Agent Skills Index

Agent skills index, page 32

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

Open search

No.: 3,101
glabGitLab CLI (glab) for working with GitLab from the command line. Read this skill before running any `glab` or GitLab API command — it applies to every GitLab operation, whether reading or writing (for example merge requests, issues, work items, discussions and threaded replies, comments, CI/CD pipelines, releases, packages, members, and project settings). Whenever a task touches GitLab in any way, consult this skill first so you use the correct, safe command on the first try. Prefer glab over raw API calls for all GitLab operations.
Repository: gitlabhq/gitlabhq
GitHub stars: 24,548Updated: Oct 3, 2026
No.: 3,102
rhel-server-adminUse when administering Red Hat Enterprise Linux 9 systems — dnf/rpm package management, subscription-manager, user/group management, SSH hardening, systemd services, firewalld, NetworkManager/nmcli networking, LVM/Stratis storage, kernel tuning, security hardening (CIS, SELinux, fail2ban), Cockpit web console, backup/restore, and on-prem VM guest tools (Proxmox, VMware, Hyper-V). Parent skill for the rhel-* skill family.
Repository: joogy06/agent-foundry
GitHub stars: 3Updated: Jul 30, 2026
No.: 3,103
pybammSimulates lithium-ion battery charge, discharge and rest experiments with PyBaMM, records parameter-set provenance, checks mesh and solver sensitivity, and compares predicted voltage curves with measured cycling data. Use for SPM or DFN electrochemical battery modeling, C-rate protocols, voltage cutoffs, parameter studies and numerical validation of battery simulations.
Repository: K-Dense-AI/scientific-agent-skills
GitHub stars: 56,174Updated: Oct 1, 2026
No.: 3,104
horoscope-dailyGenerates personalized horoscope readings for all twelve zodiac signs based on Western astrology. Supports any date (today, tomorrow, a specific date) and any time period (daily/weekly/monthly), covering five dimensions — Overall, Love, Career, Finance, and Health — with a Lucky Guide and Daily Tip. Can deliver personalized readings based on the user's birthday. Pure LLM generation, no external API required. Trigger words: horoscope, daily horoscope, zodiac forecast, what's my horoscope today, weekly horoscope, monthly horoscope, star sign reading, astrology forecast, what's my sign today. Not intended for: Ba Zi (Four Pillars), Zi Wei Dou Shu, Tarot, Numerology, or Feng Shui — use fortune-hub to find the right skill for those domains.
Repository: LeoYeAI/openclaw-master-skills
GitHub stars: 2,169Updated: Jun 29, 2026
No.: 3,105
screenwriting-videoScreenwriting Video Maker — Create Script Writing and Film Story Videos.
Repository: LeoYeAI/openclaw-master-skills
GitHub stars: 2,169Updated: Jun 1, 2026
No.: 3,106
ljg-relationshipRelationship analyst combining structural diagnostics (5-layer framework) with psychoanalytic depth (transference, unconscious patterns, resistance). Guides users through dialogue to "see" the real structure of their relationship issues. Use when user says "关系分析", "分析关系", "relationship", "人际关系", or describes a specific relationship problem they want to understand.
Skill content language: Chinese
Repository: lijigang/ljg-skills
GitHub stars: 7,630Updated: Oct 26, 2026
No.: 3,107
make-textbook-figure构建教材级别的黑白矢量插图（几何图、受力分析图、光路图、电路图、函数图像、坐标系、物理/数学示意图等），以自包含 HTML 文件呈现——所有线条用 SVG 绘制，所有公式、符号、运算符、物理/数学符号用 LaTeX 经 MathJax 渲染为矢量，支持一键导出高清 PNG。当用户说"画个教材图/教材插图/教学示意图""画受力分析图/光路图/电路图/函数图/几何图""做一张黑白矢量图/示意图""把这道题/这个原理配张图""画个坐标系/数轴"，或任何为教材、讲义、试卷、课件绘制精确黑白教学插图的需求时，必须使用本技能，即使用户没明说"教材"二字。注意：本技能与 make-infographic 不同——make-infographic 做彩色信息图/海报（给家长客户看，版式驱动），本技能做黑白精确教学插图（给师生用，准确性驱动），不要混用。
Skill content language: Chinese
Repository: lingxiaobc/claude_code_template
GitHub stars: 0Updated: Jul 8, 2026
No.: 3,108
business-central-developmentExpert guidance for Microsoft Dynamics 365 Business Central development using AL language and extensions
Repository: Mindrally/skills
GitHub stars: 289Updated: Oct 8, 2026
No.: 3,109
pptx-generatorGenerate, edit, and read PowerPoint presentations. Create from scratch with PptxGenJS (cover, TOC, content, section divider, summary slides), edit existing PPTX via XML workflows, or extract text with markitdown. Triggers: PPT, PPTX, PowerPoint, presentation, slide, deck, slides.
Repository: MiniMax-AI/skills
GitHub stars: 13,789Updated: Mar 21, 2026
No.: 3,110
free-llm-apisGuide users through obtaining and configuring free API keys for LLM providers. Use when the user wants to set up a free LLM API, get a free API key, connect to a free model provider, configure an OpenAI-compatible endpoint at no cost, or asks about free tiers for AI models. Triggers on "free API key", "free LLM", "set up Gemini/Groq/Mistral/etc.", "which free provider", "how to get an API key", "free model access", "configure LLM for free".
