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 501 of 1,818
- View details
errorsSkillFiles & storage
Teaches your agent how to define and check error classes when working on Ledger Live code.
Ready to connect★ 616
- View details
feature-devSkillDev tools
Lets your agent develop features step by step while understanding your codebase and its architecture.
Ready to connect★ 616
- View details
get-pr-commentsSkillDev tools
Fetch and summarize review comments from the active pull request
Ready to connect★ 616
- View details
gh-code-reviewSkillDev tools
Gives your agent step-by-step instructions for reviewing GitHub pull requests.
Ready to connect★ 616
- View details
git-conventionsSkillCommunication
Lets your agent follow your team's git conventions for branch names, commit messages, and pull request titles.
Ready to connect★ 616
- View details
impacting-prsSkillDev tools
Lets your agent find open PRs affected by a refactor or migration and notify their authors with the right level of warning.
Ready to connect★ 616
- View details
knip-migrationSkillDev tools
Lets your agent detect unused code and dependencies in packages using the knip tool with explicit exports.
Ready to connect★ 616
- View details
ldls-nativeSkillMedia
Lets your agent follow Ledger's Lumen design rules when building React Native user interfaces.
Ready to connect★ 616
- View details
ldls-webSkillMedia
Lets your agent follow Ledger's Lumen React design system rules when building UI components.
Ready to connect★ 616
- View details
ledger-wallet-cliSkillFiles & storage
Lets your agent manage a Ledger hardware wallet: check balances, receive funds, send crypto, and swap.
Ready to connect★ 616
- View details
mvvm-architectureSkillFiles & storage
Lets your agent plan and review app code following the MVVM pattern in Ledger Live desktop and mobile projects.
Ready to connect★ 616
- View details
package-public-apiSkillFiles & storage
Guides your agent to structure package exports using barrel files and keep private code in internals folders.
Ready to connect★ 616
- View details
pre-reviewSkillDev tools
Lets your agent perform a deep code review before you commit changes.
Ready to connect★ 616
- View details
prefer-set-hasSkillFiles & storage
Guides your agent to write faster membership checks in TypeScript using Set.has() instead of Array.includes().
Ready to connect★ 616
- View details
react-generalSkillFiles & storage
Gives your agent React and React Native coding rules to follow when writing or reviewing TypeScript files.
Ready to connect★ 616
- View details
rebuild-to-fix-lib-import-errorsSkillDev tools
Lets your agent rebuild a library in the monorepo when typecheck reports an import error from it.
Ready to connect★ 616
- View details
redux-sliceSkillDev tools
Gives your agent best-practice guidance for writing Redux Toolkit createSlice code.
Ready to connect★ 616
- View details
remove-feature-flagSkillProductivity
Lets your agent remove a feature flag from the codebase, validate the change, and open a draft pull request.
Ready to connect★ 616
- View details
rtk-query-apiSkillDev tools
Gives your agent best practices for writing RTK Query createApi code.
Ready to connect★ 616
- View details
run-buildsSkillDev tools
Lets your agent trigger production builds (desktop, Android, iOS) for a ledger-live branch and comment on the PR.
Ready to connect★ 616
- View details
run-e2e-ciSkillDev tools
Lets your agent trigger end-to-end test workflows on a branch and post the results as a PR comment.
Ready to connect★ 616
- View details
slack-pr-messageSkillCommunication
Lets your agent draft a formatted Slack message to share a pull request with your team.
Ready to connect★ 616
- View details
wire-devtoolSkillAI & models
Lets your agent wire an existing devtool package into host apps and optionally create bindings.
Ready to connect★ 616
- View details
zod-schemasSkillDev tools
Gives your agent Zod schema patterns for validating API types.
Ready to connect★ 616
- View details
agentic-rolloutSkillAI & models
Assess an agent, bridge it into Relax, check launch readiness, and demonstrate resident Agentic rollout with evidence. Use when evaluating an agent app before integration, connecting an external agent with --use-agentic-rollout, auditing model-visible context linearity or SessionForest export, check
Ready to connect★ 615
- View details
debug-hangSkillProductivity
Lets your agent troubleshoot frozen distributed training jobs by collecting cluster state and task stacks.
Ready to connect★ 615
- View details
model-integrationSkillAI & models
Lets your agent add new model architectures to the Relax training pipeline and fix weight sync problems.
Ready to connect★ 615
- View details
nemo-gym-recipe-integrationSkillDev tools
Integrate a new NVIDIA NeMo Gym environment into Relax as a three-step recipe. Use when adding or debugging a recipe under examples/nemo_gym_agentic/recipes; covers data preparation, a local private Gym service, direct Ray training launch, verifier validation, callback networking, lifecycle cleanup,
Ready to connect★ 615
- View details
nw-ab-critique-dimensionsSkillAI & models
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Ready to connect★ 614
- View details
nw-abr-critique-dimensionsSkillAI & models
Lets your agent review its own work against quality checks like templates, safety, testing, and priorities.
Ready to connect★ 614
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.