Claude skills directory
Short answer
A Claude skills directory is a browsable catalog of reusable instructions for Claude and other agents, with links to their sources. AgentSkillsDir is an independent, source-linked directory for discovering Claude and Codex skills, plus separate MCP server and agent collections. It is not Anthropic’s official documentation or a hosted runtime.
How to use itBrowse by task, open a skill card, then review its source and follow the upstream installation instructions for your client.
- 328 entries
- 34 publishers
- 324 with an open license
- Checked 17 Oct 2026 – 3 Nov 2026
All Claude skills
328 entries, metadata checked 17 Oct 2026 – 3 Nov 2026
Use case
Productivity45Development26Security analysis4Scientific research3Creative tools2Application & supply-chain security0Cloud & infrastructure security0Identity & email security0Incident response & forensics0Integrations0OT & ICS security0Threat detection0Publisher
alirezarezvani26addyosmani20mukul97512vercel-labs8phuryn6artouc1cloudflare1cursor1EL4CTEO1Fission-AI1garrytan1Graphify-Labs1Jakeschincariol1juliobsz1K-Dense-AI1mattpocock1tt-a1i10xS4N4TG0AirsupHQ0alchaincyf0anthropics0assafkip0debpalash0DietrichGebert0FeedHive0footalytics0Garinmckayl0GhostPawJS0heydamir0kepano0lemomo-ai0Leonxlnx0wheresryan220Yuan1z08250Community first · Anthropic official entries follow. Sort applies within each group.
- adversarial-reviewerSubjects a code change to a deliberately critical review, looking for concrete weaknesses that a familiar implementation perspective may overlook.
- agent-launcher-orchestratorGuides creation and evaluation of a Claude Managed Agent in the user's account, taking an agent brief toward a launchable configuration.High static risk — review source first
- agent-protocolDefines structured messages between executive-role agents, including invocation, isolation and loop-prevention conventions for coordinated work.
- api-design-reviewerReviews REST API designs for inconsistent conventions and breaking changes, turning endpoint definitions into a structured design scorecard.High static risk — review source first
- boost-asio-proSupports asynchronous C++ networking work with Asio, covering event-loop ownership, concurrent handlers and coroutine-based client or server code.
- ci-cd-pipeline-builderUses detected stack information to draft a CI/CD baseline, with repeatable checks and distinct delivery stages for each environment.High static risk — review source first
- code-reviewerAnalyzes code changes across supported languages for complexity, correctness and review risk, producing actionable findings for pull-request review.High static risk — review source first
- coverageExamines a project's tests and coverage information to identify untested behaviors and suggest additional checks with meaningful failure detection.
- engineering-advanced-skillsIndexes an advanced engineering skill collection, helping choose a focused specialist for agent infrastructure, development or operations work.
- evalCompares completed AgentHub runs using a chosen metric or judge, producing ranked results for an experiment rather than new implementations.
- feature-flags-architectPlans feature-flag rollout and retirement from a project's release needs, including kill switches, ownership and stale-flag cleanup.
- git-worktree-managerSets up isolated Git worktrees for concurrent features, coordinating branches, local ports and environment handling for separate development contexts.High static risk — review source first
- hivemindOrganizes isolated coding workers and benchmark comparisons for delegated work, documenting orchestration choices and claimed cost tradeoffs.High static risk — review source first
- loopConfigures an iterative research experiment with a selected interval, defining repeated runs for an existing autoresearch workflow.
- monorepo-navigatorMaps dependencies and package boundaries in a monorepo, helping select affected tests and builds instead of processing every package indiscriminately.
- named-persona-adversarial-reviewReviews code using explicitly named engineering philosophies, comparing concrete implementation choices against documented principles rather than generic checklists.
- pw-reviewReviews Playwright tests for weak assertions and unreliable execution patterns, producing improvements to browser-test quality and maintainability.
- rag-architectDesigns retrieval pipelines around document chunking, embeddings and search evaluation, relating architecture choices to measurable retrieval quality.
