Annuaire Agent Skills

Index des Agent Skills, page 23

Parcourez cet index de skills publiques ou utilisez la recherche pour accéder à toute la bibliothèque.

Ouvrir la recherche

N°: 2 201
animation-vocabularyReverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.
Langue du contenu du Skill : anglais
Dépôt: emilkowalski/skills
Étoiles GitHub: 56 198Mis à jour: 15 sept. 2026
N°: 2 202
cumcm-live-workflowCUMCM（全国大学生数学建模竞赛）真题全流程实战手册。用于完整打一场数模竞赛（环境准备→读题自查→建模出图→LaTeX论文→交叉审阅→填表→AI自查表终审→清理打包），内含题意理解红线、数值严谨性守则、去AIGC特征清单、写作规范、LaTeX编号与图表规范、2026 AI合规与终审核查框架。触发于用户开始完整做真题、备赛训练、即将正式参赛，或要求按AI自查表对成品论文终审整改。**启动关键词**：国赛、数学建模竞赛、真题全流程、按竞赛标准走完流程、备赛、环境检查/检查环境/准备环境、按自查表审查——命中任一即启动，启用后第一步自动执行环境检查。
Langue du contenu du Skill : chinois
Dépôt: haoxilin/cumcm-live-workflow-skill
Étoiles GitHub: 186Mis à jour: 7 sept. 2026
N°: 2 203
ad-image-createCreate ad-ready product images (single or collage) by back-solving sub-image sizes from target output ratio, grounding scene design with media_comprehension, generating images via image_generator with strict request params and actor-count control, and pairing each deliverable with a short social tagline for 小红书/抖音.
Langue du contenu du Skill : anglais
Dépôt: inclusionAI/AWorld
Étoiles GitHub: 1 246Mis à jour: 15 sept. 2026
N°: 2 204
dropshipping-product-researchProduct research for dropshipping businesses. Identify profitable products with reliable suppliers, healthy margins, and manageable competition. Evaluates shipping times, return risk, and marketing viability.
Langue du contenu du Skill : anglais
Dépôt: nexscope-ai/eCommerce-Skills
Étoiles GitHub: 1 391Mis à jour: 9 avr. 2026
N°: 2 205
html-ppt-retro-quarterly-reviewRetro Quarterly Review presentation template in a bold blue + orange editorial language. Use when users ask for a high-impact quarterly review / roadmap deck with heavyweight slab headlines, clean cream paper sections, structured grids, and fast premium motion pacing (3 slides, each hold under 3s in video mode).
Langue du contenu du Skill : anglais
Dépôt: nexu-io/open-design
Étoiles GitHub: 107 245Mis à jour: 9 mai 2026
N°: 2 206
see使用外部视觉服务或本地 OCR 分析本地图片、截图、视频及明确提供的媒体 URL，输出 Markdown。用户明确要求 see，或当前主模型缺少完成媒体分析所需的视觉能力时使用。不拦截普通文本、任意 URL 或已有原生视觉可以直接完成的任务；不用于生图、编辑图片或自动操作屏幕。使用外部服务前说明发送的媒体与服务范围，无法识别时如实说明限制。
Langue du contenu du Skill : chinois
Dépôt: oil-oil/see-skill
Étoiles GitHub: 161Mis à jour: 10 sept. 2026
N°: 2 207
geo-sleuthGeolocate or chronolocate a photo with tool-verified reasoning (where was this taken / when was it taken / photo geolocation / geo-guessing). Given one or more photos, intake.py does metadata, OCR and reverse image search (Baidu/Yandex) in one command; clues and candidates go on a candidate board (board.py) that ranks them and gives the next step; clues.py looks up calling codes, driving side, plates and area codes from region packs; for satellite and street view the machine ranks first and you look only at the top few (CLIP in sat_scan.py, DINOv2+SIFT in match.py); plus sun and shadow math, OSM Overpass and DEM skylines. Every conclusion is checked against real data; output is coordinates + error radius, evidence images and tiered confidence. Use when the user shares a photo and asks where was this taken / geolocate this / when was this taken / 这是哪 / 在哪拍的 / 帮我定位这张照片 / 网络迷踪 / 图寻 / 几点拍的.
Langue du contenu du Skill : anglais
Dépôt: Oldcircle/geo-sleuth
Étoiles GitHub: 6 875Mis à jour: 9 nov. 2026
N°: 2 208
geospatial-and-cartographic-visualizationDesign geospatial and cartographic visualizations. Use when the user needs help deciding whether to use a map, choosing projections or basemaps, building choropleths or symbol maps, or implementing thematic maps, slippy maps, or geospatial interactions with D3 geo, Leaflet, MapLibre, Mapbox GL JS, Google Maps, OpenLayers, deck.gl, ArcGIS Maps SDK, Azure Maps, HERE Maps, CesiumJS, or related tools.
Langue du contenu du Skill : anglais
Dépôt: openai/plugins
Étoiles GitHub: 7 904Mis à jour: 26 mai 2026
N°: 2 209
fluwx-integration在 Flutter App 中接入微信 SDK 插件 fluwx / fluwx_no_pay（v6+）的完整指南：微信分享（会话/朋友圈/收藏）、微信登录（获取 auth code）、微信支付、拉起小程序、订阅消息、微信客服、H5 拉起 App，以及 Android / iOS / OpenHarmony 的平台配置与排错。只要在 Flutter 项目里涉及微信相关功能——分享到微信、微信授权登录、WeChat Pay、universal link、LSApplicationQueriesSchemes、errCode -1、无法拉起微信等——即使用户没有点名 fluwx，也应使用本 skill。
Langue du contenu du Skill : chinois
Dépôt: OpenFlutter/fluwx
Étoiles GitHub: 3 325Mis à jour: 4 août 2026
N°: 2 210
muapi-interior-designCreate professional interior design visualizations — redesign existing rooms, generate new room concepts, or visualize specific furniture styles in a space.
