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.
46,700 skills from 2,243 repositories · updated 12 hours ago
5,805 skills
- python-openpyxlcxcscmu/SkillLearnBenchUsing openpyxl to read, write, and modify Excel files while preserving formatting and using formulas.EngineeringNo warnings★ 91↓ —
- learn-codebasektaletsk/learn-codebaseSocratic tutor that teaches codebase understanding through questioning, challenges, and active recall. Invoke with /learn-codebase when onboarding to a new codebase or deepening understanding of existing code. Maintains a learning journal that tracks mastery and schedules reviews.EngineeringNo warnings★ 95↓ —
- agent-ready-api-catalogfabricioctelles/skillsSub-skill de agent-ready-cloudflare: Implement API CatalogEngineeringNo warnings★ 122↓ —
- github-api-queriescxcscmu/SkillLearnBenchQuery GitHub API for pull requests and issues within a date range, retrieving all metadata needed for metrics collection. Use this skill whenever you need to fetch GitHub PR or issue data with date filtering, especially when gathering activity reports or computing statistics across a time period.EngineeringNo warnings★ 91↓ —
- zhangyi-reviewaph199686/zhangyi-studio张翼审查收尾：发布前或阶段节点的全面审查——范围与证据口径先行、六级结论分级、每条结论带证据引用、执行摘要与'未来两周 N 件事'。输出审查裁决书。Use when the user prepares for release/launch, wants a full project audit, checks store/platform readiness, reviews builds/CI/saves/rights, or asks whether the project is ready. 用户准备上架发布、想做全面项目审查、检查平台就绪度、核查构建/CI/存档/权利链、或问'现在能发了吗'时使用。EngineeringNo warnings★ 119↓ —
- huashu-agent-swarmalchaincyf/huashu-skills多Agent蜂群并行协作，纯git自组织，适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。EngineeringNo warnings★ 2K↓ —
- code-reviewNewNoobyGains/godmodeUse when a task, feature or bug fix is implemented and before it is committed, merged or handed back to the user, and when the user asks for a review of a change, a branch or a pull request.EngineeringNo warnings★ 114↓ —
- use-conversational-languageeai-org/agent-toolkitVoice rules for text published under a person's name and read as if a person typed it, such as chat messages to colleagues, PR comments and descriptions, commit messages, review replies, and code comments. Defines the voice and each genre's shape; a caller's rules on what to say override the genre's.EngineeringNo warnings★ 76↓ —
- maintainer-revieweai-org/agent-toolkitReview someone else's pull request as the maintainer deciding whether it merges.EngineeringNo warnings★ 76↓ —
- rviz2robium-ai/robiumInspect and debug live ROS 2 robot state with RViz2.EngineeringNo warnings★ 100↓ —
- erThomasMoreAI/legal-skills-openAI4L - Main Skill for Evidence Review Creation and Auditing using @AGENTSEngineeringNo warnings★ 95↓ —
- cortex-setup-projectcdeust/CortexBootstrap Cortex for a new project or import existing session history. Use when the user says 'set up Cortex', 'seed this project', 'import my history', 'backfill memories', 'bootstrap memory', 'initialize Cortex for this project', or when starting to use Cortex on an existing codebase that already has Claude Code conversation history.EngineeringNo warnings★ 75↓ —
- cli-ghPaulRBerg/agent-skillsUse for GitHub CLI automation: repository reads, workflow runs, search, codespaces, releases, configuration, or gh command syntax. Use yeet for contribution writes to PRs, issues, comments, or discussions.EngineeringNo warnings★ 101↓ —
- cortex-importcdeust/CortexImport memories from other AI memory systems into Cortex. Supports claude-mem (SQLite), Claude Desktop sessions, ChatGPT web export (JSON), Gemini Takeout (JSON), Cursor conversations, and Claude Code JSONL. Use when the user says 'import from claude-mem', 'migrate memories', 'import ChatGPT history', 'import from Gemini', 'transfer memories', or when Cortex detects another memory system is installed.EngineeringNo warnings★ 75↓ —
- code-instrumentation-generatorArabelaTso/Skills-4-SEAutomatically instruments source code to collect runtime information such as function calls, branch decisions, variable values, and execution traces while preserving original program semantics. Use when users need to: (1) Add logging or tracing to code for debugging, (2) Collect runtime execution data for analysis, (3) Monitor function calls and control flow, (4) Track variable values during execution, (5) Generate execution traces for testing or profiling. Supports Python, Java, JavaScript, and C/C++ with configurable instrumentation levels.EngineeringNo warnings★ 259↓ —
- review-code-assistanteai-org/agent-toolkitAssist a human reviewing a pull request or branch locally, read-only and never posting.EngineeringNo warnings★ 76↓ —
- spine-apitonone-ai/tononeDesign and spec an API — endpoints, request/response shapes, error codes, auth pattern, pagination. Applies Stripe's consistency principles. Use when asked to "design an API", "build API endpoints", "create REST API", or "API for this feature".EngineeringNo warnings★ 76↓ —
- verify-understandingeai-org/agent-toolkitVerify the engineer is ready to implement a feature through a teach-back conversation over its ticket review.EngineeringNo warnings★ 76↓ —
- extract-pr-review-ruleseai-org/agent-toolkitExtract the conventions a repo's reviewers enforce in inline PR review comments into a per-reviewer rules doc; re-runs resume from a checkpoint.EngineeringNo warnings★ 76↓ —
- pi-setupwquguru/skillsThis skill should be used when the user wants to install or configure Pi Agent (@earendil-works/pi-coding-agent) with DeepSeek (built-in), Ant-Ling Ring-2.6-1T (single-model custom provider), and ZenMux (multi-model OpenAI-compatible aggregator including Gemini 3.5 Flash, inclusionAI Ling-3.0-flash, Claude, GPT), including auth, models.json, settings.json, a curated extension set, and known-pitfall fixes. Triggers on "配置 pi"、"setup pi agent"、"pi 装一下"、"配 ring/deepseek/gemini/zenmux/ling 到 pi".EngineeringNo warnings★ 94↓ —
- tool.datadog_api_client.8d8db4e9e130b100AI45Lab/OpenARTQuery and manage Datadog resources (logs, metrics, monitors, dashboards, incidents, APM traces) using the datadog-api-client Python library. Use when the user asks about Datadog monitoring, wants to search logs, check metrics, manage monitors, investigate incidents, or interact with any Datadog API.EngineeringNo warnings★ 255↓ —
- tool.asana.094ded3e89364a6eAI45Lab/OpenARTManage Asana workspaces, projects, tasks, and comments via the REST API.EngineeringNo warnings★ 255↓ —
- grace-migrateosovv/grace-marketplaceAgent-applied GRACE 3 to GRACE 4 migration workflow. CLI validates the result but does not convert or delete files.EngineeringNo warnings★ 254↓ —Also in 1 other repo
- verification-boundary-reporterArabelaTso/Skills-4-SEAnalyze formal verification artifacts (Isabelle, Coq, Dafny, etc.) and produce structured reports identifying the precise boundary between verified, assumed, and unverified components. Use when assessing verification coverage, understanding trust boundaries, auditing formal proofs, or documenting verification scope. Reports explicitly list verified code, assumptions, axioms, trusted computing base, and unverified components. Conservative and explicit about verification status without attempting to repair or mask gaps.EngineeringNo warnings★ 259↓ —