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.
14,533 skills from 417 repositories · updated 21 hours ago
14,417 skills
- graphqlsickn33/agentic-awesome-skillsGraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper controls, clients can craft queries that bring down your server.OtherNo warnings★ 48.3K↓ —
- track-managementwshobson/agentsUse this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.PlanningNo warnings★ 41.5K↓ —
- code-auditsickn33/agentic-awesome-skillsAuthorized source-code security review and SAST workflows: Semgrep and CodeQL pattern hunting, dangerous API identification, and fix verification.EngineeringNo warnings★ 48.3K↓ —
- nature-social-scienceYuan1z0825/nature-skills社会科学及相邻学科学术写作与选题论证工作台,覆盖选题构思、文献梳理、论证组织、学术表达四大要素。Use for 找论文题目/研究问题、把兴趣或宽泛主题变成可讨论的研究方向、文献综述与领域版图、区分"研究少"与真正未决的知识问题、设计证据路线与主张边界、新颖性审计与"审稿人2"式攻击、博士/论文可行性评估、导师沟通话术、或检查论文中的过度断言与概念混用。也适用于开题报告、研究计划书、学位论文的选题阶段与论证自检。ScienceNo warnings★ 50.1K↓ —
- hunt-grpcsickn33/agentic-awesome-skillsHunt gRPC vulnerabilitiesSecurityNo warnings★ 48.3K↓ —
- blockrunsickn33/agentic-awesome-skillsBlockRun works with Claude Code and Google Antigravity.EngineeringNo warnings★ 48.3K↓ —
- competitive-landscapewshobson/agentsAnalyze competition, identify differentiation opportunities, and develop winning market positioning strategies using Porter's Five Forces, Blue Ocean Strategy, and positioning maps. Use this skill when evaluating competitors, assessing market positioning, identifying sustainable competitive advantages, or preparing competitive strategy analysis for a startup or investor pitch.FinanceNo warnings★ 41.5K↓ —
- nature-experiment-logYuan1z0825/nature-skills标准化实验日志记录——直接上传或读取本地图片、语音和文字,产出带 YAML frontmatter 的 Markdown;可选集成飞书 CLI 与 Obsidian。EngineeringNo warnings★ 50.1K↓ —
- assaysickn33/agentic-awesome-skillsRun assay on a web page you just wrote or changed. It opens the page in a real browser, drives every control, and reports where the page contradicts itself. Deterministic, no API key, no network.BrowserNo warnings★ 48.3K↓ —
- debuggersickn33/agentic-awesome-skillsDebugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.EngineeringNo warnings★ 48.3K↓ —
- nature-ref-verifierYuan1z0825/nature-skills对学术文献逐条执行多源交叉验证,逐字段对比作者、标题、年份、卷期、页码, 标记卷年/DOI年冲突、作者顺序异常、页码偏差等问题,输出结构化验证报告。 可批量处理整篇论文/开题报告的参考文献列表,也可单条校验,支持与 Zotero 同步修正。OtherNo warnings★ 50.1K↓ —
- dispatchsickn33/agentic-awesome-skillsDelegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessionsEngineeringNo warnings★ 48.3K↓ —
- doc2mathsickn33/agentic-awesome-skillsConvert narrative technical documents into grounded Mathematical Problem Specifications with variables, constraints, objectives, and uncertainty.PlanningNo warnings★ 48.3K↓ —
- equiblessickn33/agentic-awesome-skillsQuery Equibles for US stock market data: SEC filing search, XBRL financial statements, earnings call transcripts, insider and 13F holdings, and daily prices.FinanceNo warnings★ 48.3K↓ —
- aws-lambdasickn33/agentic-awesome-skillsBuild and deploy serverless functions on AWS Lambda. Configure triggers, manage permissions, and optimize performance. Use when implementing serverless applications.DevOpsNo warnings★ 48.3K↓ —
- form-crosickn33/agentic-awesome-skillsOptimize any form that is NOT signup or account registration — including lead capture, contact, demo request, application, survey, quote, and checkout forms.MarketingNo warnings★ 48.3K↓ —
- gh-attachgithub/awesome-copilotUploads a local file (screenshot, image, PDF, zip, video) to GitHub user-attachments, downloads GitHub user-attachments, and embeds local files in a PR, issue, or comment. Use when asked to "attach a screenshot to the PR", "add an image to the issue", "embed before/after screenshots", "attach this file", or "download this GitHub attachment". Powered by `gh-attach`.DocumentsNo warnings★ 40.3K↓ —
- fp-reactsickn33/agentic-awesome-skillsPractical patterns for using fp-ts with React - hooks, state, forms, data fetching. Works with React 18/19, Next.js 14/15.EngineeringNo warnings★ 48.3K↓ —
- lsp-setupgithub/awesome-copilotEnable code intelligence (go-to-definition, find-references, hover, type info) for any programming language by installing and configuring an LSP server for Copilot CLI. Detects the OS, installs the right server, and generates the JSON configuration (user-level or repo-level). Use when you need deeper code understanding and no LSP server is configured, or when the user asks to set up, install, or configure an LSP server.EngineeringNo warnings★ 40.3K↓ —
- grill-mesickn33/agentic-awesome-skillsA relentless interview to sharpen a plan or design.DesignNo warnings★ 48.3K↓ —
- grillingsickn33/agentic-awesome-skillsInterview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.TestingNo warnings★ 48.3K↓ —
- hunt-atosickn33/agentic-awesome-skillsHunt account takeover taxonomyOtherNo warnings★ 48.3K↓ —
- nature-statisticsYuan1z0825/nature-skillsAudit or improve manuscript statistical reporting, including experimental units, replication, uncertainty, tests, and figure statistics. Use for 统计审查、统计方法小节、图注统计 and reviewer concerns; compute new analyses only when requested with data.TestingNo warnings★ 50.1K↓ —
- nature-paper-xrayYuan1z0825/nature-skillsRead one supplied paper closely enough to reconstruct how its authors actually got there, rather than restating what the abstract claims. Use for 精读论文, 讲透这篇论文, 把这篇读懂, 作者为什么这么设计, 这个公式怎么推出来的, paper x-ray, and deep single-paper comprehension before building on, reviewing, presenting, or citing that paper. Recovers the real starting point and the bet the authors placed, separates load-bearing design from decoration, grounds each key formula in a worked micro-example with concrete numbers, and checks how far the evidence actually reaches, including where the authors are confident and where the paper does not report something. Delivers a structured Markdown long-read by default. Not a summary, not a translation, not a peer review.ScienceNo warnings★ 50.1K↓ —