Repository: mnfst/awesome-free-llm-apis
GitHub stars: 12,285Updated: Nov 4, 2026
No.: 3,111
qiuzhi2046-skill秋芝2046（前产品经理，AI Native创作者）的AI科普内容创作思维——爆肝实操导向、痛点前置产品思维、全平台内容矩阵、B站深度+抖音短平快+飞书系统化。触发词：「秋芝2046视角」「像秋芝2046那样写」「AI科普教程」「DeepSeek教程」「One-Click解决一切」。擅长：AI工具测评与推荐、AI教程设计（幼儿园→专业级）、技术热点快速响应、AIGC内容实验、多平台内容矩阵运营、飞书知识库架构、AI春晚级别的项目管理。
Skill content language: Chinese
Repository: momozi1996/awesome-ai-persona-skills
GitHub stars: 1,081Updated: May 3, 2026
No.: 3,112
caipiao-500500 彩票网竞彩足球当日售卖中全部场次（含欧五大联赛、杯赛、亚洲联赛等）的对阵、亚盘、欧赔、数据分析、预计阵容快照。回答赛前盘口/赔率/交战历史类问题。
Skill content language: Chinese
Repository: nelsonie/caipiao
GitHub stars: 1Updated: Nov 5, 2026
No.: 3,113
industrial-brutalist-uiRaw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Jun 2, 2026
No.: 3,114
fal-tryonVirtual try-on — see how clothes look on a person via fal.ai's hosted try-on models. Useful for ecommerce, lookbooks, and styling experiments.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 3,115
gsap-utilsOfficial GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe. Use when the user asks about gsap.utils, clamp, mapRange, random, snap, toArray, wrap, or helper utilities in GSAP.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Oct 14, 2026
No.: 3,116
docker-managementManage Docker containers, images, volumes, and Compose.
Repository: NousResearch/hermes-agent
GitHub stars: 260,788Updated: Aug 8, 2026
No.: 3,117
drug-discoveryDrug discovery: ChEMBL search, drug-likeness, interactions.
Repository: NousResearch/hermes-agent
GitHub stars: 260,788Updated: Oct 8, 2026
No.: 3,118
game-narrativeA full narrative pipeline where an agent team collaborates to design game story, quests, dialogue, and branching scenarios all at once. Use this skill for 'create a game scenario,' 'game story design,' 'quest design,' 'game dialogue writing,' 'branching scenarios,' 'world-building,' 'NPC dialogue,' 'game scenario branching,' 'interactive story,' and all other aspects of game narrative design. Also supports quest/dialogue/branch design when existing world-building or story is provided. Note: game programming, level design (terrain/maps), game balancing (numerical values), and UI/UX design are outside the scope of this skill.
Repository: revfactory/harness-100
GitHub stars: 1,320Updated: Mar 22, 2026
No.: 3,119
new-energy-research-pipeline新能源电力一体化科研论文全流程（20阶段）总控管线协调器。适用于新能源并网、风光储协同、微电网、综合能源系统、源网荷储协同、虚拟电厂、需求响应、电力市场、低碳调度、不确定性优化、储能配置与新能源消纳等方向，协调并指引从识别入口、前沿扫描、选题发现、创新点打分、模型代码搭建、数据集工程、实验图表设计、参考论文结构迁移、论文写作到审稿自检的完整周期。
Skill content language: Chinese
Repository: sdjuchen/new-energy-ies-research-skills
GitHub stars: 1Updated: Jul 4, 2026
No.: 3,120
testcase-generator针对 PRD、原型、接口文档、用户故事或已有用例，进行需求分析、全维度测试点提炼、测试用例设计与编写、审核覆盖缺口，并可直接导出带样式/可筛选的 Excel（.xlsx）或 CSV 以导入禅道/TestRail/飞书多维表格。用户要求生成、设计、编写、补充、评审测试用例，或明确要求导出 Excel/xlsx/表格文件、禅道/TestRail 导入时使用。
Skill content language: Chinese
Repository: SeaZhusp/tester-skills
GitHub stars: 48Updated: Sep 5, 2026
No.: 3,121
paper-writingResearch paper writing assistant that enforces Arpit Gupta's editorial principles, voice profile, and writing workflow. MANDATORY TRIGGERS: Use this skill whenever the user mentions writing a paper, drafting a section, revising a section, editing a paper, reviewing a draft, rewriting an introduction, writing an evaluation, polishing prose, compressing text, or any task involving .tex files, Overleaf, conference submissions, or paper deadlines. Also trigger when the user mentions any paper by name (NetBurst, NetForge, BQT+, TurboTest, etc.) in a writing context. This skill should activate for ANY research writing task — sections, abstracts, rebuttals, camera-ready edits, cover letters, or response to reviewers.
Repository: SNL-UCSB/paper-writing-skill
GitHub stars: 247Updated: Jul 31, 2026
No.: 3,122
wx-channel-style-profiler提取微信视频号作品 DNA：单条视频生成 report，按 dna-id 聚合选题、短标题与视频描述、内容创意、业务植入套路、互动引导与 CTA 套路、视频形态与制作指向、制作规格、口播文案子模块与账号运营子模块，推导 main agent 的视频 Brief template。
Skill content language: Chinese
Repository: TeamWiseFlow/xiaobei
GitHub stars: 8,686Updated: Oct 27, 2026
No.: 3,123
learning-to-learnInfuse learning strategies and metacognition into a concept-centered OpenMAIC classroom as a parallel goal. Use when the user wants students to learn how to learn while studying a subject: retrieval practice, self-explanation, prediction before feedback, monitoring understanding, deliberate review, or productive failure. Do not use when learning science or study skills should be the standalone subject of the lesson.
Skill content language: Chinese
Repository: THU-MAIC/OpenMAIC
GitHub stars: 42,718Updated: Aug 27, 2026
No.: 3,124
coverage-analysisMeasures and interprets what a fuzzing campaign actually reaches, using llvm-cov, lcov, or a fuzzer's own coverage output. Covers baselining a new campaign, reading coverage reports, and turning uncovered regions into harness, seed, or dictionary work. Use when a fuzzer plateaus, when judging whether a harness is effective, after changing a harness, or when asking why some code is never reached.
