Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,352 skills from 2,375 repositories · updated 10 minutes ago
10,613 skills
- sales-qualificationliqiongyu/lenny_skills_plusBuild a Sales Qualification Pack (ICP, scorecard, discovery script, pipeline hygiene rules).OtherNo warnings★ 52↓ —
- live-stream-clipsxianyu110/ecommerce-video-skills直播切片：从电商直播录屏中找出高光片段（按时间戳 / 按字幕关键词 / 按停顿自动提议），批量导出 9:16 竖屏切片，自动模糊填充横屏画面、烧录标题与字幕、响度标准化，并给切片写标题与开头钩子。Use when the user has a livestream recording and wants 直播切片, 切片, highlights, clips, 高光片段, repurpose a live stream into short videos for 抖音 / 视频号 / TikTok.OtherNo warnings★ 117↓ —
- multimodal-genaAAaqwq/AGI-Super-Team多模态内容生成（图片、视频）。当用户需要生成图片、生成图像、生成视频、AI绘画、AI作图、画一张图、做个视频、文生图、文生视频时使用此技能。自动调用 multimodal-agent 进行生成。OtherNo warnings★ 112↓ —
- fair-simulation-packagerHeshamFS/materials-simulation-skillsCreate FAIR-minded reproducibility bundles for materials simulations by collecting input/output file inventories, hashes, units, engine versions, structure identifiers, provenance, and NOMAD/OPTIMADE/Materials Project friendly metadata. Use before publishing, sharing, archiving, or handing simulation results to another agent.OtherNo warnings★ 83↓ —
- skill-retrievalmoonlight-lupin/agent-skillsBM25-based skill retrieval plugin for Hermes Agent. Replaces the full skill list in the system prompt with a names-only compact view (~2K tokens) and injects top-K relevant skill descriptions per turn via BM25 retrieval (~300 tokens). Saves ~9K tokens/turn. Use when system prompt token overhead from skills is a concern, or when skill discovery quality matters.OtherNo warnings★ 115↓ —
- kai-retrocgallic/kai-cmo-harnessRun a learning retrospective on the Kai harness. Mines gate-failure logs and 30-day performance results into lessons, triages candidate lessons (promote/keep/retire), and graduates repeated lessons into enforced gate checks with golden corpus cases. Use when "retro", "what have we learned", "triage lessons", "promote lessons", "why does this keep failing", "harness retrospective", or monthly / after any heavy content sprint.OtherNo warnings★ 61↓ —Also in 1 other repo
- convergence-studyHeshamFS/materials-simulation-skillsPerform spatial and temporal convergence analysis for solution verification — compute observed convergence orders from grid or timestep refinement studies, apply Richardson extrapolation to estimate discretization error, and calculate the Grid Convergence Index (GCI) per ASME V&V 20 standards. Use when verifying that a numerical solution converges at the expected rate, estimating the error on the finest mesh, checking whether grids are in the asymptotic range, or preparing formal verification reports, even if the user only asks "is my mesh fine enough" or "how accurate is my solution."OtherNo warnings★ 83↓ —
- feishu-channelaAAaqwq/AGI-Super-Team飞书 (Lark/Feishu) 与 OpenClaw 的双向集成通道。通过飞书机器人实现消息的接收和发送，支持私聊、群聊、@提及检测、卡片消息、文件传输。当需要通过飞书与 AI 助手交互、接收飞书消息触发 AI 响应、或从 OpenClaw 发送消息到飞书时使用此技能。与 feishu-automation 的区别：本 skill 专注于消息通道集成，feishu-automation 专注于飞书平台自动化操作（多维表格、文档等）。OtherNo warnings★ 112↓ —
- jamescameron-perspectivemomozi1996/DirectorAgents詹姆斯·卡梅隆导演风格顾问——技术先驱的感官革命。 核心特征：技术先驱、极致震撼 代表作品：《阿凡达》《泰坦尼克号》 触发词：「詹姆斯·卡梅隆风格」「像詹姆斯·卡梅隆那样拍」「詹姆斯·卡梅隆视角」 适用场景：剧本创作、影像设计、叙事决策、风格参考OtherNo warnings★ 64↓ —
- dsh-marker-readerDeadHead04/skillEdDecode the marker fixture used by the DeepSeek Harness integration example.OtherNo warnings★ 74↓ —
- optimizingOdradekAI/bundles-forgeUse when optimizing a bundle-plugin or single skill — improving descriptions, reducing tokens, fixing audit findings, restructuring workflows, adding skills to fill gaps, or iterating on user feedbackOtherNo warnings★ 227↓ —
- openai-webhookshookdeck/webhook-skillsReceive and verify OpenAI webhooks. Use when setting up OpenAI webhook handlers for fine-tuning jobs, batch completions, or async events like fine_tuning.job.completed, batch.completed, or realtime.call.incoming.OtherNo warnings★ 97↓ —