Langue du contenu du Skill : anglais
Dépôt: SamurAIGPT/Generative-Media-Skills
Étoiles GitHub: 33Mis à jour: 29 sept. 2026
N°: 2 211
expert-bd商务拓展与联络专家。承接潜客探索筛选、客户与合作方背景核验、评论回复、私信、邮件、点赞收藏关注、直播间互动、客户触达与联络记录。商业情报、竞对监控、直播调研及市场研究走 expert-osbi；公开资料按平台使用文中列出的采集技能或公共 smart-search，融资推进走 expert-ir。
Langue du contenu du Skill : chinois
Dépôt: TeamWiseFlow/xiaobei
Étoiles GitHub: 8 715Mis à jour: 8 nov. 2026
N°: 2 212
project-workbench-builder搭建或规范 MCU/嵌入式项目工作台，包括标准目录、项目记忆文件、源码分层、资料位置和归档规则。适用于新建 MCU 项目、整理混乱项目文件、补充 AI 可读取的项目记忆，或给老项目补建可维护结构时。
Langue du contenu du Skill : chinois
Dépôt: Tsaiguohua/mcu-ai-workflow-skills
Étoiles GitHub: 14Mis à jour: 5 juin 2026
N°: 2 213
cjournal-analyzerC刊（CSSCI来源期刊）论文全面分析工具。当用户提供一个具体的C刊期刊名称（如"管理世界"、 "社会学研究"、"经济研究"等）时，自动通过知网（CNKI）查询该期刊最近5年所有期次的文章目录、作者和摘要信息，并生成专业的Word分析报告。报告包含：选题热点趋势、高频关键词、研究方法偏好、核心作者群、栏目主题演变、研究空白识别、投稿方向建议等全维度分析。触发条件：用户提到需要分析某个C刊/CSSCI期刊/核心期刊的发文趋势、选题偏好、投稿方向；或提供中文学术期刊名称并要求查看近年发表论文的主题分布和趋势；或说"帮我分析一下XX期刊"。注意：本skill用于期刊层面的宏观分析，不同于paper-analyzer（单篇论文拆解）和 literature-review-writer（文献综述写作）。
Langue du contenu du Skill : chinois
Dépôt: yipng05-max/-skills
Étoiles GitHub: 324Mis à jour: 30 mars 2026
N°: 2 214
documentation-lookupUse up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
Langue du contenu du Skill : anglais
Dépôt: affaan-m/ECC
Étoiles GitHub: 301 144Mis à jour: 16 mars 2026
N°: 2 215
react-patternsReact 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
Langue du contenu du Skill : anglais
Dépôt: affaan-m/ECC
Étoiles GitHub: 301 144Mis à jour: 7 juin 2026
N°: 2 216
browser-visible当用户需要控制 browser 的浏览器启动方式时，使用本 skill。browser 默认由 Playwright 直接管理、不开放调试端口（需让其他本地工具附加时显式传 `cdp_port`）；`headed` 控制是否显示窗口，`private_mode` 保留用于兼容、不再改变默认行为，`browser_args` 传入额外的 Chromium 启动参数，`executable_path` 指定自定义浏览器可执行文件路径。
Langue du contenu du Skill : chinois
Dépôt: agentscope-ai/QwenPaw
Étoiles GitHub: 37 631Mis à jour: 30 juil. 2026
N°: 2 217
oracleStrategic technical advisor with two modes. Use for second opinions, architecture decisions, debugging, security analysis, and research. REPO MODE explores your codebase autonomously (finds gaps, reviews code, traces bugs). WEB MODE researches external info via @steipete/oracle CLI (current best practices, library comparisons, docs). Run both in parallel when comparing your implementation against current standards.
Langue du contenu du Skill : anglais
Dépôt: andreasasprou/agent-skills
Étoiles GitHub: 7Mis à jour: 22 févr. 2026
N°: 2 218
wxjava-api-contributor按 WxJava 的 Maven 多模块、Java 8、公共 API 兼容性和 TestNG 约定，为微信官方接口新增或维护 SDK 支持。适用于新增 Service API、请求响应 Bean、序列化、HTTP 实现、Starter 配置或回归测试时。
Langue du contenu du Skill : chinois
Dépôt: binarywang/WxJava
Étoiles GitHub: 33 196Mis à jour: 20 juil. 2026
N°: 2 219
unityIntegrate SpacetimeDB with Unity game projects. Use when building Unity clients with MonoBehaviour lifecycle, FrameTick, and PlayerPrefs token persistence.
Langue du contenu du Skill : anglais
Dépôt: clockworklabs/SpacetimeDB
Étoiles GitHub: 25 541Mis à jour: 4 nov. 2026
N°: 2 220
tailwindcss-developmentAlways invoke when the user's message includes 'tailwind' in any form. Also invoke for: building responsive grid layouts (multi-column card grids, product grids), flex/grid page structures (dashboards with sidebars, fixed topbars, mobile-toggle navs), styling UI components (cards, tables, navbars, pricing sections, forms, inputs, badges), adding dark mode variants, fixing spacing or typography, and Tailwind v3/v4 work. The core use case: writing or fixing Tailwind utility classes in HTML templates (Blade, JSX, Vue). Skip for backend PHP logic, database queries, API routes, JavaScript with no HTML/CSS component, CSS file audits, build tool configuration, and vanilla CSS.
Langue du contenu du Skill : anglais
Dépôt: coollabsio/coolify
Étoiles GitHub: 65 966Mis à jour: 1 oct. 2026
N°: 2 221
public-relationsWhen the user wants press and media coverage, or asks what to say to a reporter, whether a story is newsworthy, or how to handle a crisis: pitches, press releases, media lists, HARO, op-eds, podcast guest prep, newsjacking (public relations, not pull requests). For directories, see directory-submissions. For launches, see launch. For cold outreach to prospects, see cold-email.
Langue du contenu du Skill : anglais
Dépôt: coreyhaines31/marketingskills
Étoiles GitHub: 59 836Mis à jour: 9 nov. 2026
N°: 2 222
kai-lite-v2-9-5资深民商事诉讼律师基于要件审判方法与请求权基础分析法，融合20年诉讼经验和团队管理流程打造，支持民商事诉讼案件全流程处理。Lite版包含8个核心子技能模块：立项建档和文件管理、案情梳理和法律分析、起诉状写作、答辩状写作、证据目录制作、质证意见写作、代理意见写作、上诉状写作。配备10个案件类型要件库+220+案由请求权基础总览，适用于合同、侵权、物权、房产、公司股权、婚姻家庭继承、劳动合同、担保、知识产权、人格权等案件类型。
Langue du contenu du Skill : chinois
Dépôt: CSlawyer1985/legal-skillhub
Étoiles GitHub: 32Mis à jour: 4 août 2026
N°: 2 223
medchemMedicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.