- runCoordinates the stages of an AgentHub experiment from baseline through evaluation and merge, using the session's selected competition workflow.
- saas-scaffolderScaffolds a SaaS application's authentication, database, billing and dashboard structure using the source's supported full-stack conventions.High static risk — review source first
- senior-computer-visionSupports computer-vision system design across detection and segmentation tasks, connecting model architecture and training choices to visual-analysis requirements.High static risk — review source first
- senior-fullstackCompares full-stack architecture choices and scaffolds supported application stacks, pairing implementation structure with code-quality assessment.High static risk — review source first
- snowflake-developmentSupports Snowflake SQL and data-pipeline development, including managed table updates, stream/task processing and Cortex-based data features.High static risk — review source first
- sql-database-assistantUses database schemas and a query goal to draft SQL, migrations or optimization suggestions for common database and ORM workflows.High static risk — review source first
- stage-launchConverts an approved managed-agent build sheet into API payloads and a resumable launch sequence using the user's own credentials.High static risk — review source first
- write-a-skillTurns a repeatable task into a structured agent skill with focused instructions, progressive references and the supporting resources it needs.
Guides that use this category
Best Blender MCP Servers & Skills (2026)Blender MCP connects an AI client to a running Blender session through the Model Context Protocol, so the model can read your scene and run Python through Blender’s API.Blender Agent Skills
Install Claude Code Skills: Folder, Plugin & CLIChoose one of three ways to install Claude Code skills: copy a complete skill folder, install a plugin from its marketplace, or use npx skills add with Claude Code selected.frontend-designpdfvercel-react-best-practices
Claude Code Security: Audit & Hardening SkillsA Claude Code security review starts with an authorized scope and a question to investigate.Cloudflare Security Auditsecurity-and-hardening
Best Codex Skills (2026)Codex can use agent skills: folders with a SKILL.Skills for Real EngineersgstackTaste SkillawwwardsAI Slop DetectorGhostPaw Codexhuashu-motionLemo-OpuscarMachine SkillanatomyBlender Agent Skills
Best Claude Skills for Video EditingPick a Claude skill by the video you need to ship.huashu-motionpapercut-explainerLemo-OpuscarMachine Skill
Skills directory and structure FAQ
6 questions · what the directory is, how skill folders are laid out, how to submit
What is a Claude skills directory?
A Claude skills directory is a browsable catalog of reusable instructions for Claude and other agents, with links to their sources. AgentSkillsDir is an independent, source-linked directory for discovering Claude and Codex skills, plus separate MCP server and agent collections. It is not Anthropic’s official documentation or a hosted runtime.
What is the typical Claude / agent skills directory structure?
Under the common Agent Skills convention, each skill has its own folder with a SKILL.md file. Optional scripts/, references/ and assets/ folders hold supporting code, documents and templates. This is a common layout, not a requirement for every listed project: follow each repository’s layout and your client’s documentation.
How is AgentSkillsDir different from claude.com docs / skillmd?
AgentSkillsDir provides source links and independent editorial summaries to help you discover resources. It is separate from Anthropic’s official Claude documentation and from other directories such as skillmd. Use official documentation for Claude product behavior and each publisher’s repository for setup, compatibility and license terms. A listing does not certify safety or successful installation.
How do I find the best Claude skills or MCP servers from here?
Start with the task and client you need, then compare the source-linked entries. For focused shortlists, use the video skills, Codex skills or Cursor MCP guides below. Check each candidate’s prerequisites and source terms; inclusion is not a promise that it will work in your setup.
How do I submit a skill or MCP server?
Open the submission page and share the public repository or project URL for manual review. Nothing is published automatically, and listing is not guaranteed. If online intake is unavailable, email the public link to submit@agentskillsdir.com.
What is a SKILL.md file?
SKILL.md is the instruction file in an Agent Skills folder. In the standard format, YAML front matter records a name and description, followed by Markdown instructions explaining the task. Read it and any supporting scripts before enabling a skill; the file is instructions, not proof of an audited or tested workflow.
