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 500 of 1,818
- View details
gumcliSkillDev tools
Lets your agent scaffold, generate, validate, and screenshot UIs for Gum projects via the gumcli command-line tool.
Ready to connect★ 620
- View details
html-to-gum-fidelitySkillDev tools
Lets your agent convert HTML pages into Gum UI layouts and iteratively refine them until they match pixel-for-pixel.
Ready to connect★ 620
- View details
refactoring-directionSkillDev tools
Gives your agent rules for how to restructure Gum code, like extracting helpers or placing new logic.
Ready to connect★ 620
- View details
skills-writerSkillFiles & storage
Lets your agent create and update skill files that document how parts of your project work.
Ready to connect★ 620
- View details
user-asksSkillSearch
Lets your agent answer user questions by searching docs and code, citing sources, and filing GitHub issues.
Ready to connect★ 620
- View details
xnafiddleSkillDev tools
Lets your agent create and run XNA-syntax code experiments in the browser and export them to a chosen runtime.
Ready to connect★ 620
- View details
dataframelySkillDev tools
Teaches your agent to write Polars data-processing code using dataframely schemas and collections.
Ready to connect★ 618
- View details
batch-feature-devSkillProductivity
Lets your agent work through batches of Jira tickets, developing each feature and opening draft pull requests.
Ready to connect★ 616
- View details
card-endpoint-shapeSkillDev tools
Gives your agent the conventions to follow when adding or editing an endpoint in the card management API file.
Ready to connect★ 616
- View details
client-idsSkillDev tools
Lets your agent look up and manage privacy-safe client identifiers like device, user, and Datadog IDs.
Ready to connect★ 616
- View details
cloud-sync-moduleSkillDev tools
Helps your agent write, review, or debug cloud sync data modules in Ledger Live.
Ready to connect★ 616
- View details
codeownershipSkillFiles & storage
Lets your agent annotate files with their owning team to help split large pull requests.
Ready to connect★ 616
- View details
coin-families-contractSkillDev tools
Guides your agent to keep coin-specific code in families/ and use the families contract in shared UI code.
Ready to connect★ 616
- View details
coin-modulesSkillDev tools
Gives your agent the rules and file layout for building or editing coin modules in Ledger Live's codebase.
Ready to connect★ 616
- View details
console-logSkillMonitoring & ops
Gives your agent a shared convention for choosing console log levels when writing code in this monorepo.
Ready to connect★ 616
- View details
create-changesetSkillDocs & knowledge
Lets your agent create changeset files that document package changes for releases in the ledger-live repo.
Ready to connect★ 616
- View details
ddd-data-layer-advancedSkillDev tools
Helps your agent structure a data layer where one API response feeds several entities using RTK Query or createAsyncThunk.
Ready to connect★ 616
- View details
ddd-structure-flowSkillDev tools
Guides your agent to organize code into the right layers and packages in a domain-driven monorepo.
Ready to connect★ 616
- View details
ddd-types-state-mocksSkillDev tools
Guides your agent to structure a data layer with entity slices, types, state, mocks, and tests.
Ready to connect★ 616
- View details
debug-rn-native-crashSkillMonitoring & ops
Lets your agent investigate native React Native crashes when JavaScript error logs are missing or unhelpful.
Ready to connect★ 616
- View details
detect-data-leaksSkillDev tools
Lets your agent check whether your current code changes introduce new personal-data leaks.
Ready to connect★ 616
- View details
device-intent-executorSkillDev tools
Lets your agent look up reference docs for building and running device intents in Ledger Live.
Ready to connect★ 616
- View details
devtools-import-boundarySkillDev tools
Lets your agent check that code files only import from allowed places when working in the devtools folder.
Ready to connect★ 616
- View details
dialogs-sliceSkillDev tools
Gives your agent a ready-made Redux slice pattern for managing dialog state in apps using MVVM.
Ready to connect★ 616
- View details
docs-migrateSkillDev tools
Lets your agent migrate and reorganize existing docs into a target structure.
Ready to connect★ 616
- View details
docs-update-or-createSkillFiles & storage
Gives your agent the repo's rules for writing or editing documentation files like READMEs and docs folders.
Ready to connect★ 616
- View details
e2e-desktop-add-or-updateSkillWeb & browsing
Lets your agent add or update end-to-end tests for sending and receiving cryptocurrencies in a desktop app.
Ready to connect★ 616
- View details
e2e-earnSkillWeb & browsing
Lets your agent run and fix end-to-end tests for Ledger's Earn staking features on desktop and mobile.
Ready to connect★ 616
- View details
e2e-mobile-add-or-updateSkillDev tools
Lets your agent write and update Detox end-to-end tests for the Ledger Live mobile app.
Ready to connect★ 616
- View details
e2e-swapSkillWeb & browsing
Lets your agent write and update end-to-end tests for swap features in Ledger Live desktop and mobile apps.
Ready to connect★ 616
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.