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 research37Productivity36Development7Creative tools1Application & supply-chain security0Cloud & infrastructure security0Identity & email security0Incident response & forensics0Integrations0OT & ICS security0Security analysis0Threat detection0Publisher
alirezarezvani79phuryn41K-Dense-AI40addyosmani25vercel-labs7kepano6Yuan1z08253alchaincyf2mattpocock20xS4N4TG1AirsupHQ1artouc1assafkip1cloudflare1cursor1DietrichGebert1EL4CTEO1FeedHive1Fission-AI1footalytics1Garinmckayl1garrytan1GhostPawJS1Jakeschincariol1juliobsz1lemomo-ai1Leonxlnx1wheresryan221anthropics0debpalash0Graphify-Labs0heydamir0mukul9750tt-a1i0Community first · Anthropic official entries follow. Sort applies within each group.
Showing 81 of 328
- ab-test-analysisInterprets A/B experiment results using sample-size and uncertainty checks, producing a supported ship, extend or stop recommendation.
- ansoff-matrixMaps growth options across existing and new products and markets, making the assumptions behind each Ansoff strategy explicit.
- beachhead-segmentCompares potential launch segments by pain, purchasing capacity and reachable market share, selecting a focused first market to validate.
- brainstorm-okrsTurns company priorities into team-level objectives and measurable key results, supporting a focused quarterly goal discussion.
- business-modelDescribes how a business creates and captures value through the nine Business Model Canvas sections, revealing dependencies for further validation.
- code-reviewReviews implementation boundaries for actionable correctness defects, tracing each finding from an agreed contract to the code that violates it.
- cohort-analysisOrganizes engagement and retention data into cohorts, comparing segment trends to expose differences hidden in aggregate product metrics.
- create-prdBuilds a lean product requirements document from product context, organizing objectives, users, value and solution decisions into a reviewable brief.
- draft-ndaStructures an NDA draft from the parties, information types and jurisdiction, marking clauses that need qualified legal review before use.
- dummy-datasetGenerates synthetic datasets from requested columns and constraints, producing test fixtures in formats such as CSV, JSON or SQL.
- grammar-checkChecks supplied prose for grammar, logic and flow, suggesting localized corrections that preserve the author's wording and intended argument.
- growth-loopsExplores recurring growth mechanisms around a product's user behavior, comparing candidate loops and the conditions each needs to sustain itself.
- intended-vs-implementedCompares a system's intended behavior with its implementation, building an explicit model of expectations to reveal gaps generic scanners may miss.
- interview-scriptBuilds a customer-interview script around jobs and real experiences, avoiding leading questions and premature product pitching.
- job-storiesTranslates customer situations and motivations into job stories, adding expected outcomes and acceptance conditions for product-backlog discussion.
- metrics-dashboardPlans a product metrics dashboard with named data sources and alert rules, tying each measure to an operational or product question.
- monetization-strategyDevelops monetization options for a product and audience, pairing each proposed revenue model with fit assumptions, risks and validation experiments.
- north-star-metricDefines a product's North Star metric and supporting inputs, checking whether the measurement reflects the value users receive.
- outcome-roadmapRewrites a feature-output roadmap around intended outcomes, connecting proposed initiatives to user and business changes rather than deliverable counts.
- pre-mortemChallenges a PRD or launch plan with a pre-mortem, grouping possible failures and identifying which risks could block launch.
- pricing-strategyExamines pricing models, competitors and willingness-to-pay evidence, producing a pricing design whose uncertain assumptions remain visible.
- prioritization-frameworksCompares prioritization frameworks and their required inputs, helping a team select an approach suited to its decision rather than a universal score.
- product-strategyOrganizes product strategy around target segments, value, capabilities and tradeoffs, connecting a vision to the choices required to pursue it.
- release-notesConverts tickets and change records into user-facing release notes, organizing concrete changes by type and explaining their effects.
- retroFacilitates a sprint retrospective from team observations, producing prioritized improvements with owners and follow-up actions.
- review-resumeReviews a product-management resume against a target role, improving evidence, structure and relevance without inventing experience.
