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.
Category: AI & models
9,019 results · page 44 of 301
- View details
talk-normalSkillAI & models
Lets your agent write shorter, plain responses by installing a system prompt into AGENTS.md.
Ready to connect★ 2k
- View details
crashlytics-triageSkillAI & models
Lets your agent triage app crashes by pulling top issues from Firebase Crashlytics and summarizing them.
Ready to connect★ 2k
- View details
ai-cinematic-short-filmSkillAI & models
Plan AI short films with story, shots, prompts, and continuity.
Ready to connect★ 2k
- View details
create-motion-graphicsSkillAI & models
Use whenever the agent needs to add, create, hand-author, patch, or place Motion Graphic JSX assets in a OpenChatCut project. This is the direct-authoring path: use create_motion_graphic_from_code / edit_asset / edit_item, not motion-graphic-gen or submit_motion_graphic. Covers project/timeline inta
Ready to connect★ 2k
- View details
product-helpSkillAI & models
OpenChatCut product knowledge — UI layout, editor features, and how generation providers are configured. Use when the user asks about the product interface, how to use a feature, where to find something, or needs GUI guidance for something the agent cannot do directly. Also use as fallback when a ta
Ready to connect★ 2k
- View details
verificationSkillAI & models
Use when checking whether agent edits are reflected in the OpenChatCut project and editor.
Ready to connect★ 2k
- View details
widget-formsSkillAI & models
Use when the agent should ask the user for structured input with an in-chat form, including single-select, multi-select, text fields, style pickers, or voice audition choices.
Ready to connect★ 2k
- View details
github-codebase-briefingSkillAI & models
Lets your agent generate a briefing on any GitHub repository, summarizing the code and highlighting key issues and PRs.
Ready to connect★ 2k
- View details
stitch-sdk-developmentSkillAI & models
Lets your agent work on the Stitch SDK codebase with guidance on its architecture, error handling, and workflow.
Ready to connect★ 2k
- View details
agent-coordinationSkillAI & models
Lets your agent coordinate multiple helper agents by assigning and tracking work across them.
Ready to connect★ 2k
- View details
babysit-babysitter-issuesSkillAI & models
Lets your agent find and work on GitHub issues assigned to it in the babysitter repo.
Ready to connect★ 2k
- View details
consensus-mechanismsSkillAI & models
Lets your agent coordinate multiple agents by agreeing on shared state and electing a leader.
Ready to connect★ 2k
- View details
convoy-managementSkillAI & models
Lets your agent create, track, and land convoys of related work orders across multiple AI agents.
Ready to connect★ 2k
- View details
external-tool-coordinationSkillAI & models
Lets your agent delegate tasks to external AI tools like Codex and Gemini for cross-model review and implementation.
Ready to connect★ 2k
- View details
integrate-harnessSkillAI & models
Guides your agent through adding a new CLI coding agent adapter, including scaffolding, session parsing, auth, and tests.
Ready to connect★ 2k
- View details
merge-queueSkillAI & models
Lets your agent manage a code merge queue by collecting changes, resolving conflicts, and merging them in order.
Ready to connect★ 2k
- View details
model-profile-resolutionSkillAI & models
Lets your agent pick the right AI model for each task based on cost and quality needs.
Ready to connect★ 2k
- View details
research-orchestrationSkillAI & models
Lets your agent run several research sub-agents in parallel and combine their findings into one validated report.
Ready to connect★ 2k
- View details
session-managementSkillAI & models
Lets your agent start, hand off, and restore AI agent sessions with a persistent identity.
Ready to connect★ 2k
- View details
work-decompositionSkillAI & models
Lets your agent break big goals into small, trackable units of work it can follow one by one.
Ready to connect★ 2k
- View details
tinybird-typescript-sdk-guidelinesSkillAI & models
Gives your agent guidance for writing type-safe TypeScript code with the Tinybird SDK to manage data sources and queries.
Ready to connect★ 2k
- View details
domain-name-brainstormerSkillAI & models
Lets your agent suggest domain name ideas for a project and check if they are available across endings like .com or .io.
Ready to connect★ 2k
- View details
lead-research-assistantSkillAI & models
Lets your agent research and score potential sales leads and suggest ways to contact them.
Ready to connect★ 2k
- View details
beuiSkillAI & models
Pick and install beUI (@beui) animated React components from the shadcn registry. Use when building motion UI, agent/chat interfaces, toasts, docks, bottom sheets, drawers, popovers, sliders, loaders, 404 pages, or any beui.dev component. Maps user intent to exact @beui install slugs instead of inve
Ready to connect★ 2k
- View details
error-diagnose-fixSkillAI & models
Agent Loop for build/compilation errors: run the build yourself, collect ALL errors at once, find root causes via dependency analysis, fix in order, revert failed hypotheses, loop until green. Eliminates the user-paste-error → agent-guess → still-broken ping-pong.
Ready to connect★ 2k
- View details
ui-iterationSkillAI & models
Agent Loop for pixel-perfect UI adjustments: extract a structured spec from the user's intent, apply changes one property at a time, self-verify via screenshot, and converge instead of ping-ponging. Designed for high-fidelity UI cloning and spacing/style iteration.
Ready to connect★ 2k
- View details
agent-deviceSkillAI & models
Lets your agent tap, type, scroll, and screenshot on iOS and Android simulators or devices.
Ready to connect★ 2k
- View details
agent-evaluationSkillAI & models
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
Ready to connect★ 2k
- View details
context-engineeringSkillAI & models
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
Ready to connect★ 2k
- View details
create-agentSkillAI & models
Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns
Ready to connect★ 2k
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.
54,764 of the 55,196 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.