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.
- 327 entries
- 33 publishers
- 323 with an open license
- Checked 17 Oct 2026 – 1 Nov 2026
All Claude skills
327 entries, metadata checked 17 Oct 2026 – 1 Nov 2026
Use case
Productivity45Development26Security analysis4Scientific research3Creative tools1Application & supply-chain security0Cloud & infrastructure security0Identity & email security0Incident response & forensics0Integrations0OT & ICS security0Threat detection0Publisher
alirezarezvani79mukul97563K-Dense-AI43phuryn41addyosmani25Yuan1z082523anthropics12vercel-labs9kepano6alchaincyf2mattpocock20xS4N4TG1AirsupHQ1artouc1assafkip1cloudflare1cursor1debpalash1DietrichGebert1EL4CTEO1FeedHive1Fission-AI1Garinmckayl1garrytan1GhostPawJS1Graphify-Labs1heydamir1Jakeschincariol1juliobsz1lemomo-ai1Leonxlnx1tt-a1i1wheresryan221Community first · Anthropic official entries follow. Sort applies within each group.
Showing 79 of 327
- ad-creativeDevelops paid-ad headlines and copy variants from a campaign brief, supporting creative iteration across messages and audience angles.
- 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.
- business-name-fitEvaluates business-name candidates against a founder's cultural identity and target markets, balancing personal meaning with professional usability.
- c-level-skillsRoutes a management question through the C-level advisory bundle, helping select the relevant executive role or cross-functional workflow.
- caio-reviewQuestions an AI feature plan about model choice, evaluation, regulation and economics, making evidence gaps visible before an executive approves it.
- captureOrganizes an unstructured brain dump into actionable items and reference material while retaining the information supplied in the original notes.
- chief-ai-officer-advisorEvaluates startup AI strategy across sourcing choices, regulation and cost, preparing decision support for an executive rather than implementation code.
- chief-customer-officer-advisorUses retention and customer-segment evidence to examine customer strategy, separating churn causes from headline revenue-retention figures.
- 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
- clinical-researchHelps design a prospective clinical study by organizing endpoint choices and planning assumptions before the protocol is submitted for professional review.High static risk — review source first
- cmo-advisorConnects brand positioning and growth choices to marketing budgets and team design, preparing a coherent marketing leadership plan.
- cmo-reviewChallenges positioning and campaign plans through customer definition, narrative and channel fit, identifying weaknesses behind an unclear marketing message.
- 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
- collab-proofReviews a human-agent work session to distinguish contributions and decisions, producing a retrospective grounded in collaboration evidence.
- commercial-forecasterBuilds a bookings or recurring-revenue forecast from pipeline assumptions, separating committed outcomes from optimistic and pipeline-only scenarios.
- competitive-teardownCombines public competitor signals from pricing, reviews and hiring into a structured comparison, keeping observations separate from inferred strategy.
- compliance-readinessQuestions a compliance program about its scope, readiness and evidence, highlighting decisions needed before an audit or a new framework rollout.
- content-creatorRedirects older content-creator requests to more specific writing or marketing workflows, preserving compatibility with a retired entry point.
- copywritingRewrites product-page and landing-page copy from a marketing brief, clarifying the offer and the visitor's next action.
- coverageExamines a project's tests and coverage information to identify untested behaviors and suggest additional checks with meaningful failure detection.
- cpo-advisorExamines product vision, portfolio choices and evidence of market fit to support product-leadership decisions and organizational planning.
- decideRecords a founder-approved decision memo in the executive memory system, keeping its approved outcome separate from discussion transcripts.
- decision-loggerSeparates raw meeting transcripts from approved executive decisions, retaining a decision history that can be reviewed without confusing drafts with commitments.High static risk — review source first
- deep-researchInvestigates a research question across multiple sources, comparing claims and provenance to produce a traceable synthesis with explicit uncertainty.
- engineering-advanced-skillsIndexes an advanced engineering skill collection, helping choose a focused specialist for agent infrastructure, development or operations work.
- epic-designBuilds layered interactive websites from a visual brief, combining scroll-driven storytelling and animation without requiring a WebGL scene.
- eu-ai-act-specialistMaps an AI system and its evidence to operational EU AI Act questions, organizing risk classification and compliance work for specialist review.
- evalCompares completed AgentHub runs using a chosen metric or judge, producing ranked results for an experiment rather than new implementations.
- executive-mentorStress-tests a founder's plan or difficult decision, surfacing tradeoffs and questions for board preparation or a retrospective.
