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
55,196 results · page 76 of 1,840
- View details
ce-strategySkillDev tools
Lets your agent create or update a STRATEGY.md file to capture product direction and roadmap.
Ready to connect★ 25k
- View details
ce-sweepSkillCommunication
Lets your agent collect new feedback from Slack and GitHub Issues, acknowledge it, and produce a ready-to-work plan.
Ready to connect★ 25k
- View details
ce-test-browserSkillWeb & browsing
Lets your agent run browser tests for the pages changed in your current branch or pull request.
Ready to connect★ 25k
- View details
ce-test-xcodeSkillDev tools
Lets your agent build and test iOS apps in a simulator and capture results as evidence.
Ready to connect★ 25k
- View details
ce-worktreeSkillDev tools
Lets your agent set up isolated git worktrees on a new branch or an existing branch, PR, or commit.
Ready to connect★ 25k
- View details
claude-only-skillSkillAI & models
Marks a skill so it only runs inside Claude Code and is skipped elsewhere.
Ready to connect★ 25k
- View details
custom-skillSkillAI & models
Lets your agent run a structured engineering workflow for planning, implementing, and reviewing code changes.
Ready to connect★ 25k
- View details
default-skillSkillAI & models
Lets your AI agent use official Compound Engineering workflows in code editors like Claude Code and Cursor.
Ready to connect★ 25k
- View details
disabled-skillSkillAI & models
A disabled skill placeholder that lets the agent skip model invocation for this entry.
Ready to connect★ 25k
- View details
lfgSkillDev tools
Lets your agent build and ship code autonomously, pushing changes and opening a pull request without stopping for check-ins.
Ready to connect★ 25k
- View details
skill-oneSkillDev tools
Lets your agent use a sample skill from the compound engineering plugin.
Ready to connect★ 25k
- View details
differential-fuzzerSkillDatabases & data
Lets your agent run a differential fuzzer to catch bugs in Turso by comparing outputs.
Ready to connect★ 24k
- View details
memory-benchmarkSkillDatabases & data
Shows your agent how to measure and analyze memory usage and heap allocations in Turso code.
Ready to connect★ 24k
- View details
testingSkillDatabases & data
Teaches your agent how to write and run tests, including .sqltest and Rust tests.
Ready to connect★ 24k
- View details
yield-injectionsSkillDatabases & data
Lets your agent add safe pause and failure points to state machines so long tasks can resume after interruptions.
Ready to connect★ 24k
- View details
furniture-fitSkillDev tools
Assess whether furniture fits in a measured Pascal room or layout. Use this skill for sofa, table, bed, cabinet, appliance, staging, placement, collision, clearance, or rotated-footprint questions. Produce a tool-backed spatial report that distinguishes footprint fit from unsupported height, door-sw
Ready to connect★ 24k
- View details
open-prSkillDev tools
Open a pull request on pascalorg/editor using the repo's PR template. Use when the user asks to open/create a PR, push and PR, or ship a branch in the editor repo.
Ready to connect★ 24k
- View details
open-pr2SkillDev tools
Open or update a pull request on pascalorg/editor with a plain-language issue-and-fix description based on the full branch diff. Use only when the user explicitly asks for OpenPR2 or /open-pr2.
Ready to connect★ 24k
- View details
pascal-3dSkillAI & models
Connect to Pascal and use its MCP tools to create, inspect, edit, validate, save, or hand off editable 3D building scenes. Use this skill whenever a user asks an agent to work in Pascal, make a room or building model, inspect a Pascal project, perform spatial edits, connect Pascal MCP, or return a v
Ready to connect★ 24k
- View details
review-architectureSkillAI & models
Review a PR against the Pascal architectural rules — package boundaries (core/viewer/editor/nodes), the registry-driven composition model (def.geometry / def.renderer / def.system), legacy-dispatch regressions, the slots + world-scale-UV convention for new nodes/geometry, hook hygiene (useEditor/use
Ready to connect★ 24k
- View details
devSkillDev tools
Guides your agent through building, installing, testing, and running the Happy monorepo's apps locally.
Ready to connect★ 24k
- View details
maintainSkillDev tools
Lets your agent triage GitHub issues for the slopus/happy project, drafting comments and finding duplicates with your approval.
Ready to connect★ 24k
- View details
metrics-graphanaSkillMonitoring & ops
Query and manage Grafana dashboards and Prometheus metrics for Happy infrastructure. Covers grafanactl CLI usage, direct Prometheus queries through Grafana proxy, and dashboard-as-code workflows. Use when user asks about metrics, dashboards, monitoring, Grafana, Prometheus, or wants to add/modify pa
Ready to connect★ 24k
- View details
office-hoursSkillMedia
Lets your agent pressure-test your startup idea with six tough questions or brainstorm side project ideas.
Ready to connect★ 24k
- View details
open-code-reviewSkillDev tools
Lets your agent review Git changes, commits, or pull requests with AI and get line-level comments on bugs and quality issues.
Ready to connect★ 23k
- View details
open-code-review-delegateSkillFiles & storage
Lets your agent run a structured code review by getting file lists, rules, and diffs then reviewing the code itself.
Ready to connect★ 23k
- View details
nc-hermes-e2eSkillDev tools
Verifies Hermes skill discovery and fresh-session execution
Ready to connect★ 22k
- View details
nemoclaw-contributor-onboardSkillDev tools
Lets your agent set up a NemoClaw code checkout and verify it is ready for contributing a first pull request.
Ready to connect★ 22k
- View details
nemoclaw-contributor-plan-issueSkillDev tools
Lets your agent plan and break a NemoClaw GitHub issue into small, independently valuable work slices.
Ready to connect★ 22k
- View details
nemoclaw-contributor-update-dependenciesSkillSecurity
Lets your agent audit and carry out dependency upgrades safely, tracing upstream changes into your project.
Ready to connect★ 22k
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.