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.
16,653 skills from 551 repositories · updated 29 minutes ago
3,174 skills
- tellsAThevon/genjutsuInternal genjutsu module - the reflexes a model falls into when nothing asked for them (invented data, decorative filler, converged layouts, hollow copy), each named by its evidence and a question back to the validated thesis. Loaded by cast and paint on web stacks, after the thesis gate.OtherNo warnings★ 650↓ —
- notaireromainsimon/paperasseNotaire IA pour le droit immobilier, les successions, les donations, le droit de la famille et le droit des sociétés en France. Copilote juridique pour la préparation d'actes, le conseil patrimonial, les calculs de frais et la vérification de conformité. Couvre le calcul des frais de notaire (DMTO, émoluments, débours, CSI), la plus-value immobilière, les droits de succession et donation, le démembrement, les contrats de mariage, les PACS, les SCI, et la rédaction de projets d'actes (compromis, statuts, testaments). Triggers: notaire, frais de notaire, acte de vente, compromis, succession, donation, héritage, testament, PACS, contrat de mariage, SCI, plus-value immobilière, droits de mutation, DMTO, usufruit, nue-propriété, partage successoral, réserve héréditaire, viager, donation-partage, diagnostics immobilier, droit de préemption, acte notarié, droit immobilierOtherNo warnings★ 2.6K↓ —
- rag-evalagentscope-ai/OpenJudgeUse when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or "is my RAG pipeline working." Outputs a diagnostic matrix that pinpoints whether problems are in retrieval or generation.OtherNo warnings★ 887↓ —
- backup-recoveryBagelHole/DevOps-Security-Agent-SkillsImplement backup and recovery strategies. Configure rsync, Restic, and cloud backups. Use when designing data protection solutions.OtherNo warnings★ 1.2K↓ —
- reverse-proxyBagelHole/DevOps-Security-Agent-SkillsConfigure nginx and Traefik as reverse proxies. Implement SSL termination and routing. Use when setting up application gateways.OtherNo warnings★ 1.2K↓ —
- baidu-searchcountbot-ai/CountBot百度 AI 搜索。支持网页搜索、百度百科、秒懂百科、AI 智能生成四种模式。自动包含当前日期上下文。当用户要求搜索信息、查询百科、获取最新资讯、搜索新闻、查找资料时使用。OtherNo warnings★ 782↓ —
- systemd-servicesBagelHole/DevOps-Security-Agent-SkillsCreate and manage systemd services and timers. Configure service dependencies and resource limits. Use when managing system services.OtherNo warnings★ 1.2K↓ —
- away-briefsno-ai/sno-station-skillsGive the owner one page when they come back from sleep, a meeting or a long run: what got done, what is stuck, what waits for their answer, and what it cost in quota. Use when the owner asks what happened while they were away, wants a status page, or when you finish a long stretch of work and must report it.OtherNo warnings★ 638↓ —
- agent-relayAgentWorkforce/relayUse when you need Codex to coordinate multiple agents through Agent Relay for peer-to-peer messaging, lead/worker handoffs, or shared status tracking across sub-agents and terminals.OtherNo warnings★ 893↓ —
- plsno-ai/sno-station-skillsMANUAL-ONLY — load solely when the human owner types `/pl`, uses `$pl`, or asks you to act as the Project Lead (PL). Supervise one project lane and its executor agents. A charter or dispatch means: you are an EXECUTOR, not the PL.OtherNo warnings★ 638↓ —
- medicsno-ai/sno-station-skillsCheck that this machine's agent team can work and say what is wrong in plain lines: tools installed, core skills installed, skill commands runnable, hooks configured, Reach seat live, a heartbeat running, both vendors' quota readable, temp space free. Checks only, never repairs. Use on a new machine, when agents stop reaching each other or a long run fails to start, or when the owner asks whether everything is healthy.OtherNo warnings★ 638↓ —
- swiftui-graphicsAThevon/genjutsuAdvanced SwiftUI visuals - Metal shaders (.colorEffect, .layerEffect, .distortionEffect), .visualEffect, Liquid Glass (iOS 26), Canvas, holographic and CRT effects.OtherNo warnings★ 650↓ —
- cron-managercountbot-ai/CountBot定时任务管理。创建、查看、修改、删除定时任务，管理任务会话数据。当用户需要设置提醒、定时执行任务、管理调度计划时使用。OtherNo warnings★ 782↓ —
- load-balancingBagelHole/DevOps-Security-Agent-SkillsConfigure load balancers and traffic distribution. Implement health checks and SSL termination. Use when distributing traffic across servers.OtherNo warnings★ 1.2K↓ —
- performance-tuningBagelHole/DevOps-Security-Agent-SkillsOptimize Linux system performance. Configure kernel parameters, analyze bottlenecks, and tune resources. Use when improving system performance.OtherNo warnings★ 1.2K↓ —
- ima-knowledge-basecountbot-ai/CountBot通过 IMA OpenAPI 处理知识库任务。支持知识库内容搜索、命中详情查看、条目浏览、列出知识库、上传文件、导入网页。用户提到知识库、资料库、上传到知识库、导入网页、搜知识库时使用。OtherNo warnings★ 782↓ —
- github-discussion-to-devrel-contentVarnan-Tech/opendirectoryFind recurring confusion in your repo's GitHub Discussions, rank it by urgency, and draft the actual docs fixes and content angles — with verbatim community quotes and source links as evidence.OtherNo warnings★ 685↓ —
- agent-team-managercountbot-ai/CountBot多智能体团队管理。创建、查看、修改、删除 CountBot 的多智能体团队，管理团队成员（角色）和团队级自定义模型配置。当用户要新建 Pipeline/Graph/Council 团队、调整成员分工、修改依赖关系、开关技能系统、设置团队专属模型时使用。OtherNo warnings★ 782↓ —
- redisBagelHole/DevOps-Security-Agent-SkillsConfigure Redis for caching and data storage. Set up clustering, persistence, and Sentinel. Use when implementing Redis caching or queues.OtherNo warnings★ 1.2K↓ —
- framer-motionAThevon/genjutsuFramer Motion / Motion sub-skill - AnimatePresence, layout animations, gestures, motion values.OtherNo warnings★ 650↓ —
- crackethanplusai/codex-on-crackLead substantial Codex builds with one configured implementation worker and lead acceptance. Use when the user requests codex-on-crack, names a model to delegate work to, asks to run subagents through Claude, or requests a lead/worker split. Keep host-only work direct; honor explicit external model choices. Workers must not invoke this orchestrator.OtherNo warnings★ 765↓ —
- startup-it-troubleshootingBagelHole/DevOps-Security-Agent-SkillsPractical IT troubleshooting playbooks for small teams without dedicated IT staff.OtherNo warnings★ 1.2K↓ —
- canvas-generativeAThevon/genjutsuAlgorithmic and generative art with Canvas 2D - particles, flow fields, noise, fractals, L-systems.OtherNo warnings★ 650↓ —
- model-selectionawslabs/agent-pluginsSelects a base model for the user's use case by querying SageMaker Hub. Use when the user asks which model to use, wants to select or change their base model, mentions a model name or family (e.g., "Llama", "Mistral", "Nova"), or wants to evaluate a base model — always activate even for known model names because the exact Hub model ID must be resolved. Queries available models, presents benchmarks and licenses, and confirms selection.OtherNo warnings★ 927↓ —