Langue du contenu du Skill : anglais
Dépôt: davila7/claude-code-templates
Étoiles GitHub: 33 360Mis à jour: 20 déc. 2025
N°: 2 224
using-superpowersUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Langue du contenu du Skill : anglais
Dépôt: davila7/claude-code-templates
Étoiles GitHub: 33 360Mis à jour: 25 janv. 2026
N°: 2 225
academic-pptxUse this skill whenever the user wants to create or improve a presentation for an academic context — conference papers, seminar talks, thesis defenses, grant briefings, lab meetings, invited lectures, or any presentation where the audience will evaluate reasoning and evidence. Triggers include: 'conference talk', 'seminar slides', 'thesis defense', 'research presentation', 'academic deck', 'academic presentation'. Also triggers when the user asks to 'make slides' in combination with academic content (e.g., 'make slides for my paper on X', 'create a presentation for my dissertation defense', 'build a deck for my grant proposal'). This skill governs CONTENT and STRUCTURE decisions. For the technical work of creating or editing the .pptx file itself, also read the pptx SKILL.md.
Langue du contenu du Skill : anglais
Dépôt: Gabberflast/academic-pptx-skill
Étoiles GitHub: 1 509Mis à jour: 14 juil. 2026
N°: 2 226
power-platform-architectUse this skill when the user needs to transform business requirements, use case descriptions, or meeting transcripts into a technical Power Platform solution architecture, including component selection and Mermaid.js diagrams.
Langue du contenu du Skill : anglais
Dépôt: github/awesome-copilot
Étoiles GitHub: 41 059Mis à jour: 17 avr. 2026
N°: 2 227
technical-job-searchUse this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV/resume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.
Langue du contenu du Skill : anglais
Dépôt: github/awesome-copilot
Étoiles GitHub: 41 059Mis à jour: 22 juin 2026
N°: 2 228
video-directorCanonical entrypoint for every AI chat request that asks to make, generate, plan, or edit a video, including promotional films, ads, short videos, product videos, reference-image videos, image-to-video, first/last-frame transitions, storyboard/keyframes, character talking-head videos, 宣传片, 广告片, 短视频, 视频, 口播视频, 分镜图, 图片转视频, and 商品宣传片. Do not invoke cosyvoice-ssml or tts-director as the first response to a video request. This skill must draft a script and shot table, generate storyboard contact-sheet preview images through image.generate, ask the user to confirm the script plus storyboard together, and only then call video generation.
Langue du contenu du Skill : anglais
Dépôt: Jamailar/Beav
Étoiles GitHub: 2 372Mis à jour: 22 mai 2026
N°: 2 229
baoyu-image-genAI image generation with OpenAI GPT Image 2.5, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
Langue du contenu du Skill : anglais
Dépôt: JimLiu/baoyu-skills
Étoiles GitHub: 27 471Mis à jour: 1 nov. 2026
N°: 2 230
latex-postersCreates research posters in LaTeX using beamerposter, tikzposter, or baposter. Use for conference posters, academic presentations, multi-column scientific layouts, figure integration, typography, compilation, and PDF preflight.
Langue du contenu du Skill : anglais
Dépôt: K-Dense-AI/scientific-agent-skills
Étoiles GitHub: 56 867Mis à jour: 1 oct. 2026
N°: 2 231
statistical-powerCalculates sample sizes and statistical power for study planning. Applies when someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers closed-form power for t-tests, ANOVA, proportions, correlations, chi-square, and regression, plus simulation-based (Monte Carlo) power for complex designs — logistic/Poisson regression, mixed models, cluster-randomized trials, survival, and interactions. Also handles requests that only mention an effect size, alpha, or "80% power" without saying "power analysis" explicitly. For laying out the study (randomization, blocking, factorial/DOE, crossover, sequential designs) use experimental-design; for analyzing data already collected and reporting it use statistical-analysis.
Langue du contenu du Skill : anglais
Dépôt: K-Dense-AI/scientific-agent-skills
Étoiles GitHub: 56 867Mis à jour: 1 oct. 2026
N°: 2 232
modlensPlug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: <path>]` line, or inside a tag) and you cannot see that image's content, run this skill on it before any other approach: no self-built OCR, no PIL, no tesseract. Also triggers on pasted-image placeholders such as `[Image #1]` and `[Unsupported Image]`. If you can actually see the image, do not use this skill. When unsure, run `modlens guard` before the first read of a session: a deny verdict means the active model has native vision and must read the image itself. Runs the modlens CLI to convert the image into structured JSON evidence: every word transcribed, layout regions, semantics, visual clues. Also use when the user asks how to install, configure, or switch modlens providers (Gemini API key, OpenAI-compatible endpoints, Claude API or Claude Code CLI).
Langue du contenu du Skill : anglais
Dépôt: liustack/modlens
Étoiles GitHub: 4 924Mis à jour: 7 nov. 2026
N°: 2 233
code-reviewPerform a code review of the current session's changes. Use when the user requests a code review via the Run Code Review button in the Changes toolbar.
Langue du contenu du Skill : anglais
Dépôt: microsoft/vscode
Étoiles GitHub: 195 313Mis à jour: 10 juin 2026
N°: 2 234
polymarketQuery Polymarket: markets, prices, orderbooks, history.
Langue du contenu du Skill : anglais
Dépôt: NousResearch/hermes-agent
Étoiles GitHub: 262 813Mis à jour: 10 oct. 2026
N°: 2 235
sn-deepresearch-cli一键启用 SenseNova-Skills-DeepResearch，用于行业与市场研究、竞品分析、政策或技术调研、商业尽调、趋势分析、方案对比、事实核查，以及研究报告、白皮书等交付场景。用户提出深度研究、调研、调查、尽调、research/deepresearch，或任务需要跨来源取证、多维度比较和交叉验证时主动使用；Skill 会完成环境检查、SenseNova-Skills-DeepResearch 安装或升级、Harness 与 Search/Camofox 准备、参数确认、研究启动和 Web 进度提示。简单常识问答、单一来源整理和纯文字润色不使用。
Langue du contenu du Skill : chinois
Dépôt: OpenSenseNova/SenseNova-Skills
Étoiles GitHub: 6 070Mis à jour: 11 sept. 2026
N°: 2 236
math-model-selectorRoutes problems to appropriate mathematical frameworks using expert heuristics
Langue du contenu du Skill : anglais
Dépôt: parcadei/Continuous-Claude-v3
Étoiles GitHub: 3 950Mis à jour: 10 janv. 2026
N°: 2 237
humanizer-plRemoves AI-writing tells from Polish AND English text while preserving meaning and the author's voice. Use when asked to humanize, de-AI, de-slop or clean up AI-sounding text (post, email, draft, newsletter). Auto-detects language (PL/EN). Does NOT trigger for translation or general editing.
