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.
49,450 skills from 2,407 repositories · updated 31 minutes ago
48,350 skills
- metric-designagentscope-ai/OpenJudgeUse when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader selection, metric design, judge prompt engineering, rubric design, evaluation pipeline code, or "how to evaluate [X] automatically." Outputs executable OpenJudge pipeline code.DesignNo warnings★ 1.1K↓ —
- devops-infrastructureCloudAI-X/claude-workflow-v2Guides Docker, CI/CD pipelines, deployment strategies, infrastructure as code, and observability setup. Use when writing Dockerfiles, configuring GitHub Actions, planning deployments, setting up monitoring, or when asked about containers, pipelines, Terraform, or production infrastructure.DevOpsNo warnings★ 1.4K↓ —
- web-developmentTencentCloudBase/CloudBase-AI-ToolkitUse when users need to implement, integrate, debug, build, deploy, or validate a Web frontend after the product direction is already clear, especially for React, Vue, Vite, browser flows, or CloudBase Web integration.DevOpsNo warnings★ 1.2K↓ —Also in 5 other repos
- 00-academic-routeragentscope-ai/OpenJudgeUse when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.ScienceNo warnings★ 1.1K↓ —
- minutes-recordsilverstein/minutesStart or stop recording a meeting, call, or voice memo. Use this whenever the user says "record", "start recording", "capture this meeting", "stop recording", "I'm in a meeting", "take notes on this call", or wants to transcribe live audio. Also use when they ask about recording status or want to know if something is being recorded.MediaNo warnings★ 1.6K↓ —Also in 1 other repo
- ai-model-webTencentCloudBase/CloudBase-AI-ToolkitUse this skill when a browser/Web app (React, Vue, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI, 页面, 前端, 网页) needs AI models via @cloudbase/js-sdk. Default routing for Web/frontend AI — call directly from the browser, do NOT propose a Node.js proxy. Covers generateText and streamText; models via ai.createModel with groups cloudbase, the legacy hunyuan-v3 / hunyuan-exp, or custom-*, model id in the `model` field. MUST run two-step preflight before code — see body. NOT for Node.js backend (use ai-model-nodejs), Mini Program (use ai-model-wechat), or image generation (Node SDK only).DesignNo warnings★ 1.2K↓ —
- agent-designeralirezarezvani/claude-skillsDesign multi-agent systems (supervisor, swarm, pipeline) and tool schemas; find bottlenecks in run logs. Use whenever agents split work or a run is slow or costly. Not for Claude Code workflow files (workflow-builder).DesignNo warnings★ 29.3K↓ —
- cloudbase-document-database-in-wechat-miniprogramTencentCloudBase/CloudBase-AI-ToolkitUse CloudBase document database WeChat MiniProgram SDK to query, create, update, and delete data. Supports complex queries, pagination, aggregation, and geolocation queries.DataNo warnings★ 1.2K↓ —Also in 5 other repos
- clerahashgraph-online/awesome-codex-pluginsConnect the user's AI client to the Clera MCP server and hire through it: search vetted startup candidates, screen them against a role, and request intros. Also covers the candidate side.OtherNo warnings★ 1.5K↓ —
- puahashgraph-online/awesome-codex-plugins强化高能动性和高压闭环执行的行为技能。适用于连续失败、原地打转、空口完成、 把问题甩给用户、没搜就猜、修完就停等场景，也支持手动通过 /pua 进入核心模式。OtherNo warnings★ 1.5K↓ —
- the-open-housemohitagw15856/pm-claude-skillsSimulate the open house and the listing agent's read of you — the questions that profile your budget and urgency, the staging that hides what inspection finds, and the offer-pressure choreography, run before you fall in love with anything. Use when asked what is the listing agent thinking, practice viewing a house, what should I not say at an open house, or simulate the offer pressure. Produces the walkthrough transcript with the agent's private profile of you, the what-the-staging-hides checklist, and a debrief on information discipline — what to ask, what to never volunteer.OtherNo warnings★ 1.5K↓ —
- repairhashgraph-online/awesome-codex-pluginsSafe maintenance for an existing docflow setup. Regenerates INDEX.md, installs or refreshes recognized DocFlow-managed helper scripts, runs link checks, and reports placeholder/validation issues. Use when docflow exists, after adding or renaming docs, or when doctor recommends repair.OtherNo warnings★ 1.5K↓ —
- momentum-mapmohitagw15856/pm-claude-skillsBreak a stuck, stalled week with three tiny wins sequenced for momentum — because motion creates motivation, not the other way around. Use when asked I'm in a rut, help me get unstuck this week, I've stalled on everything, or I need momentum. Produces three small, genuinely-achievable wins ordered so each fuels the next, a deliberately easy first one to prove motion is possible, the dopamine logic behind the sequence, and a reframe that you don't need motivation to start — starting creates it — turning a paralyzed week into a moving one.OtherNo warnings★ 1.5K↓ —
- oma-debugfirst-fluke/oh-my-agentDiagnose a reproducible failure, fix its cause, and verify the regression. Use for crashes, incorrect behavior, and failing tests.EngineeringNo warnings★ 1.4K↓ —
