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
55,435 results · page 881 of 1,848
- View details
language-idioms-refinerSkillDocs & knowledge
Lets your agent define your project's language-specific coding idioms in a shared document to guide generated code.
Ready to connect★ 193
- View details
lattice-initSkillDev tools
Lets your agent scan a Lattice project repo and set up or update its configuration files.
Ready to connect★ 193
- View details
learning-harvestSkillDocs & knowledge
Lets your agent save lessons learned from past work and reuse them to guide future tasks.
Ready to connect★ 193
- View details
om-backlogSkillProductivity
Lets your agent turn a product brief or spec into a tracker backlog with epics, stories, and tasks.
Ready to connect★ 193
- View details
om-discoverSkillDev tools
Lets your agent run a product discovery session and write a product brief covering problem, stakeholders, flows, scope, and success criteria.
Ready to connect★ 193
- View details
om-mockup-prototypeSkillDev tools
Lets your agent turn a product brief into a clickable low-fi prototype to test flows during discovery.
Ready to connect★ 193
- View details
om-setup-discovery-pipelineSkillAI & models
Lets your agent add product roles, discovery stages, and protected decision files to an already configured pipeline repo.
Ready to connect★ 193
- View details
om-synthetic-usersSkillDev tools
Lets your agent simulate a panel of user personas and interview them to test a brief, spec, or prototype.
Ready to connect★ 193
- View details
python-runSkillFiles & storage
Lets your agent run, debug, and fix Python scripts in your project, including checking dependencies and analyzing errors.
Ready to connect★ 193
- View details
refactor-safelySkillMonitoring & ops
Lets your agent restructure existing code without changing how it behaves, using safety checks and tests.
Ready to connect★ 193
- View details
refiners-updateSkillDocs & knowledge
Lets your agent update existing Lattice standards after changes, recording a git-native change note.
Ready to connect★ 193
- View details
requirement-forgeSkillDev tools
Lets your agent turn rough feature ideas into structured specs by interviewing you like a product manager.
Ready to connect★ 193
- View details
requirement-forge-refinerSkillDev tools
Lets your agent run a guided session to set your project's requirement standards and save them as a requirement-standards.md file.
Ready to connect★ 193
- View details
requirement-qualitySkillDev tools
Lets your agent write and check feature specs for completeness, testable acceptance criteria, and clear scenarios.
Ready to connect★ 193
- View details
review-refinerSkillDocs & knowledge
Lets your agent customize how code reviews are run and save the rules to a review-standards.md file.
Ready to connect★ 193
- View details
secure-codingSkillDatabases & data
Makes your agent write code with built-in security checks like input validation and secret handling.
Ready to connect★ 193
- View details
skill-alignSkillDocs & knowledge
Lets your agent audit and fix project docs so they match the skills that actually exist in the codebase.
Ready to connect★ 193
- View details
skill-enhanceSkillAI & models
Lets your agent rewrite and improve an existing Lattice skill to work reliably with modern AI models.
Ready to connect★ 193
- View details
skill-forgeSkillFiles & storage
Lets your agent create new Lattice skills (atom, molecule, or refiner) that follow all framework conventions.
Ready to connect★ 193
- View details
skill-reviewSkillDev tools
Lets your agent audit a Lattice skill by simulating expert reviewers and producing a ranked gap report with fixes.
Ready to connect★ 193
- View details
skill-tightenSkillAI & models
Lets your agent rewrite skill instructions into concise, imperative language that agents follow more reliably.
Ready to connect★ 193
- View details
skill-validateSkillFiles & storage
Lets your agent check a Lattice SKILL.md file for structural errors and convention violations.
Ready to connect★ 193
- View details
bullmqSkillProductivity
Lets your agent create and manage BullMQ background job queues and workers in your codebase.
Ready to connect★ 192
- View details
commit-and-doneSkillProductivity
Lets your agent commit changes, mark the current task done, and close its tab.
Ready to connect★ 192
- View details
comparison-pageSkillWeb & browsing
Lets your agent create or update website comparison pages with verdicts, screenshots, and pros and cons.
Ready to connect★ 192
- View details
comparison-publishingSkillWeb & browsing
Turns your stored competitor data into ready-to-use website content.
Ready to connect★ 192
- View details
comparison-taxonomySkillDev tools
Lets your agent keep the comparison schema consistent across the catalog.
Ready to connect★ 192
- View details
competitor-discoverySkillDev tools
Finds new competitors worth adding to your comparison program.
Ready to connect★ 192
- View details
create-tierSkillDev tools
Lets your agent add a new API tier with config, middleware, routes, and tests to your codebase.
Ready to connect★ 192
- View details
crudSkillDev tools
Lets your agent generate and edit CRUD API modules with add, delete, update, and query routes.
Ready to connect★ 192
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.
55,004 of the 55,435 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.