Langue du contenu du Skill : polonais
Dépôt: pielas-activy/humanizer-pl
Étoiles GitHub: 11Mis à jour: 15 juin 2026
N°: 2 238
sales-cs-manager对外销售客服（sales-cs crew）管理技能。负责启用（channel、workspace、业务知识）、复盘升级（客户反馈、话术与客服手册）以及主动跟进定时任务的开启、调整和停用；调度由 main 派 IT engineer 管理原生 Automations。sales-cs 不自行升级或管理系统调度。零散 channel 检查、反馈扫描也可直接做。不涉及商务获客（expert-bd）、投资人关系（expert-ir）、content-producer 启用（AGENTS.md crew 管理）。
Langue du contenu du Skill : chinois
Dépôt: TeamWiseFlow/xiaobei
Étoiles GitHub: 8 715Mis à jour: 18 oct. 2026
N°: 2 239
talking-head-cut口播类视频（口播/演讲/访谈/直播）的轻剪辑——ASR 转写拿逐字时间戳，去口气词/结巴/静音，或识别高光段剪成集锦。仅做基于人声的轻剪辑，不出脚本不烧字幕；纯画面类素材的集锦剪辑走 video-edit。
Langue du contenu du Skill : chinois
Dépôt: TeamWiseFlow/xiaobei
Étoiles GitHub: 8 715Mis à jour: 5 nov. 2026
N°: 2 240
backend-microservice-development编写 BK-CI 后端微服务代码时使用，例如新增 Resource、组织 API/Service/DAO 分层、依赖注入、服务归属判断和 Spring Boot 开发约定。当用户要做 Kotlin/Java 后端开发时优先使用。
Langue du contenu du Skill : chinois
Dépôt: TencentBlueKing/bk-ci
Étoiles GitHub: 2 535Mis à jour: 9 mai 2026
N°: 2 241
media-crawler-tiebaCollect Baidu Tieba thread and user evidence with MediaCrawler using keyword or bar discovery, exact thread detail, replies, and creator pages. Use for community pain-point, vocabulary, objection, topic, or user research with thread-context preservation.
Langue du contenu du Skill : anglais
Dépôt: tsingyuai/growth-lab
Étoiles GitHub: 1 972Mis à jour: 28 juil. 2026
N°: 2 242
ima-noteIMA 个人笔记服务 API skill，用于管理用户的 IMA 笔记。支持搜索笔记、浏览笔记本、获取笔记内容、新建笔记和追加内容。当用户提到笔记、备忘录、记事、知识库，或者想要查找、阅读、创建、编辑笔记内容时，使用此 skill。即使用户没有明确说"笔记"，只要意图涉及个人文档的存取（如"帮我记一下"、"我之前写过一个关于XX的东西"、"把这段内容保存下来"），也应触发此 skill。
Langue du contenu du Skill : chinois
Dépôt: UnicomAI/wanwu
Étoiles GitHub: 2 385Mis à jour: 2 juil. 2026
N°: 2 243
protected-vercel-deploymentsAccess and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection with agent-browser. Use when a preview or production URL redirects to a Vercel login page, returns a protection 401 or 403, or needs short-lived Trusted Sources OIDC authentication instead of a static bypass secret or public exception.
Langue du contenu du Skill : anglais
Dépôt: vercel-labs/agent-browser
Étoiles GitHub: 49 952Mis à jour: 3 nov. 2026
N°: 2 244
auto-paper-improvement-loopAutonomously improve a generated paper via Gemini review through gemini-review MCP → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
Langue du contenu du Skill : anglais
Dépôt: wanshuiyin/Auto-claude-code-research-in-sleep
Étoiles GitHub: 19 051Mis à jour: 3 sept. 2026
N°: 2 245
follow-buildersAI builders digest — monitors top AI builders on X and YouTube podcasts, remixes their content into digestible summaries. Use when the user wants AI industry insights, builder updates, or invokes /ai. No API keys or dependencies required — all content is fetched from a central feed.
Langue du contenu du Skill : anglais
Dépôt: zarazhangrui/follow-builders
Étoiles GitHub: 7 124Mis à jour: 12 nov. 2026
N°: 2 246
protocol-reverseUse for authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery.
Langue du contenu du Skill : chinois
Dépôt: zhaoxuya520/reverse-skill
Étoiles GitHub: 44 521Mis à jour: 8 août 2026
N°: 2 247
telegram-bot-builderThis skill should be used when the user asks to "create a Telegram bot", "build a Telegram chatbot", "set up a Telegram webhook", "add inline keyboards to a bot", "handle Telegram callback queries", "implement Telegram payments", "send media via Telegram bot", "configure Telegram bot commands", "deploy a Telegram bot", or mentions the Telegram Bot API, telegram bot tokens, getUpdates, setWebhook, or bot frameworks like node-telegram-bot-api, grammy, python-telegram-bot, or aiogram. Provides comprehensive guidance for building production-ready Telegram bots with Node.js and Python.
Langue du contenu du Skill : anglais
Dépôt: davila7/claude-code-templates
Étoiles GitHub: 33 360Mis à jour: 15 févr. 2026
N°: 2 248
dmux-workflowsMulti-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
Langue du contenu du Skill : anglais
Dépôt: affaan-m/ECC
Étoiles GitHub: 301 144Mis à jour: 18 sept. 2026
N°: 2 249
strategic-compact임의의 자동 컴팩션 대신 논리적 간격에서 수동 컨텍스트 압축을 제안하여 작업 단계를 통해 컨텍스트를 보존합니다.
Langue du contenu du Skill : coréen
Dépôt: affaan-m/ECC
Étoiles GitHub: 301 144Mis à jour: 4 juil. 2026
N°: 2 250
blueprint将单行目标转化为多会话、多代理工程项目的分步构建计划。每个步骤包含独立的上下文简介，以便新代理能直接执行。包括对抗性审查门、依赖图、并行步骤检测、反模式目录和计划突变协议。触发条件：当用户请求复杂多PR任务的计划、蓝图或路线图，或描述需要多个会话的工作时。不触发条件：任务可在单个PR或少于3个工具调用中完成，或用户说“直接执行”时。
Langue du contenu du Skill : chinois
Dépôt: affaan-m/ECC
Étoiles GitHub: 301 144Mis à jour: 1 oct. 2026
N°: 2 251
springboot-securityJava Spring Boot 服务中认证/授权、验证、CSRF、密钥、标头、速率限制和依赖安全性的 Spring Security 最佳实践。
Langue du contenu du Skill : chinois
Dépôt: affaan-m/ECC
Étoiles GitHub: 301 144Mis à jour: 3 mars 2026
N°: 2 252
commercial-forecasterUse when building a bookings, ARR, pipeline or NRR forecast, or a commit, best-case and pipeline board number. Forecasts with bookings_forecaster.py, projects cohorts with cohort_arr_projector.py and scores stage confidence with funnel_confidence_scorer.py, showing every conversion assumption.
