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
55,055 results · page 736 of 1,836
- View details
idea-teamSkillDev tools
Lets your agent run a group-chat debate between AI roles like researcher and devil's advocate to stress-test an idea.
Ready to connect★ 280
- View details
idea-to-productSkillDev tools
Coaches your agent to turn a one-sentence product idea into a PRD and a clickable HTML prototype.
Ready to connect★ 280
- View details
illustrated-gallerySkillDev tools
Lets your agent build an illustrated portfolio or showcase website with an art gallery and ASCII dissolve transitions.
Ready to connect★ 280
- View details
incident-slo-runbookSkillMonitoring & ops
Lets your agent create and review SLOs, alerts, incident steps, runbooks, and outage communications.
Ready to connect★ 280
- View details
ip-checkSkillDatabases & data
Lets your agent check whether an IP or proxy is trustworthy, where it is, and whether AI services can be accessed from it.
Ready to connect★ 280
- View details
meditateSkillDocs & knowledge
Lets your agent review its own notes, prune outdated content, and consolidate principles across files.
Ready to connect★ 280
- View details
multi-ai-researchSkillAI & models
Lets your agent run the same research question across several AI models in parallel and compare their answers.
Ready to connect★ 280
- View details
multi-model-orchestratorSkillDocs & knowledge
Lets your agent coordinate complex tasks across multiple AI agents using a shared handoff document.
Ready to connect★ 280
- View details
noodleSkillProductivity
Helps your agent run Noodle CLI commands, explain flags, and edit .noodle.toml config files.
Ready to connect★ 280
- View details
npm-supply-chain-checkSkillMonitoring & ops
Lets your agent scan a code repository for malicious npm packages and suspicious install scripts.
Ready to connect★ 280
- View details
observability-sreSkillMonitoring & ops
Lets your agent set up monitoring, logging, tracing, SLOs, and incident response using Prometheus, Grafana, and OpenTelemetry.
Ready to connect★ 280
- View details
oopsSkillDev tools
Lets your agent fix broken builds, failing tests, stale state, and environment drift in your project.
Ready to connect★ 280
- View details
optimize-networkSkillDev tools
Lets your agent diagnose and improve your local network speed, Wi-Fi, DNS, and latency.
Ready to connect★ 280
- View details
performance-capacitySkillDev tools
Lets your agent plan and diagnose performance work like latency budgets, load tests, caching, and bottleneck analysis.
Ready to connect★ 280
- View details
playwright-automationSkillWeb & browsing
Lets your agent control a web browser to test apps, automate tasks, take screenshots, and check page behavior.
Ready to connect★ 280
- View details
prd-masterSkillDev tools
Lets your agent draft product requirement docs, user stories, acceptance criteria, and prioritize features.
Ready to connect★ 280
- View details
product-ux-expertSkillDev tools
Lets your agent review UI designs, evaluate user experience, and check accessibility against WCAG 2.2.
Ready to connect★ 280
- View details
project-health-auditorSkillDev tools
Lets your agent analyze a codebase's health, finding code quality issues, technical debt, and dependency problems.
Ready to connect★ 280
- View details
react-hooks-best-practicesSkillMedia
Gives your agent React best practices for hooks, effects, refs, and component design when writing components.
Ready to connect★ 280
- View details
recapSkillAI & models
Lets your agent review your recent Claude Code sessions and summarize what you worked on, with patterns and suggestions.
Ready to connect★ 280
- View details
release-engineeringSkillDatabases & data
Lets your agent plan and verify software releases with versioning, changelogs, rollbacks, and deployment checks.
Ready to connect★ 280
- View details
repo-agent-context-auditSkillAI & models
Lets your agent audit a repo's instruction files and recommend improvements to its agent-readable docs.
Ready to connect★ 280
- View details
repo-scaffoldSkillDocs & knowledge
Lets your agent create a standard, production-ready repository layout with docs, tests, CI, and configs.
Ready to connect★ 280
- View details
review-agent-harnessSkillDocs & knowledge
Lets your agent review whether a repo's coding-agent setup reliably carries tasks from intent to delivery.
Ready to connect★ 280
- View details
review-gateSkillFiles & storage
Makes your agent stop and ask for your approval before committing or pushing any code changes it made.
Ready to connect★ 280
- View details
ruminateSkillAI & models
Lets your agent review your past coding sessions to extract patterns, corrections, and lessons you didn't save.
Ready to connect★ 280
- View details
rust-projectSkillDev tools
Guides your agent to set up well-structured Rust projects with idiomatic patterns for workspaces, errors, and async.
Ready to connect★ 280
- View details
rustdesk-doctorSkillDev tools
Diagnoses why RustDesk remote desktop connections fail, like missing IDs or registration errors.
Ready to connect★ 280
- View details
server-securitySkillFiles & storage
Lets your agent scan a server for security issues like open ports, weak permissions, and brute-force attacks, then apply fixes.
Ready to connect★ 280
- View details
skill-ecosystem-doctorSkillDev tools
Lets your agent audit and repair duplicate, drifting, or retired skills across projects.
Ready to connect★ 280
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.
54,624 of the 55,055 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.