Repository: trailofbits/skills
GitHub stars: 8,020Updated: Sep 16, 2026
No.: 3,125
wechat-article-spider微信公众号文章爬虫 - 将微信公号文章转换为 Markdown + 本地图片
Skill content language: Chinese
Repository: UnicomAI/wanwu
GitHub stars: 2,384Updated: Jul 2, 2026
No.: 3,126
fastapi-templatesCreate production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
Repository: wshobson/agents
GitHub stars: 42,226Updated: Oct 15, 2026
No.: 3,127
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.
Repository: wshobson/agents
GitHub stars: 42,226Updated: Sep 28, 2026
No.: 3,128
reverse-video-promptReverse-engineer and iteratively improve AI video prompts from a provided video, generated attempt, frame sequence, storyboard, or short-video reference. Use when the user asks to 反推视频提示词, 拆解视频, 复刻视频效果, 复刻爆款短视频, 生成后复盘, 迭代提示词, 优化 skill, 从视频生成提示词, or produce a ready-to-use prompt for TikTok/UGC/TikTok Shop/Seedance/Kling/Runway/Pika-style video generation, especially when the output needs a clear first-3-second product hook, dense audio/visual information, ecommerce selling-point proof, close recreation of a reference, or community-driven skill iteration.
Repository: zhengzhentao86/reverse-video-prompt
GitHub stars: 58Updated: Jul 17, 2026
No.: 3,129
openfoamUse when working on CFD cases with OpenFOAM, including solver selection, dictionary setup, mesh workflows, turbulence models, or flow and heat-transfer verification.
Skill content language: Chinese
Repository: ZimoLiao/scholaraio
GitHub stars: 584Updated: Apr 26, 2026
No.: 3,130
pentest-agent-os渗透测试Agent操作系统。把渗透抽象成状态空间搜索:不预设固定路径,以项目黑板 Fact 图 (upsert_project_fact)+漏洞记录沉淀认知,路径从已验证事实上涌现。覆盖全杀伤链攻击手法 (联网情报/Web/认证/服务端/源码/社工/后渗透/二进制/内网域/云/区块链/AI/无线/硬件)+0day+ 组合拳+代理自举。核心:全网搜不到洞时现场推导独属于目标的攻击链。本文件为套件索引。 Use when starting a full-chain pentest engagement or needing the skill map for this suite.
Skill content language: Chinese
Repository: AIPentest/CyberStrikeAI
GitHub stars: 8,415Updated: Jul 29, 2026
No.: 3,131
landingUse when asked for a premium single-file HTML landing page with 3D CSS, GSAP scroll effects and parallax. Locks positioning in a short intake, validates the palette with brand_palette_validator.py and the output with html_validator.py.
Repository: alirezarezvani/claude-skills
GitHub stars: 29,341Updated: Oct 30, 2026
No.: 3,132
artifact-diagrammingDiagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.
Repository: asgeirtj/system_prompts_leaks
GitHub stars: 70,820Updated: Oct 10, 2026
No.: 3,133
thai-government-formUse this skill for any task involving Thai government letters, official correspondence, formal petitions, authorization letters, leave requests, or ราชการ forms. Trigger whenever the user asks to: write หนังสือราชการ, draft a คำร้อง, write an authorization (หนังสือมอบอำนาจ), submit a leave form (ใบลา), petition a government agency, or write a formal letter to a Thai official. Also trigger for requests like "เขียนหนังสือราชการ", "ยื่นเรื่อง", "คำร้อง", "หนังสือถึงราชการ", "ทำหนังสือถึง", "ใบลา", "หนังสือมอบอำนาจ", "official Thai letter", or any formal ราชการ document task.
Skill content language: Thai
Repository: Boom-Vitt/claude-thai-skills
GitHub stars: 58Updated: May 17, 2026
No.: 3,134
videohub-story-editor把长视频或已有字幕转成有完整叙事的几分钟短片。先基于原文字幕和画面证据理解、选段与重排，再对最终时间轴重新翻译和可选润色；既可输出保留原声的双语字幕版，也可把原声降到 30% 并用 MiniMax 或豆包 TTS 生成影视解说、短剧混剪、播客串讲或知识解读版。已有项目可进入本地五轨时间线继续调整切点、旁白、原声窗口、字幕、音量和转场，并按修订版本渲染。用于“把长视频讲成短故事”“按字幕自动剪辑”“剪好后再翻译”“制作 TTS 解说版”“可视化精修”“生成抖音发布文件夹和文案”等任务。
Skill content language: Chinese
Repository: cacity/VideoHub
GitHub stars: 178Updated: Aug 11, 2026
No.: 3,135
video-understandUnderstand video content locally using ffmpeg frame extraction and Whisper transcription. No API keys needed. Use when: (1) Understanding what a video contains, (2) Transcribing video audio locally, (3) Extracting key frames for visual analysis, (4) Getting video content without API keys.
Repository: calesthio/OpenMontage
GitHub stars: 76,985Updated: Mar 29, 2026
No.: 3,136
website-to-videoCapture a general website/URL and turn it into a HyperFrames video (site tour, showcase, or social clip from the site's own visuals). Uses headless Chrome screenshots + brand assets. Use when intent is general — portfolio/blog/landing-page showcase or social clip from the site. NOT for: product/SaaS launch or promo (→ /product-launch-video, even from a URL); topic explainer with no site (→ /faceless-explainer); GitHub PR (→ /pr-to-video); adding captions to existing video (→ /embedded-captions); short unnarrated page-highlight motion graphic (→ /motion-graphics). Unclear launch-vs-general-site? Ask one question or start at /hyperframes.
