
commodity-analysisCommodity analysis (oil supply-demand balance / gold pricing / copper as an economic predictor / inventory cycles / futures premium-discount structure / seasonality), generating directional commodity signals.
Repository: HKUDS/Vibe-Trading
GitHub stars: 37,696Updated: Apr 9, 2026
No.: 2,091
game-dev-workflow游戏开发流程引导技能（策划阶段）。**强前置：仅当工作区根目录已存在 project.godot 且 godot-editor/ 已包含 Godot*.exe 时才可激活**。引导用户按「策划 → 开发 → 测试」顺序完成游戏。如果工作区是空的、或缺少 project.godot / 缺少 Godot 编辑器， **绝对不要启动本技能**，必须先调用 godot-setup（或走 project-init 路由）完成环境装配，环境就绪后再进入策划。仅当明确说"开始策划""生成策划文档""设计 XX 系统" "完善玩法"等明确调起策划阶段的场景下才调用。
Skill content language: Chinese
Repository: infometa/workbuddyskills
GitHub stars: 407Updated: Jul 21, 2026
No.: 2,092
otelOpenTelemetry guidance for VS Code agent experiences. Use when changing Agent Host telemetry, local Copilot Chat telemetry, provider-native spans or metrics, OTel settings and managed policy, trace persistence/export, or monitoring documentation.
Repository: microsoft/vscode
GitHub stars: 194,693Updated: Nov 2, 2026
No.: 2,093
headless-captureCapture screenshots/recordings of desktop or web apps for visual verification. Works across Linux, macOS, and Windows. Supports Tauri, Electron, native desktop apps (via Xvfb/screencapture/gdigrab), and web apps (via Playwright). Use proactively after UI changes so the human can verify without running the app locally.
Repository: binhonglee/headless_visual_demo_skill
GitHub stars: 3Updated: Jun 22, 2026
No.: 2,094
math-modeling-contest-route-selectionSelect superior mathematical modeling contest problems and modeling-solution routes for CUMCM A/B/C, MCM, ICM, and similar contests. Use when comparing contest topics, choosing modeling methods, distilling award-paper per-subquestion modeling/solving logic, auditing AI-generated topic choices, evaluating engineering feasibility, designing baseline-main-validation-refutation model stacks, or proving why one problem/method route is more executable and paper-worthy than alternatives.
Repository: y3519712124-ui/math-modeling-contest-route-selection
GitHub stars: 92Updated: Jun 19, 2026
No.: 2,095
interactive-fiction可选项驱动的互动小说创作完整规范：支持穿越/自创/创世/随机开局，内置视角一致性、字数区间、选项机制、存档系统与角色卡体系。当用户想玩、想写互动小说，或说「加载小说包」「开个互动小说」「选项小说」「互动故事」时使用。
Skill content language: Chinese
Repository: Treasure-hub-agent/interactive-fiction-skill
GitHub stars: 37Updated: Oct 18, 2026
No.: 2,096
docker-patternsPatrones de Docker y Docker Compose para desarrollo local, seguridad de contenedores, networking, estrategias de volúmenes y orquestación de múltiples servicios.
Skill content language: Spanish
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Jun 7, 2026
No.: 2,097
benchmark-methodologyScore a scoped competitor set into comparable profile cards: nine weighted dimensions (positioning, voice, visual craft, offer packaging, evidence, enterprise-readiness, thought leadership, pricing, client tension) with 1-5 evidence-anchored rubrics and a tension 2x2 plot. Use when benchmarking or scoring competitors, building a competitive comparison matrix, or grading rival positioning before assembling the report; runs after competitive-platform-analysis and before competitive-report-structure.
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Sep 27, 2026
No.: 2,098
cherry-browserControl the user's visible Agent browser: navigate, click, type, screenshot, debug. Needs the Browser setting.
Repository: CherryHQ/cherry-studio
GitHub stars: 53,284Updated: Oct 20, 2026
No.: 2,099
find-gapsAdversarially review an existing written artifact — stories, plans, acceptance criteria, specs, or design mocks — to surface missing states, unhandled edge cases, unstated assumptions, unverifiable criteria, and slices still too broad or horizontal. Works interactively, one question at a time, writing each answer back into the artifact as a new acceptance criterion, plan update, or mock-state spec. Use when an artifact needs tightening before planning or coding ("what's missing?", "poke holes in this", "tighten this up"). Requires an artifact to inspect — for a fuzzy decision tree with no artifact yet, use specification or an installed grill-me skill; for splitting oversized work, see story-splitting.
Repository: citypaul/.dotfiles
GitHub stars: 759Updated: Aug 9, 2026
No.: 2,100
llm-wiki个人知识库构建系统（基于 Karpathy llm-wiki 方法论）。让 AI 持续构建和维护你的知识库，支持多种素材源（网页、推特、公众号、小红书、知乎、YouTube、PDF、本地文件），自动整理为结构化的 wiki。触发条件：用户明确提到"知识库"、"wiki"、"llm-wiki"，或要求对已初始化的知识库执行消化、查询、健康检查等操作。不要在用户只是要求"总结这篇文章"时触发——必须是明确的知识库相关意图。
Skill content language: Chinese
Repository: sdyckjq-lab/llm-wiki-skill
GitHub stars: 2,578Updated: Jul 27, 2026