- senior-backendalirezarezvani/claude-skillsBuild and fix backend services: REST or GraphQL APIs, auth, microservices, PostgreSQL queries, migrations and load tests. Use whenever the user's API is slow or broken, needs login or auth added, a schema change, or a new endpoint or service scaffolded.TestingNo warnings★ 29.3K↓ —
- rag-architectalirezarezvani/claude-skillsDesign a RAG pipeline: chunk size, embedding model, vector database and retrieval quality metrics. Use whenever the user builds search over their docs, picks a vector store or finds answers miss the right context.PlanningNo warnings★ 29.3K↓ —
- openspec-archive-changeMemeMeow-Studio/MemeMeowArchive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.ProductivityNo warnings★ 1.3K↓ —Also in 1 other repo
- bug-triage-packmohitagw15856/pm-claude-skillsTriage a raw bug report into something a team can act on — clean repro steps, a defensible severity/priority, environment, likely area/owner, and duplicate check. Use when asked to triage this bug, set severity and priority, is this a P1, or clean up this bug report for the backlog. Produces the normalized repro, a severity and priority with the reasoning (impact × frequency × workaround), the environment/metadata, a suspected component and owner queue, and a duplicate/related-issue check — flagging when info is missing rather than guessing.OtherNo warnings★ 1.5K↓ —
- minimal-web-baas-demoTencentCloudBase/CloudBase-AI-ToolkitFast path for a minimal CloudBase Web + database demo (最小前后端 / 最小可用 fullstack / Lovable-like BaaS). Defaults to @cloudbase/js-sdk client CRUD (NoSQL app.database / PG app.rdb), MCP-only schema, preview-first, and forbids cloud functions unless secrets, cron/background jobs, or logic that security rules/RLS cannot express. Use for 搭一套 demo、留言板、Todo、Notes、Kanban, or when users say 带云函数+云数据库 but only need CRUD. NOT for production multi-service backends, CloudRun, WeChat Mini Programs, or tasks that truly need server secrets.SecurityNo warnings★ 1.2K↓ —Also in 5 other repos
- chatcut-plugin-basics-claudeUpdatedChatCut-Inc/agent-pluginUse for installing ChatCut (安装 ChatCut), recreating a viral or reference video with the user's own footage (recreate, clone, remake, 复刻爆款, 复刻视频, 做同款), and MANDATORY before hosted ChatCut video editing in Claude Code. Also use whenever video editing should stay editable in ChatCut, even if the user does not mention ChatCut: edit or cut a video (剪视频、剪辑), add captions or subtitles (加字幕), clean up a talking-head recording (剪口播), or add B-roll, music or motion graphics. Default new installations and generic source-video remakes to Desktop; honor user-selected Skills/workflows, existing Web projects and explicit Web requests. Covers hosted connection setup and editing tools.MediaNo warnings★ 1K↓ —
- cn-customs-docsmohitagw15856/pm-claude-skillsUse when asked 出口报关需要什么单证, 报关资料清单, 申报要素怎么填, 报关单和发票对不上, 出口退税需要的单证, 进口清关资料, or prepare customs documents for an export or import shipment in mainland China. Produces a document checklist for this shipment (报关单 data, 商业发票, 装箱单, 合同, 委托书, licences and certificates), a cross-document consistency check, the 申报要素 to prepare for the HS code, inspection and licence flags, the timeline with the customs broker, and the records to keep for the export rebate, all marked to confirm with the broker and customs.EngineeringNo warnings★ 1.5K↓ —
- image-to-uihashgraph-online/awesome-codex-pluginsRecreate an image, screenshot, or mockup as a 1:1 UI implementation. Match the reference rather than redesigning it, then render and compare the result to correct visible differences.DesignNo warnings★ 1.5K↓ —Also in 1 other repo
- wine-pairingmohitagw15856/pm-claude-skillsPick a wine that flatters tonight's meal — at your budget, from what's actually available — without the sommelier mystique. Use when asked what wine goes with [dish], help me pick a wine, what should I drink with dinner, or recommend a bottle for. Produces a couple of specific bottle styles (not just 'a red'), why each works with the dish, a budget-tier pick, an easy-to-find fallback, and a non-alcoholic option — with a plain reason you can remember next time.PlanningNo warnings★ 1.5K↓ —
- improve-architecturedaveebbelaar/bamaArchitecture check-in for a growing macOS Swift codebase. Finds hot spots, proposes deeper modules, and refactors one step per commit with behavior proven unchanged. Use at the end of a milestone, before a big feature, when a file passes 600 lines, when one feature touches many files, when bugs repeat in one area, or when the user asks to refactor or clean up the code.PlanningNo warnings★ 1.6K↓ —
metric-design
agentscope-ai/OpenJudge
DesignUpdated 5 hours ago
From the author
Use when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader selection, metric design, judge prompt engineering, rubric design, evaluation pipeline code, or "how to evaluate [X] automatically." Outputs executable OpenJudge pipeline code.
Install
npx skills add agentscope-ai/OpenJudge --skill metric-design -a claude-code
Installs to .claude/skills/metric-design/ · 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
Instructions onlyUses the networkLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance76
Maintenance100
Licence100
Adoption49
Files (1)
- SKILL.md