Langue du contenu du Skill : anglais
Dépôt: alirezarezvani/claude-skills
Étoiles GitHub: 29 673Mis à jour: 30 oct. 2026
N°: 2 253
cos-effect-prompt为 COS 照片（cosplay 角色照 / 写真）生成专业级 JSON 后期指令，可直接配合 Nano Banana （Gemini 图像模型）使用。用户在给自己的角色照做后期时使用——加特效（魔法阵、火焰、雷电、冰霜、翅膀、光环、圣光、粒子、辉光、霓虹、雨、雪、花瓣、赛博街景）、做综合修图（身体塑形液化、服装焕新、裙摆/披风风动效果）都在范围内。本技能会输出一份结构化的 JSON 指令：保底规则（构图/脸/姿势不变）+ 检测分析 + 按需启用的处理模块 + 约束与光影噪点一致性。请务必在用户提到「给照片加特效」「COS 后期」「P 图」「修图」「加魔法阵/火焰/光环/翅膀」「液化/瘦身/塑形」「裙子飘起来/加风效」「衣服太皱了」等任何 COS 照片后期需求时使用本技能，即使他们没有说出「提示词」或「指令」——用户提到 Nano Banana / 香蕉模型 / Gemini 图像时也务必使用。用户**给出照片**并问「这个效果怎么做」「分析这张图的后期」「这张图用了什么修图/特效」「照着这张图做」「反推一下提示词」时，进入**反推模式**：观察照片、识别已有后期处理、反推出可复现的 JSON 指令。输出格式为**可直接导入图像处理插件的预设 JSON**（信封结构：id/title/content/category/ subCategory/refImages/_isFactory），content 内是转义后的指令 JSON 字符串。用户提到「MJ 风格 / Midjourney / 二次元 / 动漫 / 日系 / 原画 / 官方立绘 / 厚涂 / 手绘 / 赛博朋克 / 霓虹 / 电影感 / 大片质感 / 梦幻 / 仙气 / 写实 / 极简 / 高级感」等任何**画面风格** 需求，或提到「插件预设 / 导入插件 / 预设格式 / 提示词模板」时，也务必使用本技能——内置 MJ 风格知识库，能把风格需求转译成可执行的指令措辞。用户问「这是什么风格 / 识别这张图的风格 / 分析画风 / 这个风格叫什么 / 这个风格怎么做」时，进入**风格识别**：对照风格库识别照片或描述的风格，输出可用的风格预设；用户提供**新风格** 时，可**学习**入库（styles-learned.md），之后生成可直接调用。用户提到「ComfyUI / Comfy / Stable Diffusio
Langue du contenu du Skill : chinois
Dépôt: Couer869/cos-effect-prompt
Étoiles GitHub: 75Mis à jour: 30 sept. 2026
N°: 2 254
financial-report-analyst深度解读企业财报，将财报 PDF 或 URL 转化为面向普通投资者的专业分析报告，以 Markdown 格式保存到当前项目的 markdown/ 目录。触发条件：用户上传或提供财报 PDF、提到"分析财报"/"读财报"/"解读财报"/"看看这家公司"/"帮我分析一下 XX 公司"，或任何需要深入理解一份财务报告的场景。输出一份犀利、有逻辑支撑的投资参考报告，涵盖：核心收入分析、财务健康诊断、隐蔽风险雷区排查、行业竞争格局、前瞻性估值，以及明确的投资参考建议。即使用户只说"帮我看这份年报"但内容是财报，也应使用本 skill。
Langue du contenu du Skill : chinois
Dépôt: digoal/blog
Étoiles GitHub: 8 605Mis à jour: 22 avr. 2026
N°: 2 255
sql-expertExpert guidance for generating accurate, performant, and secure SQL queries. Focuses on schema-first prompting, index awareness, and handling complex joins/aggregations.
Langue du contenu du Skill : anglais
Dépôt: DOX69/agent-performance-hub
Étoiles GitHub: 0Mis à jour: 17 févr. 2026
N°: 2 256
ruoyi-plus-ai-coding在仓库内按代码生成器模板、项目 reference 文档和既有约定生成或修改代码。用于新增或修改 CRUD 模块、controller/service/mapper/BO/VO/entity、MyBatis-Plus/MPJ 查询、数据权限、缓存、翻译/JSON 增强、公共 common 模块能力、JavaDoc 注释，以及与后端接口配套的 Vue 或 React 前端页面、types 和 api 文件；触发后应先按任务类型读取对应 references，再阅读目标模块真实代码和 generator 模板。
Langue du contenu du Skill : chinois
Dépôt: dromara/RuoYi-Vue-Plus
Étoiles GitHub: 2 862Mis à jour: 28 oct. 2026
N°: 2 257
patent-reader专利通俗解读：中国或海外（美欧日韩等）公开号 / PDF 成通俗笔记、图谱与 Obsidian 入库。
Langue du contenu du Skill : chinois
Dépôt: handsomestWei/patent-disclosure-skill
Étoiles GitHub: 13 357Mis à jour: 3 nov. 2026
N°: 2 258
cite-verifyUse when verifying bibliography citations in a document or when the user pastes academic citations to check, especially when worried about LLM hallucinations where real DOIs or NBER working paper numbers are paired with fabricated titles. Queries Crossref canonical metadata and flags metadata mismatches.
Langue du contenu du Skill : anglais
Dépôt: jonckr/cite-verify
Étoiles GitHub: 3Mis à jour: 25 avr. 2026
N°: 2 259
frontend-ui-systemDiseña e implementa interfaces de alta calidad para apps, sitios web y dashboards con enfoque tipo v0.dev: dirección visual clara, design system, jerarquía visual fuerte, componentes reutilizables, mobile-first, consistencia UI y revisión iterativa.
Langue du contenu du Skill : espagnol
Dépôt: LeoYeAI/openclaw-master-skills
Étoiles GitHub: 2 169Mis à jour: 11 mai 2026
N°: 2 260
sync-upstreamUpdate a stale session branch by rebasing onto the latest origin. Use when the upstream has moved significantly and the session needs to catch up, resolving conflicts by preserving upstream changes and adapting session work to fit.