Repository: calesthio/OpenMontage
GitHub stars: 76,985Updated: Jun 27, 2026
No.: 3,137
remove-ai-flavor去除 AI 味道的文章风格优化技能。用于识别并改写文章、公众号稿、自媒体稿、口播稿、演讲稿、课程稿、产品文案中的 AI 痕迹、模板腔、资料味、翻译腔、内容空心、空洞大词、过度金句、破折号滥用、bullet 堆叠、动不动加粗等问题；当用户说“去 AI 味”“去除 AI 痕迹”“不像 AI 写的”“更像人写的”“更自然”“别太机器味”“去掉模板感”“改得像公众号终稿”时使用。不用于事实核查、从零选题策划、论文转公众号、纯标题生成或追求 AI 检测器通过率。
Skill content language: Chinese
Repository: chujianyun/skills
GitHub stars: 749Updated: Sep 25, 2026
No.: 3,138
rag-engineerExpert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.
Repository: davila7/claude-code-templates
GitHub stars: 33,139Updated: Oct 24, 2026
No.: 3,139
resume-section-builderCreate targeted resume sections optimized for different experience levels and roles. Use when the user wants to build or rewrite specific sections like summary, skills, experience, education, or projects.
Repository: davila7/claude-code-templates
GitHub stars: 33,139Updated: May 16, 2026
No.: 3,140
user-storyCreate user stories with Mike Cohn format and Gherkin acceptance criteria. Use when turning user needs into development-ready work with clear outcomes and testable conditions.
Repository: deanpeters/Product-Manager-Skills
GitHub stars: 7,885Updated: Aug 10, 2026
No.: 3,141
dsh-archive-agent-notesUse when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, deletes small UI and purely mechanical records, classifies other implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind} triplet and manifest rules.
Repository: deepseek-ai/deepseek-harness
GitHub stars: 273,539Updated: Sep 18, 2026
No.: 3,142
h3-cinematic-directorConvert approved scripts, shot briefs, storyboards, keyframes, character sheets, scene assets, prop sheets, and sound briefs into director-level storyboards and production-ready MiniMax H3 prompts. Use when the user explicitly invokes $h3-cinematic-director or asks for H3 shot design, T2VA/I2VA/FL2VA/L2VA/Ref2VA prompting, camera and performance direction, first/last-frame interpolation, multi-reference control, character/scene continuity auditing, or single-variable repair. Preserve approved story content and never import or reveal private content from another project.
Repository: jtydhr88/ComfyTV
GitHub stars: 1,169Updated: Aug 24, 2026
No.: 3,143
academic-figure-prompt-modern-ml-airy-styleGenerate prompts for AI image tools to produce modern ML/RL paper-style figures matching the aesthetic of recent ICLR/NeurIPS/ICML 2024-2025 publications. Key traits — pure white canvas, white panels with soft drop shadow, rounded friendly font (Nunito/Poppins), densely packed but uncluttered floating elements, small pastel token squares, rich inline illustrations, colored keyword text, pill-shaped concept labels. Trigger phrases — "pastel风格论文配图", "现代ML论文配图", "modern ML figure prompt".
Skill content language: Chinese
Repository: LigphiDonk/academic-figure-generator
GitHub stars: 2,846Updated: Mar 26, 2026
No.: 3,144
article-writer内容工厂专用写作 Skill，生成批量文案、短视频脚本和图片提示词，并输出可回写的 workspacePatch。
Skill content language: Chinese
Repository: limecloud/lime
GitHub stars: 1,493Updated: Aug 8, 2026
No.: 3,145
academic-paper-composerSystematic writing framework for philosophy and interdisciplinary academic papers from optimized outline to submission-ready manuscript. Use when users want to: (1) write a paper from a detailed outline, (2) ensure quality control during writing, (3) maintain consistency across chapters, (4) prepare a submission-ready manuscript, or (5) systematically execute a planned paper. Triggered by phrases like 'write the paper from this outline,' 'compose the full manuscript,' 'execute the outline,' or when users have completed strategic planning (academic-paper-strategist skill) and are ready to write. Takes optimized outline as input; outputs complete manuscript with iterative quality checks.
Repository: lishix520/academic-paper-skills
GitHub stars: 1,462Updated: Jan 4, 2026
No.: 3,146
yichen-wechat-local-vault微信本地数字资产库：支持 macOS 与已实测 Windows 环境的本地全量解析，包括全库采集、认证解密、聊天记录读取/搜索/导出，以及朋友圈和收藏正文解析。Mac 另支持增量刷新和漏看/待回复检查，默认微信1，微信2须明确指定。Windows 本机采集走 windows，离线聊天查询走 snapshot，朋友圈/收藏复用包内纯函数工作流；不触发 Mac 配置或流程。依赖最新聊天时必须先刷新相应来源，不能拿旧记录代替目标。Windows 版本及功能边界见本机采集参考。
Skill content language: Chinese
Repository: mcncarl/yichen-skills
GitHub stars: 5,196Updated: Oct 28, 2026
No.: 3,147
credential-setup-with-computer-useGuides n8n credential setup through Computer Use browser tools. Use when a user needs OAuth apps, API keys, client IDs, client secrets, or other credential values from an external service console.
Repository: n8n-io/n8n
GitHub stars: 209,572Updated: Jul 7, 2026
No.: 3,148
nsfc-writeNSFC申请书撰写指南。覆盖选题、摘要、立项依据、研究内容、研究方案、创新性、可行性分析等各部分的写作技巧与模板。适用于青年C、面上、重点等项目类型。
Skill content language: Chinese
Repository: njzjz/nsfc-agent-skills
GitHub stars: 732Updated: Aug 27, 2026
No.: 3,149
agent-merge-conflict-arbiterNeutral arbiter for merge conflicts between two agents.
Repository: NousResearch/hermes-agent
GitHub stars: 260,788Updated: Aug 30, 2026
No.: 3,150
pokemon-playerPlay Pokemon via headless emulator + RAM reads.
