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
54,404 results · page 999 of 1,814
- View details
module-2SkillAI & models
Lets your agent explain concepts, code, and exercises from Module 2 (Agentic RAG) of a Build-an-Agent workshop.
Ready to connect★ 140
- View details
module-3SkillMonitoring & ops
Lets your agent explain evaluation concepts and interpret results for Module 3 of a Build-an-Agent workshop.
Ready to connect★ 140
- View details
module-4SkillAI & models
Lets your agent answer questions and explain concepts, code, and GPU issues from Module 4 of the Build-an-Agent workshop.
Ready to connect★ 140
- View details
module-5SkillAI & models
Lets your agent answer questions and explain concepts from Module 5 of the Build-an-Agent workshop.
Ready to connect★ 140
- View details
module-6SkillAI & models
Lets your agent answer questions about Module 6 of the Build-an-Agent workshop, covering agent safety concepts and code.
Ready to connect★ 140
- View details
nvwbSkillAI & models
Lets your agent create, build, and manage NVIDIA AI Workbench projects and environments using the nvwb command line.
Ready to connect★ 140
- View details
nvwb-projectSkillAI & models
Lets your agent understand the structure and setup of an NVIDIA AI Workbench project so it can work inside it correctly.
Ready to connect★ 140
- View details
principle-boundary-disciplineSkillDev tools
Guides your agent to put validation and error handling at system boundaries while keeping business logic in pure functions.
Ready to connect★ 140
- View details
principle-build-the-leverSkillAI & models
Guides your agent to build a reusable script or tool for a task instead of doing the work by hand.
Ready to connect★ 140
- View details
principle-experience-firstSkillDev tools
Guides your agent to prioritize user experience when weighing product or feature tradeoffs.
Ready to connect★ 140
- View details
principle-foundational-thinkingSkillDev tools
Guides your agent to pick core data structures and plan code structure before writing logic.
Ready to connect★ 140
- View details
principle-guard-the-context-windowSkillFiles & storage
Keeps your agent's context window manageable by routing large outputs to subagents and keeping only summaries in the main thread.
Ready to connect★ 140
- View details
principle-minimize-reader-loadSkillDev tools
Lets your agent review code for readability by counting indirection layers and collapsing needless wrappers.
Ready to connect★ 140
- View details
principle-model-the-domainSkillFiles & storage
Guides your agent to model a domain as a clear structure instead of scattered conditionals when writing stateful code.
Ready to connect★ 140
- View details
principle-never-block-on-the-humanSkillDev tools
Lets your agent proceed with reversible work on its own instead of pausing to ask for permission.
Ready to connect★ 140
- View details
principle-outcome-oriented-executionSkillDev tools
Guides your agent through code rewrites and migrations by focusing on the end architecture instead of temporary compatibility code.
Ready to connect★ 140
- View details
principle-prove-it-worksSkillProductivity
Makes your agent verify a finished task by checking the real result instead of just claiming it's done.
Ready to connect★ 140
- View details
principle-separate-before-serializing-shared-stateSkillFiles & storage
Guides your agent to split up shared files or state before letting multiple tasks write to them at once.
Ready to connect★ 140
- View details
principle-sequence-verifiable-unitsSkillDev tools
Guides your agent to break multi-step coding work into small, verifiable units and stack commits so each step is provable.
Ready to connect★ 140
- View details
principle-type-system-disciplineSkillDev tools
Guides your agent to write safer types in statically-typed languages, making invalid states impossible to represent.
Ready to connect★ 140
- View details
project-flow-opsSkillProductivity
Lets your agent track project tasks with explicit states, owners, blockers, and verified completion.
Ready to connect★ 140
- View details
recent-releaseSkillFiles & storage
Lets your agent turn recent release notes into a styled standalone HTML page.
Ready to connect★ 140
- View details
remotion-ref-replaySkillMedia
Lets your agent use the remotion claude skill to turn screen recordings into Remotion video rebuilds.
Ready to connect★ 140
- View details
session-learnSkillDev tools
Lets your agent save lessons, decisions, and next steps from a finished work session.
Ready to connect★ 140
- View details
setup-workshopSkillWeb & browsing
Lets your agent install and run the Build-an-Agent workshop locally on your own hardware.
Ready to connect★ 140
- View details
setup-workshop-nemoclawSkillAI & models
Lets your agent set up the NVIDIA Build-an-Agent workshop as a JupyterLab environment and get you the access URL and commands.
Ready to connect★ 140
- View details
show-me-your-workSkillMonitoring & ops
Lets your agent log every decision (what, why, evidence, result) to a TSV file you can review.
Ready to connect★ 140
- View details
startup-evaluationSkillDev tools
Lets your agent assess a startup's health, runway, key constraint, and next cheapest validation test.
Ready to connect★ 140
- View details
technical_writingSkillDocs & knowledge
Gives your agent a technical writing skill so it drafts clear, professional documentation.
Ready to connect★ 140
- View details
tracking-discoverSkillWeb & browsing
Lets your agent check which analytics platforms a website uses and gather its tracking data before analysis.
Ready to connect★ 140
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.
53,973 of the 54,404 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.