- sentiment-analysisAnalyzes feedback for sentiment and customer-job patterns, organizing evidence about satisfaction across distinct user segments.
- shipping-artifactsAssembles the durable documentation needed to review an AI-built application, covering architecture, permissions and operational evidence before shipping.
- sprint-planBuilds a sprint plan from capacity, candidate stories and dependencies, exposing delivery risks before the team commits to scope.
- sql-queriesDrafts SQL from a question and supplied schema information, targeting supported warehouse dialects while making the query's assumptions visible.
- stakeholder-mapMaps stakeholders by influence and interest, producing targeted communication approaches and a plan for keeping relevant people informed.
- startup-canvasCombines product strategy and business-model questions in a startup canvas, separating strategic choices from revenue and cost assumptions.
- strategy-red-teamStress-tests a product strategy's key assumptions, ranking plausible failure modes and inexpensive validation checks before delivery investment.
- summarize-interviewSynthesizes a customer interview into a structured record of jobs, satisfaction evidence and follow-up actions for product discovery.
- summarize-meetingTurns a meeting transcript into structured notes with decisions and assigned actions, keeping discussion context available for later follow-up.
- test-scenariosDerives test scenarios from user stories, recording starting conditions, roles, actions and expected results for systematic quality review.
- user-segmentationGroups users by behavior, needs and feedback evidence, producing actionable segments instead of treating the entire audience as one persona.
- user-storiesWrites backlog stories with acceptance criteria and supporting design context, applying story-quality conventions to make work discussable and testable.
- value-prop-statementsTurns an existing value proposition into customer-facing statements for marketing and onboarding, adapting wording to specific audience decisions.
- value-propositionDevelops a detailed customer value proposition by comparing the user's situation, desired change and alternatives before shaping the offer.
- wwasStructures a backlog item as purpose, change and acceptance conditions, connecting product intent to an independently testable piece of work.
- 13c-metabolic-fluxEstimates metabolic fluxes from carbon-13 tracing measurements, connecting atom mappings and simulation results to constrained fits and uncertainty checks.High static risk — review source first
- analytical-method-validationOrganizes analytical-procedure validation and transfer from method requirements, producing framework-specific plans, checks and documentation rather than a generic laboratory checklist.
- bgpt-paper-searchSearches BGPT by topic or DOI and organizes paper-level findings with reported evidence, limitations and provenance for scientific investigation.High static risk — review source first
- bulk-rnaseqTakes bulk RNA-seq reads or quantification outputs toward gene-level differential analysis, checking replication, strandedness and preprocessing assumptions.High static risk — review source first
- cellprofilerBuilds reproducible CellProfiler microscopy pipelines from images and channel manifests, producing segmentation, counts and fluorescence measurements with batch-processing checks.High static risk — review source first
- clinical-reportsStructures clinical and research report drafts from synthetic or de-identified material, adding deterministic checks without supplying independent clinical decisions.High static risk — review source first
- database-lookupRetrieves database-backed facts through documented public endpoints, retaining filters, pagination and source details so the result can be checked.High static risk — review source first
- dnanexus-integrationPackages genomics tasks for DNAnexus using its CLI and workflow tools, organizing inputs, execution definitions and provenance for reproducible runs.High static risk — review source first
- fluidsimPlans and inspects FluidSim simulations with explicit numerical and resource limits, supporting controlled restarts and analysis of computational-fluid-dynamics output.High static risk — review source first
- generate-imageCreates or revises raster visuals through the OpenRouter image interface, translating a visual brief into model requests and generated image assets.High static risk — review source first
- genomic-coordinatesChecks genomic intervals and variant representations across coordinate conventions, identifying assembly and contig mismatches before downstream comparison.High static risk — review source first
- hypogenicPlans hypothesis-generation experiments with HypoGeniC or HypoRefine, organizing labeled datasets, configuration and hypothesis-bank evaluation.High static risk — review source first
- lab-hardware-cadTurns laboratory hardware requirements into parametric build123d models and fabrication exports such as STEP, STL and DXF files.High static risk — review source first
- latex-postersArranges research content and figures into a LaTeX conference poster, using supported poster classes and checking multi-column presentation requirements.High static risk — review source first
- markitdownConverts supported documents and selected web inputs to Markdown with MarkItDown, preparing readable text for search, analysis or retrieval ingestion.High static risk — review source first
- matlabDevelops and reviews MATLAB or Octave numerical workflows, covering arrays, time data, graphics and explicit exchange with Python.High static risk — review source first
- molecular-dynamicsConfigures molecular simulations and analyzes trajectories with OpenMM and MDAnalysis, connecting system preparation to energy and production-run checks.High static risk — review source first
- nmrglueProcesses calibrated one-dimensional NMR signals into phased spectra, candidate peaks and integration regions, retaining the axis and calibration assumptions.High static risk — review source first
- omero-integrationWorks with OMERO microscopy datasets and annotations through documented clients, organizing image retrieval, region information and automation tasks.High static risk — review source first
- ontology-term-resolutionMaps scientific labels to ontology identifiers and checks existing CURIEs, using public lookup services to resolve naming and prefix ambiguity.High static risk — review source first
- opentrons-integrationAuthors and simulates Opentrons liquid-handling protocols for supported robots, checking labware, deck configuration and API compatibility before physical use.
