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.
40,909 skills from 1,920 repositories · updated 12 minutes ago
2,399 skills
- reachsno-ai/sno-station-skillsContact another agent, exchange work cards, inspect replies, or manage reachable seats through the installed Reach program. Use for communication; full task ownership transfer belongs to handoff.ProductivityNo warnings★ 731↓ —
- cold-email-verifierVarnan-Tech/opendirectoryUse when the user wants to verify cold emails, enrich a lead list, or autonomously guess email addresses from a CSV using ValidEmail.co or the open-source Reacher engine.ProductivityNo warnings★ 686↓ —
- sculptingarjun988/blender-skillsBlender sculpting for organic and hard surface detail using Dyntopo, multiresolution, brushes, alpha workflow, wrinkles, and damage. Use when high-frequency surface detail is needed before retopology in Blender via MCP.ProductivityNo warnings★ 396↓ —Also in 1 other repo
- uv-workflowarjun988/blender-skillsProduction UV unwrapping for seam placement, UV packing, texel density, UDIM, lightmap UVs, and modular UV layouts. Use when preparing meshes for texturing and engine export in Blender via MCP.ProductivityNo warnings★ 396↓ —Also in 1 other repo
- texture-workflowarjun988/blender-skillsProduction texture workflow for atlases, baking AO/curvature/normal/roughness maps, decals, and texture memory optimization. Use for game-ready texture pipelines in Blender via MCP.ProductivityNo warnings★ 396↓ —Also in 1 other repo
- pm-nextwei63w/pm-managerClaim the single next governance todo (marks in_progress).ProductivityNo warnings★ 87↓ —
- LEAPagentsope/SkillAlchemyLEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skills into one. It is called by the main SkillAlchemy workflow. Use when SkillAlchemy requires distillation or fusion.ProductivityNo warnings★ 446↓ —
- driftmembranedev/application-skillsDrift integration. Manage Persons, Organizations, Deals, Leads, Activities, Notes and more. Use when the user wants to interact with Drift data.ProductivityNo warnings★ 269↓ —
- gen-release-notesexistential-birds/beaglegenerate release notes for changes since a given tagProductivityNo warnings★ 84↓ —
- go-concurrency-webexistential-birds/beagleGo concurrency patterns for high-throughput web applications including worker pools, rate limiting, race detection, and safe shared state management. Use when implementing background task processing, rate limiters, or concurrent request handling.ProductivityNo warnings★ 84↓ —
- oneciteHzaCode/OneCiteValidate, clean, and audit academic references with OneCite from a local repository checkout. Use when a workflow needs deterministic citation verification, BibTeX cleanup, benchmark gating, or template discovery.ProductivityNo warnings★ 67↓ —
- cc-async-task-patterndoccker/cc-use-exp当 API/任务可能执行超过 10 秒(批量数据处理、远程 API 批量调用、全表扫描、跨租户聚合)时触发。防止同步接口被网关 30s 超时切断、用户重复点击触发并发、状态缓存内存泄漏等问题。提供异步任务状态机标准模板。ProductivityNo warnings★ 1.1K↓ —
- councilboshu2/agentopsCompare independent opinions from several models or contexts without inflating agreement. Use when: wanting a second opinion or debate, or summarizing several reviewers' results.ProductivityNo warnings★ 450↓ —Also in 1 other repo
- pydantic-ai-tool-systemexistential-birds/beagleRegister and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implementing function calling, or creating agent actions.ProductivityNo warnings★ 84↓ —
- automation-audit-opsmturac/everything-openai-codexEvidence-first automation inventory and overlap audit workflow for ecc. Use when the user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before fixing anything.ProductivityNo warnings★ 83↓ —
- cc-task-statedoccker/cc-use-exp任务状态沉淀与恢复工作流,适用于补记进展、记录未开始需求、标记被打断或阻塞、整理恢复入口与下一步场景;通过项目内 .codex/tasks/ 持久化任务状态。ProductivityNo warnings★ 1.1K↓ —
- colleague-distillationZhixiangLuo/10xProductivityDistill a colleague into a reusable AI skill (work + persona) using tool connections — Slack, Slack AI, Jira, GHE, Bitbucket, Confluence, SharePoint, Teams, Outlook, Notion, Linear, Google Docs, and more — without manual paste. Use when the user wants a colleague skill, digital twin of a coworker, or capture of someone's technical voice from workplace systems. Requires tool_connections + 10xProductivity verified_connections (or equivalent .env).ProductivityNo warnings★ 483↓ —
- email-opsmturac/everything-openai-codex以证据为先的邮箱分类、草稿、发送验证及已发送邮件安全跟进工作流,适用于ecc。当用户希望整理邮件、通过真实邮件界面起草或发送、或证明已发送邮件内容时使用。ProductivityNo warnings★ 83↓ —
- cc-new-featuredoccker/cc-use-exp结构化新功能交付工作流,适用于显式 new feature、从需求到实现的一站式功能开发或恢复未完成任务场景;通过项目内 .codex/tasks/ 持久化状态。ProductivityNo warnings★ 1.1K↓ —
- notion-deletebam-bam-2/solo-skills노션 페이지를 삭제(아카이브)한다. '노션에서 삭제해줘', '이 페이지 지워줘', '/notion-delete' 트리거. 페이지 ID 또는 노션 URL을 받아 Notion API로 즉시 아카이브.ProductivityNo warnings★ 366↓ —
- de-summaryBioTender-max/awesome-bio-agent-skillsSummarise pre-computed differential expression results with ranked gene lists, biological themes, and publication-ready interpretation.ProductivityNo warnings★ 206↓ —
- apifymembranedev/application-skillsApify integration. Manage Actors, Datasets, KeyValueStores, RequestQueues, Tasks. Use when the user wants to interact with Apify data.ProductivityNo warnings★ 269↓ —
- go-contextcxuu/golang-skillsUse when working with context.Context in Go — placement in signatures, propagating cancellation and deadlines, and storing values in context vs parameters. Also use when cancelling long-running operations, setting timeouts, or passing request-scoped data, even if they don't mention context.Context directly. Does not cover goroutine lifecycle or sync primitives (see go-concurrency).ProductivityNo warnings★ 181↓ —
- strategic-compactmturac/everything-openai-codexSuggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.ProductivityNo warnings★ 83↓ —