Repository: NousResearch/hermes-agent
GitHub stars: 260,788Updated: Sep 19, 2026
No.: 3,151
teams-meeting-pipelineTeams meeting summaries, job replay, Graph subscriptions.
Repository: NousResearch/hermes-agent
GitHub stars: 260,788Updated: Aug 30, 2026
No.: 3,152
pr-gardeningDiscover the pull requests this Paperclip instance opened (never community contributions), report what each is for and how confident we are that it is merge-ready, and automatically drive the non-ready ones back to green with /prepare-paperclip-pr — without ever merging.
Repository: paperclipai/paperclip
GitHub stars: 111,284Updated: Jul 27, 2026
No.: 3,153
glass-linePhysical substrate layer for Plurigrid ASI — co-deployed fiber optic + geothermal infrastructure providing sensing, communication, energy, and materials extraction through a single bore.
Repository: plurigrid/asi
GitHub stars: 72Updated: Jun 10, 2026
No.: 3,154
heygen-digital-avatarCreate and composite HeyGen digital-human videos in the content workspace. Use whenever the user asks for a 数字人, 数字人5, HeyGen, AI 口播人物, 数字人小窗, 圆形头像口播, full-screen digital human, or asks to make a video that uses the existing avatar. Enforce Creator-plan CLI OAuth, the configured Digital Twin, local IndexTTS2 narration, Avatar III for an unspecified digital human but Avatar V whenever the named preset 数字人5 is requested, adaptive face measurement plus the approved human-reviewed visual-centering offset in the headroom_08 circular bottom-left layout unless full-screen is explicitly requested, subtitle-safe placement, credit-aware master reuse, final QC/archive routing, and mandatory pairing with `heygen-avatar-motion` before any motion prompt or paid generation.
Repository: Pluviobyte/rnskill
GitHub stars: 1,725Updated: Jul 27, 2026
No.: 3,155
chatcut-plugin-basicsChatCut basics for tests
Repository: RongleCat/grok-app
GitHub stars: 1,518Updated: Aug 1, 2026
No.: 3,156
guochao-visual-cn国潮/国风视觉生成助手。当用户要"国潮风""中国风插画""国漫风格""水墨风""新中式设计""古风头像""国风配图""汉服插画""传统文化海报"时使用。内置 12 种中国美学画风配方，输出可直接复制到 Midjourney/即梦/可灵/Nano Banana 的提示词。
Skill content language: Chinese
Repository: sanhuang520-ship-it/awesome-chinese-ai-tools
GitHub stars: 11Updated: Aug 12, 2026
No.: 3,157
load-and-testRebuild CDS artifacts, reload SQLite fixture data, and run the full test suite. Use after schema or service changes.
Repository: SAP-samples/cloud-cap-hana-swapi
GitHub stars: 89Updated: Apr 22, 2026
No.: 3,158
cpp-oop-designEnforce clear abstraction and good OOP for C++ code in this repository: reject one-shot helpers, prefer composition over inheritance, separate interface from implementation, apply the right design pattern (Strategy, Factory, Observer, Adapter, Builder, Pimpl, Visitor, Chain, Command, Decorator) when the situation calls for it, and keep modules behind narrow public headers. Use when designing a new module, adding a new class or interface, refactoring duplicated logic, reviewing PR design choices, or when the user mentions abstraction, design pattern, refactor, OOP, interface, SOLID, or DRY.
Repository: sek788432/Stock-Back-Test-System
GitHub stars: 6Updated: Aug 28, 2026
No.: 3,159
miniprogram-developmentWeChat Mini Program development skill for building, debugging, previewing, testing, publishing, and optimizing mini program projects (小程序开发、调试、预览、发布). Covers project structure and config (`project.config.json`, `appid`, `miniprogramRoot`, `tabBar`, routing/navigation, icon assets), WeChat Developer Tools Nightly workflows (`wechatide` CLI, WeChat IDE Skills/MCP), `miniprogram-ci` preview/upload, console/network debugging, message push (消息推送) and customer-service auto-reply (客服消息), mini program SEO / search indexing (小程序搜索优化、页面收录、搜索推广、mpcrawler), and CloudBase integration (`wx.cloud`, 腾讯云开发, 云开发) when explicitly used. Use when users create, develop, modify, debug, preview, deploy, publish, or promote WeChat Mini Programs. NOT for Web frontend (use web-development), pure backend services (use cloudrun-development / cloud-functions), or UI-design-only tasks (use ui-design).
Repository: TencentCloudBase/CloudBase-AI-Toolkit
GitHub stars: 1,159Updated: Nov 4, 2026
No.: 3,160
water-wastewater-treatment-operatorUse when a task needs the judgment of a Water and Wastewater Treatment Plant Operator — diagnosing a rising effluent BOD/turbidity trend before it breaches an NPDES or SDWA limit, deciding how to respond to a SCADA alarm, calculating chlorine CT value or F:M ratio to correct a process, or triaging a storm-driven hydraulic overload.
Repository: wonsukchoi/domain-experts
GitHub stars: 24Updated: Jul 14, 2026
No.: 3,161
auto-editor-exportExport auto-editor's edit or microphone recording to a video editor (Premiere, DaVinci Resolve, Final Cut Pro, ShotCut, Kdenlive), to individual clips, or to auto-editor timeline files (.v1/.v2/.v3); and import timeline/XML files to render them. Use when someone wants an editor-ready project, a preserved microphone source, split clips, or timeline files instead of a finished video.