- 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
- handoffCondenses a working conversation into a continuation document, recording task state and next actions while removing secret values.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
- iso27001-audit-prepPrepares an ISO 27001 audit through questions about ISMS scope and supporting evidence, organizing gaps ahead of internal or certification review.
- iso42001-specialistReviews an AI management system against ISO 42001 requirements, organizing clause-level evidence gaps and remediation priorities for internal audit preparation.
- knowledge-opsCreates and checks internal procedures from an operations brief, producing maintainable SOPs and runbooks for recurring company work.High static risk — review source first
- linkedin-analyticsAnalyzes a user's LinkedIn performance data to distinguish post-level patterns from noise and formulate a testable explanation for reach changes.
- linkedin-strategyPlans LinkedIn positioning, content themes and publishing cadence around a professional goal, producing a sustainable channel plan rather than individual posts.
- llm-wikiTurns source material into a maintained Obsidian knowledge base, managing concept pages, cross-links and source ingestion over time.High static risk — review source first
- local-seo-managerReviews local-search visibility for service-area businesses, connecting business-profile and location evidence to a focused local SEO action plan.
- loopConfigures an iterative research experiment with a selected interval, defining repeated runs for an existing autoresearch workflow.
- ma-playbookStructures an acquisition decision around diligence, valuation, deal terms and integration, supporting either a buyer or a company preparing to sell.
- marketing-psychologyApplies behavioral concepts to a marketing problem, explaining how a proposed message or experience relates to customer decisions.
- md-documentConverts a long Markdown document into a self-contained HTML reading interface with navigation, search and copying aids.High static risk — review source first
- meeting-analyzerExamines meeting transcripts for communication patterns and behavioral problems, turning observed examples into coaching feedback.
- memory-reviewReviews an agent's stored memory for stale facts, duplication and promotion candidates, turning accumulated notes into a maintenance plan.
- 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.
- notebooklmOperates NotebookLM through its browser interface to locate notebooks and work with their source-grounded questions and materials.
- office-hoursUses a focused founder interview to examine customer problems, distribution and defensibility before offering startup advice.
- paid-adsPlans paid-media campaigns from audience and offer requirements, organizing channel choices, targeting and performance questions for subsequent validation.
- pricing-strategistCompares pricing models and willingness-to-pay research for a product, turning evidence into a pricing hypothesis and validation plan.
- product-discoveryMaps a product opportunity's assumptions and research needs, preparing a discovery sprint before resources are committed to delivery.
- programmatic-seoPlans data-backed page templates for scaled search acquisition, connecting page structure and datasets to distinct visitor tasks and quality requirements.
- pw-reviewReviews Playwright tests for weak assertions and unreliable execution patterns, producing improvements to browser-test quality and maintainability.
- quality-manager-qms-iso13485Organizes medical-device quality-system documentation and audit work around ISO 13485, including corrective actions and document-control processes.
- rag-architectDesigns retrieval pipelines around document chunking, embeddings and search evaluation, relating architecture choices to measurable retrieval quality.
- revenue-operationsExamines SaaS pipeline and revenue measurements to identify forecasting gaps and weaknesses in the go-to-market process.
- runCoordinates the stages of an AgentHub experiment from baseline through evaluation and merge, using the session's selected competition workflow.
- saas-metrics-coachInterprets supplied SaaS revenue and customer figures through retention, acquisition and recurring-revenue metrics, highlighting business-health questions to investigate.
- 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
- security-guidanceChecks proposed tool actions for common implementation hazards through a Claude Code hook, flagging risky patterns before the action runs.
- 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
- senior-securityRoutes security questions toward threat modeling or focused assessment, using structured risk methods to organize findings and next investigations.High static risk — review source first
- signup-flow-croReviews account-creation and trial-entry flows for conversion friction, turning observed signup obstacles into focused improvement hypotheses.
- skill-security-auditorInspects an agent skill before installation, examining its instructions and files for suspicious permissions or exploitable behavior.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
- statistical-analystAnalyzes experiment results with hypothesis tests, effect sizes and sample-size reasoning, distinguishing statistical evidence from a practical decision.
- vpe-advisorReviews engineering delivery and hiring evidence to locate organizational bottlenecks and prepare priorities for a startup engineering leader.
- webinar-marketingOrganizes a webinar's positioning, promotion and follow-up around demand generation, producing a plan that spans the event lifecycle.
- weekly-reviewReviews commitments and stalled projects on a weekly cycle, producing a refreshed set of next actions and unresolved decisions.
- 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.