Langue du contenu du Skill : anglais
Dépôt: microsoft/vscode
Étoiles GitHub: 195 313Mis à jour: 28 mars 2026
N°: 2 261
scrollcraftPremium scroll-driven landing pages; scroll = timeline.
Langue du contenu du Skill : anglais
Dépôt: NousResearch/hermes-agent
Étoiles GitHub: 262 813Mis à jour: 14 sept. 2026
N°: 2 262
grill-meGrill the user relentlessly about a plan, design, decision, or set of review findings — working the decision tree in rounds until nothing is left silently assumed. Use when the user wants to stress-test their thinking, says "grill me", or when another skill (for example /review-pr) delegates its evaluation pass here.
Langue du contenu du Skill : anglais
Dépôt: nrwl/nx
Étoiles GitHub: 29 465Mis à jour: 18 août 2026
N°: 2 263
openclaw-secret-scanning-maintainerTriage, redact, clean up, and resolve OpenClaw GitHub Secret Scanning alerts in issues or PRs.
Langue du contenu du Skill : anglais
Dépôt: openclaw/openclaw
Étoiles GitHub: 394 354Mis à jour: 22 juil. 2026
N°: 2 264
privacy-policyDraft a detailed privacy policy covering data types, jurisdiction, GDPR and compliance considerations, and clauses needing legal review. Use when creating a privacy policy, updating data protection documentation, or preparing for compliance.
Langue du contenu du Skill : anglais
Dépôt: phuryn/pm-skills
Étoiles GitHub: 27 898Mis à jour: 3 mars 2026
N°: 2 265
test-design-patternsPatterns for effective test design, including boundary value analysis, equivalence partitioning, state transition testing, and other systematic test case derivation methodologies. Use this skill for 'test design', 'test case derivation', 'boundary value analysis', 'equivalence partitioning', 'state transition testing', 'pairwise', 'test matrix', and other test design tasks. Enhances the test design capabilities of test-strategist and unit-tester. Note: test infrastructure setup and CI/CD configuration are outside the scope of this skill.
Langue du contenu du Skill : anglais
Dépôt: revfactory/harness-100
Étoiles GitHub: 1 326Mis à jour: 22 mars 2026
N°: 2 266
orchestrateMeta-agent supervisor that manages a fleet of Claude Code agents running in tmux windows. Auto-discovers spare worktrees, spawns agents, monitors state, kicks idle agents, approves safe confirmations, and recycles worktrees when done. TRIGGER when user asks to supervise agents, run parallel tasks, manage worktrees, check agent status, or orchestrate parallel work.
Langue du contenu du Skill : anglais
Dépôt: Significant-Gravitas/AutoGPT
Étoiles GitHub: 187 999Mis à jour: 9 avr. 2026
N°: 2 267
gzh-longform-writer公众号长文写作（1500–4000 字）。先诊断作者手上已有什么（一个念头 / 一堆素材 / 半篇草稿 / 一份大纲 / 一篇不满意的成稿），再路由到对应的六种写法之一，产出成稿并过公众号专属质检。当用户说"写篇公众号""帮我写文章""这个主题怎么写""我有一堆素材不知道怎么组织""帮我扩写""这篇改一下""写不下去了""长文""深度文"时触发。
Langue du contenu du Skill : chinois
Dépôt: SpaceZephyr/creator-buddy
Étoiles GitHub: 1 877Mis à jour: 26 août 2026
N°: 2 268
aig-agent-redteam当用户要求 AI/Agent 安全评估、蓝军演习、AI 安全审查、提示词注入测试、MCP/Skill/插件/代码包审计、Agent 工具链滥用测试，或需要生成类似渗透测试报告的 Markdown/HTML 时，必须使用本 skill。本 skill 让 Agent 以授权蓝军视角成为 AI 安全专家，面向 AI 产品、Agent、MCP Server、Skill、代码仓库和 AI 基础设施进行安全演习。优先使用第一性原理推理和真实证据，而不是机械跑 payload 库；脚本只用于 HTTP 指纹识别、证据聚合、报告渲染等确定性辅助任务。
Langue du contenu du Skill : chinois
Dépôt: Tencent/AI-Infra-Guard
Étoiles GitHub: 7 471Mis à jour: 18 août 2026
N°: 2 269
wowerpointTurn one document into a kawaii NotebookLM slide deck. Use for "wowerpoint this", "make a deck about <file>", "turn this report into slides", or any request to render a single document as shareable narrative slides.
Langue du contenu du Skill : anglais
Dépôt: thedotmack/claude-mem
Étoiles GitHub: 116 292Mis à jour: 19 oct. 2026
N°: 2 270
api-security-testingSecurity-test a REST, GraphQL, or gRPC API with Strix — autonomous agents that enumerate endpoints from an OpenAPI/GraphQL schema (or by crawling), then actually exploit the API-specific vulnerability classes in the OWASP API Security Top 10 (2023) — broken object-level authorization (BOLA/IDOR), broken object property level authorization (excessive data exposure and mass assignment), broken function-level authorization, unrestricted resource consumption, SSRF, injection, and auth/token flaws. Every finding comes with a working proof-of-concept request. Use when the user asks to pentest, security-test, audit, or find vulnerabilities in an API, endpoint, or backend service.
Langue du contenu du Skill : anglais
Dépôt: usestrix/strix
Étoiles GitHub: 75 055Mis à jour: 17 sept. 2026
N°: 2 271
astro-developerComprehensive guide for developing in the Astro monorepo. Covers architecture, debugging, testing, and critical constraints. Use when working on features, fixes, tests, or understanding the codebase structure.
