Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Filter by category
54,017 results · page 243 of 1,801
- View details
anima-security-basicsSkillSecurity
Lets your agent audit and harden Anima and Figma design tokens for design-to-code pipelines.
Ready to connect★ 3k
- View details
anima-upgrade-migrationSkillDev tools
Lets your agent analyze and run Anima SDK version upgrades with rollback evidence.
Ready to connect★ 3k
- View details
anima-webhooks-eventsSkillMedia
Lets your agent automatically generate Anima code from Figma designs when changes happen.
Ready to connect★ 3k
- View details
anth-advanced-troubleshootingSkillAI & models
Debugs complex Claude API issues like context window overflow errors.
Ready to connect★ 3k
- View details
anth-architecture-variantsSkillAI & models
Lets your agent pick and implement the right Claude API architecture pattern for a task.
Ready to connect★ 3k
- View details
anth-ci-integrationSkillAI & models
Lets your agent set up CI/CD pipelines for apps using the Claude API.
Ready to connect★ 3k
- View details
anth-common-errorsSkillAI & models
Lets your agent diagnose and fix Claude API errors by looking up HTTP status codes.
Ready to connect★ 3k
- View details
anth-core-workflow-aSkillCommunication
Lets your agent learn how to build tool use (function calling) workflows with the Messages API.
Ready to connect★ 3k
- View details
anth-core-workflow-bSkillCommunication
Lets your agent build streaming and Message Batches API workflows for Claude.
Ready to connect★ 3k
- View details
anth-cost-tuningSkillAI & models
Lets your agent cut Claude API costs by routing tasks to cheaper models and using prompt caching.
Ready to connect★ 3k
- View details
anth-data-handlingSkillAI & models
Lets your agent apply data privacy and PII-handling patterns to keep Claude usage compliant.
Ready to connect★ 3k
- View details
anth-debug-bundleSkillAI & models
Lets your agent collect Claude API debug evidence for support and troubleshooting.
Ready to connect★ 3k
- View details
anth-deploy-integrationSkillCloud & infra
Lets your agent deploy Claude API integrations to production cloud environments.
Ready to connect★ 3k
- View details
anth-enterprise-rbacSkillAI & models
Lets your agent manage Anthropic enterprise settings like workspaces and role-based access controls.
Ready to connect★ 3k
- View details
anth-hello-worldSkillCommunication
Lets your agent create a minimal working example of calling the Claude Messages API.
Ready to connect★ 3k
- View details
anth-incident-runbookSkillMonitoring & ops
Lets your agent run step-by-step incident response procedures for Claude API outages and slowdowns.
Ready to connect★ 3k
- View details
anth-install-authSkillSecurity
Sets up Anthropic Claude SDK authentication for Python so your agent can use Claude's API.
Ready to connect★ 3k
- View details
anth-known-pitfallsSkillAI & models
Helps your agent spot and avoid common Claude API mistakes and anti-patterns.
Ready to connect★ 3k
- View details
anth-load-scaleSkillAI & models
Lets your agent run load tests, set up auto-scaling, and plan capacity for Claude.
Ready to connect★ 3k
- View details
codeSkillDev tools
Guides your agent to plan before writing, reviewing, refactoring, or debugging code.
Ready to connect★ 3k
- View details
quit-sponsorSkillDocs & knowledge
Lets your agent act as a quit-smoking sponsor that tracks your quit, handles cravings, slips, and check-ins.
Ready to connect★ 3k
- View details
x-twitter-scraperSkillWeb & browsing
Lets your agent scrape X (Twitter) posts and plan actions on a connected X account.
Ready to connect★ 3k
- View details
alliance-building-diplomacySkillSecurity
Guides your agent through building multi-party alliances by analyzing each party's strengths, fears, and drafting concrete mutual defense terms.
Ready to connect★ 3k
- View details
alliance-formation-strategySkillDev tools
Guides your agent through evaluating partners and structuring alliances for defense or joint operations.
Ready to connect★ 3k
- View details
ancient-chinese-calendar-determinationSkillProductivity
Lets your agent guide you through the ancient Chinese method of finding equinoxes and solstices by observing stars and daylight.
Ready to connect★ 3k
- View details
ancient-divination-ritual-procedureSkillDocs & knowledge
Lets your agent follow step-by-step instructions for performing a traditional oracle bone divination ritual.
Ready to connect★ 3k
- View details
ancient-leadership-succession-protocolSkillAI & models
Lets your agent design leadership succession plans using a merit-based model with recommendations, testing, and formal transfer.
Ready to connect★ 3k
- View details
assassination-as-desperate-measureSkillSecurity
Lets your agent analyze historical last-resort assassination strategies from ancient Chinese statecraft texts.
Ready to connect★ 3k
- View details
astronomical-observation-methodSkillDev tools
Lets your agent interpret planetary positions and celestial anomalies as omens for governance and earthly events.
Ready to connect★ 3k
- View details
attract-talent-to-organizationSkillDev tools
Guides your agent through a step-by-step method for recruiting talented people using respect, incentives, and shared hardship.
Ready to connect★ 3k
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,585 of the 54,017 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.