- pacsomaticPrepares tumor-normal PacBio HiFi inputs for nf-core/pacsomatic, producing samplesheets and pinned Nextflow launch materials for a reproducible genomics run.High static risk — review source first
- paperclipUses the Paperclip CLI or SDK to search biomedical and regulatory records, keeping retrieved passages and document sources available for evidence review.High static risk — review source first
- parallel-webUses Parallel's search and extraction tools to gather current web evidence, supporting structured enrichment and monitored research questions.High static risk — review source first
- pathogen-variant-surveillanceQueries public pathogen-sequence surveillance data to describe lineage proportions and reporting delays, preserving the limits of descriptive genomic observations.
- pi-agentConfigures and extends the Pi terminal coding harness, connecting model providers and local settings to reusable skills and extensions.High static risk — review source first
- pptx-postersBuilds editable PowerPoint research posters from approved local text and assets, checking the resulting layout and keeping the deliverable macro-free.High static risk — review source first
- protocolsio-integrationReads and exports protocols.io records using documented interfaces, separating bounded retrieval from proposed changes that require a distinct execution decision.High static risk — review source first
- pybammSimulates battery experiments with PyBaMM and compares predicted voltage curves, documenting parameters and checking solver and mesh sensitivity.High static risk — review source first
- pyhealthBuilds clinical machine-learning workflows with PyHealth, connecting dataset loading and prediction tasks to validation that checks leakage and task assumptions.
- pymatgenAnalyzes material structures with pymatgen, supporting conversion, symmetry checks and derived materials calculations while retaining source-data assumptions.High static risk — review source first
- pytdcUses Therapeutics Data Commons datasets and benchmarks through PyTDC, organizing task-specific splits, evaluators and bounded molecular scoring.High static risk — review source first
- scholar-evaluationReviews scholarly work using traceable evidence and explicit rubrics, producing developmental feedback while separating quality discussion from consequential ranking.High static risk — review source first
- scientific-visualizationCreates scientific figures from data with standard plotting libraries, checking uncertainty, missing values and accessible visual encoding for publication.High static risk — review source first
- scikit-survivalBuilds censored and competing-risk survival analyses with scikit-survival, linking preprocessing and model selection to leakage-aware evaluation.High static risk — review source first
- shapExplains model predictions with SHAP, selecting suitable explainers and checking feature attributions against the data and model output structure.High static risk — review source first
- tamarindAccesses hosted molecular-design and structural-biology tools through Tamarind, translating a research task into remote API or MCP jobs.High static risk — review source first
- treatment-plansFormats existing clinician-approved treatment decisions into structured documentation, checking local files without originating diagnosis or treatment recommendations.High static risk — review source first
- uncertainty-and-unitsTracks units and propagates measurement uncertainty through scientific calculations, producing dimensionally checked results and explicit uncertainty budgets.High static risk — review source first
- waypoint-bioSupports research with Waypoint microbiome foundation models and related datasets, organizing checkpoint use and evaluation against documented benchmark tasks.High static risk — review source first
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.