Repository: WyattBlue/auto-editor
GitHub stars: 5,780Updated: Oct 31, 2026
No.: 3,162
docx创建、编辑、校验和转换 Word DOCX，支持把完整 LaTeX 论文转换为 DOCX，以及数学建模论文模板、原生公式、三线表、修订和批注。
Skill content language: Chinese
Repository: XiaoMaColtAI/math-modeling-skill
GitHub stars: 1,897Updated: Sep 6, 2026
No.: 3,163
math-mistake-review-skill将初中数学错题照片转化为结构化复习素材。接收用户上传的错题图片（含原题与标答），自动还原题目、分析核心考点、指出破题关键、还原答案解析，并生成2道同维度变式训练题及SVG几何示意图。基于2025-2026年中考数学考纲对齐知识点。适用于初中数学错题整理、中考数学复习、数学变式训练生成、几何题目SVG绘图、错题本制作等场景。
Skill content language: Chinese
Repository: XingS117/math-mistake-review-skill
GitHub stars: 1Updated: May 24, 2026
No.: 3,164
book2skillConvert one or more TXT, Markdown, DOCX, or PDF documents into a reusable skill zip backed by normalized Markdown, extracted images, and a grounded JSONL knowledge index. Invoke this skill before inspecting task files, then execute its workflow directly without listing directories.
Repository: zhimaAi/chatwiki
GitHub stars: 2,104Updated: Aug 14, 2026
No.: 3,165
oh-story-claudecode-writing网文写作 skill 包，覆盖长篇与短篇网络小说的扫榜、拆文、写作、去AI味全流程
Repository: reason-machines/trending-skills
GitHub stars: 89Updated: Apr 27, 2026
No.: 3,166
token-budget-advisor回答する前に、どれだけの回答深度を消費するかについてユーザーに情報に基づいた選択を提供する。ユーザーが回答の長さ、深さ、またはトークンバジェットを明示的に制御したい場合にこのスキルを使用する。トリガー条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas"、またはユーザーが回答のサイズや深さの制御を明示的に求めるその他の明確なバリエーション。トリガーしない条件：ユーザーが現在のセッションでレベルを指定済み（そのレベルを維持）、リクエストが明らかに一言の回答、または「token」が認証/セッション/支払いトークンを指している。
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Jul 17, 2026
No.: 3,167
visa-doc-translateビザ申請書類（画像）を英語に翻訳し、原文と翻訳を含むバイリンガルPDFを作成する
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: May 17, 2026
No.: 3,168
frontend-patternsReact, Next.js, state yönetimi, performans optimizasyonu ve UI en iyi uygulamaları için frontend geliştirme kalıpları.
Skill content language: Turkish
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Jun 7, 2026
No.: 3,169
x-card当需要用 @ant-design/x-card 让 AI Agent 动态渲染富交互 UI 时使用——涵盖 XCard.Box、XCard.Card、A2UI v0.9 命令、数据绑定、Catalog、Actions 和流式渲染模式。
Skill content language: Chinese
Repository: ant-design/x
GitHub stars: 4,836Updated: Oct 29, 2026
No.: 3,170
startup-ceoCEO coordinator that dispatches research, strategy, finance, and writer specialists via A2A and synthesizes their findings into a GO/NO-GO investment briefing. Use for multi-agent advisory workflows.
Repository: Atmosphere/atmosphere
GitHub stars: 3,830Updated: May 5, 2026
No.: 3,171
abaqus-fieldDefine initial conditions and predefined fields. Use when user mentions initial temperature, pre-stress, residual stress, or import from previous analysis.
Repository: Cai-aa/CAE-Agent-Hub
GitHub stars: 1,277Updated: May 19, 2026
No.: 3,172
fengge-perspective峰哥亡命天涯（周丽峰）的思维框架与表达方式。基于36氪深度访谈、腾讯新闻三篇人物报道、 B站官方账号视频、微博长文《妙瓦底生死36小时》、维基百科与20+一手来源的深度调研，提炼6个核心心智模型、8条决策启发式和完整的表达DNA。用途：作为思维顾问，用峰哥的视角分析内容创作、纪录片选题、采访方法、社会观察等问题。当用户提到「用峰哥的视角」「峰哥会怎么看」「峰哥模式」「fengge perspective」时使用。即使用户只是说「帮我用峰哥的角度想想」「如果峰哥会怎么拍」「切换到峰哥」也应触发。
Skill content language: Chinese
Repository: collabH/bigdata-growth
GitHub stars: 1,841Updated: Apr 11, 2026
No.: 3,173
web-design网页设计与部署。生成精美的单页 HTML 网页（报告、落地页、数据可视化等），支持一键部署到 Cloudflare Pages。使用 Tailwind CSS + Chart.js + Font Awesome 技术栈。当用户要求制作网页、生成报告页面、创建落地页、数据可视化展示、部署网页到线上时使用。
Skill content language: Chinese
Repository: countbot-ai/CountBot
GitHub stars: 783Updated: Mar 4, 2026
No.: 3,174
ielts-speaking-candidate-simulationSimulate an IELTS Speaking candidate, specifically excelling at Part 2 cue cards by addressing all bullet points, while handling Part 3 discussions with natural, fluent English.
Repository: ECNU-ICALK/AutoSkill
GitHub stars: 610Updated: Mar 13, 2026
No.: 3,175
game-balance-calculatorCalculate and optimize game economy balance, weapon stats, and progression curves
Repository: Eli-yu-first/skillshub
GitHub stars: 7Updated: Feb 28, 2026
No.: 3,176
analytical-method-validationPlans, executes, and documents validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP <1220>/<1225>/<1226>, ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. Use for HPLC, LC-MS/MS, GC, CE, ICP-MS, dissolution, qNMR, qPCR, NIR, and ligand binding or cell-based assays whenever the question is whether a procedure is fit for its intended purpose. Triggers include "method validation", "analytical method validation", "AMV", "validation protocol", "acceptance criteria", "linearity", "reportable range", "accuracy and precision", "repeatability", "intermediate precision", "recovery", "LOD", "LOQ", "detection limit", "quantitation limit", "specificity", "robustness", "method transfer", "method comparison", "Deming", "Passing-Bablok", "Bland-Altman", "equivalence testing", "OOS investigation", "ICH Q2", "Q2(R2)", "Q14", "USP 1225", "ICH M10", "incurred sample reanalysis", "ISR", "CLSI EP", and any request to show that an assay works.