Langue du contenu du Skill : anglais
Dépôt: withastro/astro
Étoiles GitHub: 63 907Mis à jour: 13 août 2026
N°: 2 272
sumeru-outline小说大纲/世界观/人设设计，适用于用户说"帮我写个小说大纲"、"设计主角人设"、"做世界观设定"、"搭小说剧情框架"、"写分卷细纲"、"给我设计小说人物"、"做个玄幻世界观"、"帮我梳理小说剧情"、"小说人物设定"、"写小说分章大纲"、"爽点排布规划"、"做小说人设卡"、"构建小说世界"等需求，生成完整的世界观、人物卡、剧情大纲、章节细纲与爽点规划，并执行命名合规检查，避免与真实人物/地点及知名IP撞名，大批量细纲使用子Agent并行生成（每Agent最多3章）
Langue du contenu du Skill : chinois
Dépôt: xindoo/sumeru
Étoiles GitHub: 224Mis à jour: 29 oct. 2026
N°: 2 273
story-short-scan短篇网文扫榜。分析知乎盐言、七猫、黑岩、点众等平台热门短篇数据，捕捉风口题材。触发方式：/story-short-scan、/短篇扫榜、「短篇什么火」「知乎故事排行」。
Langue du contenu du Skill : chinois
Dépôt: zenstory-ai/oh-story-claudecode
Étoiles GitHub: 8 531Mis à jour: 8 nov. 2026
N°: 2 274
travel-plan-viz把旅行行程做成美观、离线可读、手机优先的单文件 HTML（交互地图+每日时间轴+出发前订票提醒）。两种用法——只给目的地和天数让它帮你规划，或丢一份现成计划让它直接出页面。触发：旅行计划可视化、做旅行攻略网页、行程 HTML、travel plan visualization。
Langue du contenu du Skill : chinois
Dépôt: zexuanw958-svg/travel-plan-viz
Étoiles GitHub: 412Mis à jour: 15 juil. 2026
N°: 2 275
hvac-designSkill for HVAC system design and analysis per ASHRAE standards including load calculations, equipment selection, and energy efficiency analysis
Langue du contenu du Skill : anglais
Dépôt: a5c-ai/babysitter
Étoiles GitHub: 1 905Mis à jour: 1 juin 2026
N°: 2 276
x-apiX/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.
Langue du contenu du Skill : anglais
Dépôt: affaan-m/ECC
Étoiles GitHub: 301 144Mis à jour: 25 août 2026
N°: 2 277
finance-skillsPick the right finance skill: ratios, DCF, forecasts (financial-analyst), ARR, churn, CAC, LTV (saas-metrics-coach), month-end-close. Use whenever a finance ask is vague.
Langue du contenu du Skill : anglais
Dépôt: alirezarezvani/claude-skills
Étoiles GitHub: 29 673Mis à jour: 3 nov. 2026
N°: 2 278
tailwind-design-systemBuild scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.
Langue du contenu du Skill : anglais
Dépôt: OpenMontageInc/OpenMontage
Étoiles GitHub: 79 744Mis à jour: 29 mars 2026
N°: 2 279
croWhen the user wants more conversions from a page or form, or asks why a page isn't converting, what to change first, or whether to add or remove a field or element: landing and pricing pages, lead forms, or a URL shared for feedback. For signup flows, see signup. For activation, see onboarding. For popups, see popups. For running the test, see ab-testing.
Langue du contenu du Skill : anglais
Dépôt: coreyhaines31/marketingskills
Étoiles GitHub: 59 836Mis à jour: 9 nov. 2026
N°: 2 280
academic-proposal-writing根据课题题目和范例，撰写涵盖核心概念、选题依据、研究内容、思路方法、研究计划、研究基础与条件保障、可行性分析及成果等全章节的学术课题申报书。
Langue du contenu du Skill : chinois
Dépôt: ECNU-ICALK/AutoSkill
Étoiles GitHub: 610Mis à jour: 13 mars 2026
N°: 2 281
tech-doc-style-chinese在撰写、改写、校对或审阅中文技术文档、产品文案、界面文案、Markdown 文档、API 说明、操作手册、故障排查或运维文档时使用。采用克制、准确、可扫读的中文技术写作风格；保留原文事实、限制和机器可读内容；按任务读取术语排版、API 状态文案、项目覆盖或受控中文技术写作参考。
Langue du contenu du Skill : chinois
Dépôt: Fenng/Tech-Doc-Style-Chinese
Étoiles GitHub: 1 584Mis à jour: 5 oct. 2026
N°: 2 282
plan-tuneSelf-tuning question sensitivity + developer psychographic for gstack (v1: observational). (gstack)
Langue du contenu du Skill : anglais
Dépôt: garrytan/gstack
Étoiles GitHub: 141 280Mis à jour: 2 nov. 2026
N°: 2 283
open-notebookOrganizes research with the self-hosted Open Notebook alternative to NotebookLM. Supports source ingestion (PDFs, web pages, audio, video, and Office documents), cited document chat, text and vector search, notes, custom transformations, and multi-speaker podcasts. Use when automating Open Notebook through its REST API or configuring its local or cloud AI providers, including OpenAI, Anthropic, Google, Ollama, Groq, and Mistral.
Langue du contenu du Skill : anglais
Dépôt: K-Dense-AI/scientific-agent-skills
Étoiles GitHub: 56 867Mis à jour: 1 oct. 2026
N°: 2 284
aussenwirtschaft-f-gase-ozonstoffeWenn es um F-Gase und Ozonschutzstoffe: Einfuhrkontrolle und Quotenmanagement in Außenwirtschaft, Sanktionen, Zoll und CBAM geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und Gegenposition; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Langue du contenu du Skill : allemand
Dépôt: Klotzkette/claude-fuer-deutsches-recht
Étoiles GitHub: 1 428Mis à jour: 1 juil. 2026
N°: 2 285
ljg-paperExplain research papers to readers without a specialist background: what the paper studies, what the authors contribute, how the findings follow, and what the evidence does not establish. USE WHEN the user shares an arXiv link, paper URL, PDF, local paper, or paper title, or asks to read, explain, analyze, or understand a paper. Defaults to a saved Markdown note. NOT FOR reproduction, formal peer review, benchmark tables, or literature surveys.
Langue du contenu du Skill : chinois
Dépôt: lijigang/ljg-skills
Étoiles GitHub: 7 738Mis à jour: 30 oct. 2026
N°: 2 286
html-ppt-tech-sharingOpenDesign internals: how the agent stream, sandbox, and artifacts work — an engineering deep-dive talk. Built as a decision-grade AI literacy deck for engineers, dev community.
Langue du contenu du Skill : anglais
Dépôt: nexu-io/open-design
Étoiles GitHub: 107 245Mis à jour: 18 août 2026
N°: 2 287
imagegenGenerate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.
