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
Scientific research22Development21Productivity3Creative tools2Security analysis1Application & supply-chain security0Cloud & infrastructure security0Identity & email security0Incident response & forensics0Integrations0OT & ICS security0Threat detection0Publisher
alirezarezvani79mukul97563K-Dense-AI43phuryn41addyosmani25Yuan1z082523anthropics12vercel-labs9kepano6alchaincyf2mattpocock20xS4N4TG1AirsupHQ1artouc1assafkip1cloudflare1cursor1debpalash1DietrichGebert1EL4CTEO1FeedHive1Fission-AI1footalytics1Garinmckayl1garrytan1GhostPawJS1Graphify-Labs1heydamir1Jakeschincariol1juliobsz1lemomo-ai1Leonxlnx1tt-a1i1wheresryan221Community first · Anthropic official entries follow. Sort applies within each group.
Showing 49 of 328
pstackLauren Tan’s (poteto) skill pack for rigorous AI-assisted engineering: run setup, then /poteto-mode routes playbooks and the other skills.- nature-academic-searchBuilds scientific literature searches and verifies citation evidence, connecting topics, indexing terms and source records to a traceable research result.High static risk — review source first
- nature-citationFinds literature supporting manuscript claims within the requested journal scope, producing claim-to-source mappings and reference-manager exports.
- nature-dataDrafts and checks manuscript data-availability statements and repository plans, connecting actual access routes to metadata and citation requirements.
- nature-downloaderRetrieves academic full text through lawful institutional or public routes, recording access provenance and supplementary-material availability.High static risk — review source first
- nature-experiment-logTurns experimental notes and images into a structured research log with metadata, supporting optional export to the source's configured note systems.
- nature-figureCreates and audits manuscript figures in Python or R, delivering source-linked plots and exports suitable for the requested submission context.
- nature-image2pptReconstructs screenshot or image-only slides as editable PowerPoint objects, separating layout elements and text rather than merely embedding a full-page image.High static risk — review source first
- nature-literature-pipelineOrganizes literature discovery from multi-source search through scoring and close reading, producing formatted research materials with an archival trail.
- nature-paper-cardBuilds a structured reading card for one paper, linking methods and experiments to claims, limitations and possible follow-up research.High static risk — review source first
- nature-paper-to-patentTurns research evidence and inventor materials into a Chinese patent-draft package, preserving the distinction between supplied facts and proposed claim language.High static risk — review source first
- nature-paper-transTranslates selected pages or a complete English paper into a Chinese reading PDF, aiming to preserve the original page layout and figures.High static risk — review source first
- nature-paper-xrayReconstructs a paper's reasoning from methods and evidence, explaining how the authors reached a result instead of restating the abstract.
- nature-paper2pptBuilds an academic presentation from a paper and reading notes, organizing source figures, Chinese slide text and speaker notes.
- nature-polishingEdits existing academic prose for clarity and terminology while preserving factual claims, supporting translation and manuscript-layout adjustments within scope.
- nature-readerCreates aligned Chinese-English paper readers with source-linked text and visual material, supporting close reading at the requested excerpt scope.
- nature-ref-verifierChecks reference-list metadata against multiple sources, reporting author, title, date and DOI conflicts in a structured verification record.High static risk — review source first
- nature-responseDrafts and audits responses to peer review from supplied reviewer comments and revisions, connecting each response to manuscript evidence.
- nature-reviewerProvides evidence-based mock peer review of a manuscript, separating major validity concerns from smaller clarity and presentation issues.
- nature-sharedProvides shared references for the Nature skill collection, supporting other installed workflows rather than acting as a standalone research task.
- nature-social-scienceDevelops social-science and philosophy research questions into defensible proposals, organizing argument, evidence routes and boundaries for scholarly review.
- nature-statisticsChecks statistical reporting in a manuscript, reviewing experimental units, replication and uncertainty so claims can be compared with the documented analysis.
- nature-writingStructures a scientific manuscript from author-supplied evidence, connecting sections and claims into an argument for initial submission.
- researchwriteDrafts or revises a research proposal from supporting evidence, connecting the question and planned methods to a coherent research plan.
- api-and-interface-designTurns API requirements into endpoint and module contracts, with attention to compatibility, error handling and interface boundaries.
- browser-testing-with-devtoolsUses browser observations, DOM inspection and console output to diagnose interface failures and check fixes in Chrome DevTools.High static risk — review source first
- ci-cd-and-automationBuilds delivery pipelines from a project's build and test commands, organizing repeatable checks before environment-specific deployment stages.
- code-review-and-qualityReviews a proposed code change across correctness and maintainability concerns, turning concrete defects into prioritized review findings.
- code-simplificationRefactors working code to make control flow and responsibilities easier to follow while preserving the existing observable behavior.
- constraint-driven-developmentConverts a project's quality expectations into a written contract, so implementation checks use explicit thresholds rather than shifting assumptions.
- context-engineeringOrganizes rules and task context for coding agents, helping a new session start with relevant information and fewer conflicting instructions.High static risk — review source first
- debugging-and-error-recoveryInvestigates failed tests, broken builds and unexpected behavior through reproducible evidence, narrowing causes before choosing a repair.High static risk — review source first
- deprecation-and-migrationPlans transitions away from old APIs or implementations, covering compatibility, user migration and the eventual removal of deprecated behavior.
- documentation-and-adrsRecords architectural choices and public-interface changes as documentation and decision records, preserving the reasons future maintainers need.
- doubt-driven-developmentChallenges a technical decision through an independent review of its assumptions, producing objections to resolve before implementation proceeds.
- frontend-ui-engineeringDevelops responsive interface components from product requirements, checking layout, accessibility and interaction behavior as part of implementation.
- git-workflow-and-versioningOrganizes branches, commits and conflict resolution for a code change, including splitting a mixed working tree into reviewable units.High static risk — review source first
- idea-refineDevelops an unclear idea through alternatives and assumption checks, ending with a more concrete concept that can guide further work.High static risk — review source first
- incremental-implementationBreaks a multi-file implementation into small working increments, pairing each increment with evidence that its behavior is correct.High static risk — review source first
- interview-meUses a sequential interview to clarify a request's underlying goal, resolving uncertainty before treating an initial solution idea as a specification.
- observability-and-instrumentationPlans logs, measurements and traces around a feature's production behavior, making failures and operational questions easier to investigate.
- performance-optimizationInvestigates slow frontend, backend and database paths using measurements, then evaluates whether a targeted optimization improves the observed bottleneck.
- planning-and-task-breakdownTurns an agreed specification into ordered implementation tasks, exposing dependencies and verification steps before work begins.
- security-and-hardeningReviews input handling, authentication and integrations for exploitable weaknesses, organizing source-backed hardening work around concrete attack paths.
- shipping-and-launchChecks a proposed production launch against operational prerequisites, gathering launch checks and unresolved readiness issues before release.
- source-driven-developmentChecks an implementation approach against official references, connecting technical decisions to documented behavior instead of relying on recalled APIs.
- spec-driven-developmentCreates a specification from a new feature or project idea, making objectives, requirements and acceptance conditions explicit before coding.
- test-driven-developmentUses failing tests, a minimal implementation and subsequent refactoring to develop a behavior change with a repeatable correctness check.
- using-agent-skillsMatches the current task to available agent skills, explaining when an existing workflow should be loaded and used.
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.