Repository: K-Dense-AI/scientific-agent-skills
GitHub stars: 56,174Updated: Oct 1, 2026
No.: 3,177
defuddleExtract clean Markdown from HTML pages with Defuddle CLI.
Repository: kepano/obsidian-skills
GitHub stars: 50,790Updated: Sep 9, 2026
No.: 3,178
ecommerce-marketing-strategy-builderFull-stack e-commerce marketing strategy builder. Analyzes your product, market, and competitors, then builds a complete omnichannel marketing plan covering paid ads, SEO, email/SMS, content marketing, social media, influencer partnerships, and referral programs. Includes target audience persona, competitive landscape, channel prioritization with budget allocation, content direction, and a 90-day action plan. Works for any e-commerce platform — Shopify, Amazon, Etsy, WooCommerce, TikTok Shop, and more. No API key required.
Repository: LeoYeAI/openclaw-master-skills
GitHub stars: 2,169Updated: Jun 15, 2026
No.: 3,179
system-oneDesign, integrate, evaluate, self-host, and troubleshoot typed System One decision models including TypeSafe Jev, Convai Innovations Laya, CLM, and experimental Strands Decider. Use for Choice/Score/Noul judgments and experimental Jev image/Box queries inside deterministic software, app-control loops, routing, ranking, guardrails, calibration, semantic code linting and post-edit feedback, DevOps decision support, confidence-based escalation, or private open-model inference. Do not use for syntactic/style linting, exact policy or authorization, open-ended generation, or generic LLM serving without a bounded decision contract.
Repository: magnus919/agent-skills
GitHub stars: 161Updated: Oct 15, 2026
No.: 3,180
autoresearchOrchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Repository: Orchestra-Research/AI-Research-SKILLs
GitHub stars: 14,288Updated: Mar 24, 2026
No.: 3,181
planning-with-files-zh用于多步骤 AI 代理工作的持久化文件规划系统。将 task_plan.md、findings.md 和 progress.md 保存在磁盘上，生命周期钩子会注入选定的项目规划上下文。自动恢复只读取项目规划文件。只有显式运行 session-catchup.py --metadata 才会检查本机同项目的会话元数据；--replay 可输出有长度限制且由 nonce 框定的同项目摘录。可选门禁仅在宿主支持时请求继续，绝不执行 Markdown 中声明的命令。本技能没有网络上传路径。适用于研究或需要 5 次以上工具调用的工作。触发词：任务规划、项目计划、制定计划、分解任务、多步骤规划、进度跟踪、文件规划、帮我规划、拆解项目
Skill content language: Chinese
Repository: OthmanAdi/planning-with-files
GitHub stars: 27,897Updated: Nov 4, 2026
No.: 3,182
tim-mediastorm以影视飓风创始人Tim（潘天鸿）的写作风格撰写文章或文案。仅在用户明确要求使用 Tim 风格、影视飓风风格撰写内容时触发。适用场景：(1) 公众号文章，(2) 视频文案/脚本，(3) 演讲稿， (4) 其他需要 Tim 风格的文字内容。不在一般性写作请求中自动激活——用户必须明确指定 Tim 或影视飓风风格。
Skill content language: Chinese
Repository: phaseddd/PhasedddSkill
GitHub stars: 89Updated: Mar 29, 2026
No.: 3,183
us-stock-analysisComprehensive US stock analysis including fundamental analysis (financial metrics, business quality, valuation), technical analysis (indicators, chart patterns, support/resistance), stock comparisons, and investment report generation. Use when user requests analysis of US stock tickers (e.g., "analyze AAPL", "compare TSLA vs NVDA", "give me a report on Microsoft"), evaluation of financial metrics, technical chart analysis, or investment recommendations for American stocks.
Repository: tradermonty/claude-trading-skills
GitHub stars: 3,641Updated: Mar 10, 2026
No.: 3,184
render-htmlRender an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Use when the user says "渲染 HTML", "出一份 HTML 报告", "render html", "make this readable", "export to html", or wants a polished web-rendered view of a Markdown artifact.
Repository: wanshuiyin/Auto-claude-code-research-in-sleep
GitHub stars: 18,702Updated: Oct 19, 2026
No.: 3,185
zach-search-term-report-analyzer分析 Amazon Ads SP / SB / SD 搜索词报告。确定性脚本负责清洗、时间窗聚合、词根聚类和决策计算，AI 助手或人工负责词根级语义分类；通过词根继承减少长尾词的待判定比例，输出 Markdown、CSV、HTML 和 JSON 六类结果。使用时机：判断搜索词是否应该否定、控成本、继续测试或放量，分析 7/14/30 天 CVR 与 ACOS 变化，或者提炼可反馈给 Listing 的属性词和场景词。触发词：/zach-search-term-report-analyzer
Skill content language: Chinese
Repository: zach22-1999/amazon-skills
GitHub stars: 246Updated: Oct 15, 2026
No.: 3,186
wps-dbsheetCRUD operations on WPS smart sheets (数据表/多维表格/dbsheet) via wpsx. Use for querying/inserting/updating records, fields, sheet structures, imports, table management, or prompts about 多维表格/数据表/记录/字段.
Skill content language: Chinese
Repository: zhu327/wpsx
GitHub stars: 1Updated: Jun 10, 2026
No.: 3,187
public-space-designDesign parks, plazas, waterfronts, pocket parks, civic spaces, playgrounds, and urban gardens using Jan Gehl quality criteria, PPS placemaking methodology, and global best practices. Use when the user asks to design a park, create a plaza, plan a waterfront, design a civic space, lay out a playground, plan a community garden, create an outdoor gathering space, design a public realm strategy, or improve an existing public space. Also use when discussing public space programming, activation strategies, or landscape design at the urban scale.