- finishedscdenney/open-science-skillsEnd-of-session closure. Records what changed into the project's own handoff and log files, separating verified from attempted work, and reports what is uncommitted. Use when wrapping up a session. Twin of sitrep.OtherNo warnings★ 69↓ —
- single-path-process-dioramaZSeven-W/craft-skills将 3–5 步线性流程制作成单张完整、非宫格的微缩剧场成品。适用于流程故事封面、制作过程图、软件交付旅程与科普式微缩场景；以单一路径、可追踪载体、可辨识动作和题材匹配的材质表达顺序。不用于需要精确分支和数据尺度的流程图、实际操作规程或普通城市微缩景观。OtherNo warnings★ 238↓ —
- math-tablecapwitf/My-MathModeling-skillsUse when 高教社杯/CUMCM 数学建模论文需要格式化、修复、压缩或审查符号表、记号表、结果表，包括单位清理、longtable、列宽平衡或按截图修排版。OtherNo warnings★ 57↓ —
- chenkaige-perspectivemomozi1996/DirectorAgents陈凯歌导演风格顾问——人文思辨与悲剧美学。 核心特征：诗意悲悯、历史个体冲突 代表作品：《霸王别姬》《黄土地》 触发词：「陈凯歌风格」「像陈凯歌那样拍」「陈凯歌视角」 适用场景：剧本创作、影像设计、叙事决策、风格参考OtherNo warnings★ 64↓ —
- light-consistencyLight0305/Light-skillsLight 跨材料一致性常驻机读门:在所有产出材料后台核查术语 / 指标(名+值)/ 创新点表述 / 方法名 在论文·PPT·软著·代码·项目文档之间是否统一,定义一改回扫所有已产出材料,把"各处说法对齐"从口头 建议落成**可机检、可阻断、可被总控 run_checkpoint 聚合的机读门**(产 light.findings.v1,术语/指标/ 创新点硬冲突 → Critical fail → exit 1)。何时用:任一材料产出或修改后、投稿/答辩/提交前的跨材料回扫、 受控定义(术语/指标/创新点)变更后。触发词:一致性 / 术语统一 / 指标对不上 / F1 vs 准确率 / 数值冲突 / 论文和PPT不一致 / 创新点表述 / 方法名 / 改名 / 软著与系统 / 术语表 / 回扫。核心纪律:事实源是项目 `.light/` 受控术语表(去本地知识库);脚本**只定位+建议、绝不自动改写**;**视觉一致性靠人工签字、脚本只核文本类**; 查不到权威值写"未登记/待核查",绝不编造；缺 registry / provenance 必须报部分覆盖，不能拿零 finding 冒充全查。OtherNo warnings★ 852↓ —
- Echo Skill Sampleai-sns/ai-snsEcho input parameters as JSON.OtherNo warnings★ 328↓ —
- stack-pushathola/claude-night-marketPushes all branches in a stack and opens or updates one dependent PR per slice. Use after stack-create to publish the stack or after adding commits to a slice.OtherReview first★ 347↓ —
- agorageekjourneyx/agoraAgora — Intelligent router for the full deliberation ecosystem. Analyzes your question, routes to the right Room, or lists all available rooms. 6 rooms, 31 thinkers, one entry point.OtherNo warnings★ 170↓ —
- brand-positioningcofoundy/brand-skillsDefine and sharpen a brand's market positioning — where it sits relative to competitors, what it owns, and how it differentiates. Use when the user says "brand positioning", "positioning statement", "where do we sit in the market", "how are we different", "differentiation strategy", "positioning map", "competitive positioning", "what space do we own", "brand territory", "we're too similar to competitors", "help me position this brand", or wants to find a defensible place in a crowded category.OtherNo warnings★ 68↓ —
- andreitarkovsky-perspectivemomozi1996/DirectorAgents安德烈·塔可夫斯基导演风格顾问——神性静观的电影雕刻。 核心特征：雕刻时光、精神力量 代表作品：《潜行者》《镜子》 触发词：「安德烈·塔可夫斯基风格」「像安德烈·塔可夫斯基那样拍」「安德烈·塔可夫斯基视角」 适用场景：剧本创作、影像设计、叙事决策、风格参考OtherNo warnings★ 64↓ —
- a-fund-monitoraAAaqwq/AGI-Super-TeamA股基金净值监控：盘中实时估值 + 盘后实际净值，定时推送到 Telegram。OtherNo warnings★ 112↓ —
- math-hubcapwitf/My-MathModeling-skillsUse when 高教社杯/CUMCM 数学建模项目需要竞赛级范围控制、轻量 hub 状态、当前分问交付物锁定、文献启发式解题路线、结论/证据一致性、数学核验、结果一致性审查、官方规则合规、AI 使用披露跟踪、最终提交门禁或明确任务派发。OtherNo warnings★ 57↓ —
pay
runxhq/runx
OtherUpdated yesterday
From the author
Pay one exact resource with your held x402 wallet or approved Link MPP authorization, within the supplied terms and native authority.
Install
npx skills add runxhq/runx --skill pay -a claude-code
Installs to .claude/skills/pay/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Runs bundled scriptsNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 77
Security85
Provenance64
Maintenance100
Licence100
Adoption35
Files (12)
- SKILL.md
- fixtures/composes-in-graph.yaml
- fixtures/hosted-contract.yaml
- fixtures/refuses-budget.yaml
- fixtures/refuses-currency.yaml
- fixtures/refuses-resource.yaml
- fixtures/support/composed.graph
- payment.mjs
- readback.mjs
- readback.test.mjs
- references/catalog.md
- run.yaml