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
54,514 results · page 493 of 1,818
- View details
agent-authoringSkillAI & models
Guides your agent through creating and improving other AI agents, including picking models and configuring tools.
Ready to connect★ 625
- View details
agent-builderSkillFiles & storage
Lets your agent create and configure new agent definition files with system prompts and tool permissions.
Ready to connect★ 625
- View details
agent-canvasSkillWeb & browsing
Lets your agent open a web page and visually pick elements to get their selectors and details.
Ready to connect★ 625
- View details
agent-canvas-setupSkillWeb & browsing
Checks and installs the dependencies your agent needs before using canvas skills.
Ready to connect★ 625
- View details
agent-capability-assessorSkillFiles & storage
Lets your agent check whether an existing agent can handle a task by reviewing its files and skills.
Ready to connect★ 625
- View details
agent-checkSkillFiles & storage
Lets your agent figure out which audit agents should review each file based on its type and content.
Ready to connect★ 625
- View details
agent-code-generatorSkillFiles & storage
Lets your agent create agent definition files from your intent using standard templates.
Ready to connect★ 625
- View details
agent-command-authoringSkillFiles & storage
Lets your agent create slash command files that delegate tasks to subagents.
Ready to connect★ 625
- View details
agent-commitSkillAI & models
Lets your agent analyze code changes and create a git commit with a meaningful message.
Ready to connect★ 625
- View details
agent-communication-protocolSkillAI & models
Lets your agent talk to other AI agents and apps using a shared standard message format.
Ready to connect★ 625
- View details
agent-compliance-auditorSkillAI & models
Lets your agent check AI agent definitions against the Antigravity audit rubric for compliance.
Ready to connect★ 625
- View details
agent-context-generatorSkillProductivity
Lets your agent create an AGENTS.md file that documents your project's conventions, workflows, and tasks.
Ready to connect★ 625
- View details
agent-creationSkillAI & models
Guides your agent through creating and configuring new Claude agents with the Agent SDK.
Ready to connect★ 625
- View details
agent-creation-skillSkillSearch
Lets your agent browse a registry of ready-made Claude Code skills to find and install ones for new tasks.
Ready to connect★ 625
- View details
agent-curatorSkillAI & models
Lets your agent improve another agent's definition through guided research and refinement.
Ready to connect★ 625
- View details
agent-customizationSkillFiles & storage
Lets your agent create, fix, and debug instruction and prompt files that customize coding assistants.
Ready to connect★ 625
- View details
agent-deckSkillAI & models
Lets your agent start, stop, restart, and fork terminal sessions for coding agents and view their output.
Ready to connect★ 625
- View details
agent-define-skillSkillAI & models
Lets your agent define a subagent's responsibilities, expertise areas, and configuration.
Ready to connect★ 625
- View details
agent-designSkillMedia
Guides your agent through designing AI agents using recommended patterns and architectures.
Ready to connect★ 625
- View details
agent-design-best-practicesSkillFiles & storage
Guides your agent in writing and reviewing well-structured Claude Code agent definition files.
Ready to connect★ 625
- View details
light-citationSkillMonitoring & ops
Lets your agent check whether cited sources actually exist and support the claims in a manuscript.
Ready to connect★ 624
- View details
light-consistencySkillDocs & knowledge
Lets your agent check that terms, metric names and values, and method names match across your paper, slides, code, and docs.
Ready to connect★ 624
- View details
light-data-engineeringSkillDev tools
Lets your agent check research datasets for source, license, size, and leakage risks before planning experiments.
Ready to connect★ 624
- View details
light-experiment-codingSkillDev tools
Lets your agent turn a frozen experiment plan into minimal, test-first, reproducible experiment code.
Ready to connect★ 624
- View details
light-figureSkillDev tools
Guides your agent through making publication-quality research figures that clearly support the paper's argument.
Ready to connect★ 624
- View details
light-file-readingSkillFiles & storage
Lets your agent read and understand Word, PDF, Excel, images, video and other files, including charts and structure.
Ready to connect★ 624
- View details
light-frontend-designSkillDocs & knowledge
Lets your agent turn vague UI requests into working React and Tailwind code with design notes.
Ready to connect★ 624
- View details
light-idea-critiqueSkillDev tools
Lets your agent critique a research idea against top-conference reviewer standards and veto weak ones.
Ready to connect★ 624
- View details
light-idea-generationSkillAI & models
Lets your agent turn a vague research direction into structured, feasible candidate ideas instead of generic brainstorming.
Ready to connect★ 624
- View details
light-literature-searchSkillSearch
Lets your agent survey recent and classic academic papers across open databases and map a research field.
Ready to connect★ 624
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.
54,082 of the 54,514 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.