Repository: Abhinavbwj/Urban-Design-Skills-Claude
GitHub stars: 137Updated: Feb 28, 2026
No.: 3,188
code-tour创建 CodeTour `.tour` 文件——针对特定角色的、带有真实文件和行锚点的逐步演练。用于入职引导、架构演练、PR 演练、RCA 演练以及结构化的“解释其工作原理”请求。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: May 11, 2026
No.: 3,189
tavern-uiSillyTavern 前端界面开发（HTML/CSS/JS/Vue 3）。当用户需要开发酒馆消息楼层内渲染的前端 UI（状态栏、复杂交互界面、Vue 3 组件、CSS 布局与动画），或处理界面正则占位、tavern_helper_template 构建打包与 jsdelivr 部署、本地实时预览时调用。涵盖设计原则、色彩变量规范与 MVU 变量读取。
Skill content language: Chinese
Repository: ai4rpg/tavern-cards
GitHub stars: 264Updated: Sep 18, 2026
No.: 3,190
catia-v5-mcp-maintainerMaintain daiemon12/catia-v5-mcp-server against a production reliability contract. Use when changing tool schemas or implementations, COM execution, session health, structured results, object handles, topology references, recovery, diagnostics, CAA bridge integration, or regression evaluation. Requires source-first changes, truthful schemas, deterministic failure behavior, and live CATIA validation for COM/BRep semantics.
Repository: daiemon12/catia-v5-mcp-server
GitHub stars: 151Updated: Aug 20, 2026
No.: 3,191
review-responseSystematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "write rebuttal", "respond to reviewers", "draft review response", or "analyze review comments". Improves paper acceptance rates.
Repository: Galaxy-Dawn/claude-scholar
GitHub stars: 5,996Updated: May 13, 2026
No.: 3,192
ai-content-detectorAI内容检测技能，辅助使用多个免费平台进行AI率检测并多方对比。触发关键词：AI检测、AI率、检测AI、AI内容检测、查AI、AI生成检测。功能：文本预处理、平台指南、结果汇总、综合报告生成。支持ZeroGPT、Writer、Content at Scale、Sapling等免费检测工具。
Skill content language: Chinese
Repository: Jieice/ai-novel-writer
GitHub stars: 122Updated: Apr 22, 2026
No.: 3,193
ljg-roundtable一个议题，一场圆桌：主持人请来 3-5 位真实人物，定义开场，逐轮交锋，每轮收一张 ASCII 结构图，用户用指令控节奏（可/止/深入此节/引入新人物），散场后全文存入 Markdown 笔记。Use when user says "圆桌讨论", "圆桌", "roundtable", "辩论", or wants to explore a topic through multi-perspective structured debate.
Skill content language: Chinese
Repository: lijigang/ljg-skills
GitHub stars: 7,630Updated: Oct 26, 2026
No.: 3,194
budget-builderBuild a realistic personal monthly budget from someone's income and expenses. Use when asked to make a budget, plan monthly spending, allocate income, or get finances under control. Produces a categorized budget (a 50/30/20-style allocation tuned to their reality), a surplus/shortfall number, and concrete next moves. Educational, not regulated financial advice.
Repository: mohitagw15856/pm-claude-skills
GitHub stars: 1,320Updated: Jul 14, 2026
No.: 3,195
writing-humanitiesUse when writing humanities or social science papers - provides discipline-specific writing guidance
Skill content language: Chinese
Repository: Norman-bury/research-writing-skill
GitHub stars: 3,593Updated: Mar 29, 2026
No.: 3,196
slimeRL post-training for LLMs with Megatron and SGLang.
Repository: NousResearch/hermes-agent
GitHub stars: 260,788Updated: Aug 8, 2026
No.: 3,197
evolving-ai-agentsProvides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
Repository: Orchestra-Research/AI-Research-SKILLs
GitHub stars: 14,288Updated: Apr 7, 2026
No.: 3,198
word-document-processorComprehensive word document processing with full format support. Handles creation, editing, formatting preservation, tracked changes, and metadata management.
Repository: qodex-ai/ai-agent-skills
GitHub stars: 45Updated: Jan 5, 2026
No.: 3,199
daily-reviewA股每日复盘（专业版）— 基于 QuantDB 本地数据 + 当日新闻情绪 + 模型推理信号 + L1/L2 因子截面 + 板块资金流的盘后复盘：指数、涨跌结构与涨停梯队、量能、行业/概念轮动、资金面、L2 微观结构、当日有新闻股票匹配、模型推理信号复盘（昨日推理命中率 + 明日信号Top5）、次日走势方向研判（六维信号加权 → 明确方向+置信度）。用户说「复盘」「每日复盘」「复盘某天」时使用：跑取数脚本（daily_review + news_review）→ 按模板写复盘报告 → 转 PDF → 落盘股票报告目录 → 聊天回复速览。触发词：复盘、每日复盘、今日复盘、盘后复盘、复盘20260814
Skill content language: Chinese
Repository: qusong0627/QuantMind
GitHub stars: 1,874Updated: Oct 31, 2026
No.: 3,200
sphinx-fixDiagnose a failing Ray Sphinx / Read the Docs documentation build. Parses the Sphinx warning stream (an RtD build log, a local build, or pasted text), classifies each warning against a rules table, and proposes the canonical fix in severity-tier order. Detects a hard-broken build, segregates known-benign suppressed classes, and lists every unclassified warning. Use when a `docs/readthedocs.com:anyscale-ray` check fails, when asked "why is the docs build failing?" or "what warning is breaking this PR?", or to turn a Sphinx warning dump into an ordered fix list.
Repository: ray-project/ray
GitHub stars: 44,211Updated: Aug 19, 2026