Langue du contenu du Skill : anglais
Dépôt: openai/skills
Étoiles GitHub: 28 700Mis à jour: 15 avr. 2026
N°: 2 288
sn-deep-research用于用户请求深度研究、系统性研究、竞品分析、方案对比、趋势分析或事实核查时。**遇到以下任一情况就主动使用本 skill，不要自行搜几条就回答**：①用户出现触发词：深度研究 / 深度调研 / 深入研究 / 全面研究 / 系统研究 / 调研 / 调查 / 尽调 / 行业研究 / 市场研究 / 竞品分析 / 政策研究 / 技术研究 / 趋势研究 / 事实核查 / 写一份研究报告 / 调研报告 / 深度报告 / research / deep research；②请求需要跨多来源取证、多维度对比、交叉验证才能给出可靠结论；③用户要求产出报告、白皮书、行业分析或尽调文档；④话题涉及最新政策/市场/产品/价格/法规，需要系统核查。无核验要求的简单常识问答不使用。模糊或宽泛的"研究/了解一下 X"也优先触发。仅不用于：一句话摘要、已给定单一来源的整理、纯文字润色改写。
Langue du contenu du Skill : chinois
Dépôt: OpenSenseNova/SenseNova-Skills
Étoiles GitHub: 6 070Mis à jour: 25 août 2026
N°: 2 289
university-exam-prep大学备考苏格拉底式学习助手，专为应对"面向课本和PPT考试"设计。当用户说"帮我复习"、"准备考试"、"备考"、"期末复习"、"模拟学习"、"突击复习"等时触发。核心特点：(1)强制要求用户上传课本/PPT/考纲等原始材料——没有材料就无法有效辅导；(2)使用苏格拉底式提问法，不直接灌输而是引导思考；(3)专注于应用型和理解型内容，而非纯概念记忆；(4)模拟真实考试场景进行针对性练习；(5)分析材料识别高频考点和重难点。适用于大学各科目期中期末考试备考、突击复习、考前模拟。
Langue du contenu du Skill : chinois
Dépôt: staruhub/ClaudeSkills
Étoiles GitHub: 735Mis à jour: 21 juil. 2026
N°: 2 290
maoxuan-enhanced毛泽东深度思维伙伴 v2.0：不只是框架应用，而是真正以毛泽东的世界观和方法论与你展开对话——先调查研究，再矛盾定位，再战略分析，再追问反诘。 12个核心心智模型 · 调查前置协议 · 毛式反问追问库 · 231篇原典锚点基于《毛泽东选集》五卷及原典著作全面提炼。触发词：毛选、教员、毛泽东、用毛泽东的方式、教员怎么看、帮我分析
Langue du contenu du Skill : chinois
Dépôt: zhangtianruiwork-droid/Maoxuan-Changzheng
Étoiles GitHub: 460Mis à jour: 22 avr. 2026
N°: 2 291
script-forging将成熟故事稳定转化为可拍摄执行的影视剧本、分镜方案与后续 AI/拍摄可复用的数字资产清单。适用于用户要求"故事变剧本、小说改剧本、生成标准剧本、分场大纲、剧本一稿、剧本化提示包、用 AI 写剧本、剧本转分镜、分镜表、逐镜头分镜、完整分镜、拍摄分镜、AI 视频逐镜、镜头脚本、镜头表、场景清单、道具清单、角色出场清单、数字资产清单"等任务。核心流程：故事原文 → 专业形态建议 → 剧本化提示包 → 分场大纲 → 标准剧本 → 自检修订 → 分镜生成 → 数字资产清单。
Langue du contenu du Skill : chinois
Dépôt: zhlmi/script-forging
Étoiles GitHub: 284Mis à jour: 5 juin 2026
N°: 2 292
life-science-evidence-reviewGenerate evidence-based literature reviews, structured evidence synthesis, and knowledge-gap analyses for life science research.
Langue du contenu du Skill : anglais
Dépôt: ZZL-Zoro/Life-Science-Evidence-Review
Étoiles GitHub: 34Mis à jour: 12 août 2026
N°: 2 293
codex-visio-paper-figure-skillConvert paper figures and AI-generated diagrams into editable Microsoft Visio (.vsdx) files with native shapes, text, and connectors, then export to SVG/PDF/PNG/PPTX
Langue du contenu du Skill : anglais
Dépôt: reason-machines/codex-skills
Étoiles GitHub: 2Mis à jour: 24 juin 2026
N°: 2 294
frontendBuilds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain way.
Langue du contenu du Skill : anglais
Dépôt: code-yeongyu/oh-my-openagent
Étoiles GitHub: 70 860Mis à jour: 6 nov. 2026
N°: 2 295
record-browser-gifRecord browser or Web UI interaction demos as optimized GIFs using the available browser-control workflow, optional Playwright Videos for higher capture frame rates, and deterministic encoding, then attach the GIF to a pull request with `gh --attach`; publication requires gh v2.99.0 or later, and a GIF over 5 MiB is split into parts. Use when asked to make, record, or generate a GIF that demonstrates a browser workflow, and for every pull request that changes product-user-visible GUI behavior, which MUST include a GIF recorded from the pull request's real server and model flow.
Langue du contenu du Skill : anglais
Dépôt: deepseek-ai/deepseek-harness
Étoiles GitHub: 279 199Mis à jour: 28 oct. 2026
N°: 2 296
scrapling使用 scrapling 进行网页抓取和数据提取。自动选择 Fetcher，支持 Cloudflare/WAF 绕过、Session 登录、HTML 解析。当用户提到 scrape/crawl/fetch page/extract data/爬取/抓取/绕过Cloudflare/解析HTML/批量采集时触发。
Langue du contenu du Skill : chinois
Dépôt: fengshao1227/ccg-workflow
Étoiles GitHub: 5 983Mis à jour: 31 mars 2026
N°: 2 297
codebase-memory-mcpUse when exploring unfamiliar code, mapping architecture, finding symbols or relationships, tracing callers, callees, data flow or dependencies, assessing impact, auditing dead or complex code, or handling explicit Codebase Memory requests. Otherwise skip tasks confined to a supplied known file, tiny one-file check, exact literal, configuration value, error string, or non-code text.
Langue du contenu du Skill : anglais
Dépôt: github/awesome-copilot
Étoiles GitHub: 41 059Mis à jour: 7 oct. 2026
N°: 2 298
cli-anything-libreofficeCommand-line interface for Libreoffice - A stateful command-line interface for document editing, producing real ODF files (ZIP archives with ...
Langue du contenu du Skill : anglais
Dépôt: HKUDS/CLI-Anything
Étoiles GitHub: 58 632Mis à jour: 29 avr. 2026
N°: 2 299
storytelling-advisorShape pitches, brand stories, presentations, and creative writing with narrative frameworks such as the Hero's Journey, Story Spine, and Freytag's Pyramid. Use when a user wants to structure, critique, or strengthen a story.
Langue du contenu du Skill : anglais
Dépôt: iflytek/skillhub
Étoiles GitHub: 5 402Mis à jour: 31 juil. 2026
N°: 2 300
baoyu-comicKnowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
Langue du contenu du Skill : anglais
Dépôt: JimLiu/baoyu-skills
Étoiles GitHub: 27 471Mis à jour: 1 nov. 2026