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
52,958 results · page 28 of 1,766
- View details
init-deepSkillDocs & knowledge
Lets your agent create a set of AGENTS.md files that document your codebase's structure, commands, and conventions.
Ready to connect★ 69k
- View details
lcx-contribute-bug-fixSkillAI & models
Lets your agent prepare and submit a tested bug fix for LazyCodex or the Codex CLI, as a GitHub issue or fork PR.
Ready to connect★ 69k
- View details
lcx-doctorSkillAI & models
Checks whether your Codex or LazyCodex installation is healthy and up to date, returning a PASS/WARN/FAIL report.
Ready to connect★ 69k
- View details
lcx-report-bugSkillFiles & storage
Lets your agent file a detailed, evidence-backed bug report as a GitHub issue or pull request in the right repo.
Ready to connect★ 69k
- View details
lspSkillAI & models
Lets your agent check code errors, find symbol definitions and references, and safely rename code in a workspace.
Ready to connect★ 69k
- View details
lsp-setupSkillAI & models
Lets your agent set up a language server so code features like diagnostics, go-to-definition, and rename work.
Ready to connect★ 69k
- View details
mass-ulwSkillProductivity
Lets your agent run tasks in dependency order, so jobs that must wait on earlier steps execute in the right sequence.
Ready to connect★ 69k
- View details
omomomoSkillAI & models
Lets your agent show a fun hidden message explaining what Oh My OpenCode is when you ask about it.
Ready to connect★ 69k
- View details
onboardingSkillAI & models
Walks a first-time omo user through setup, a feature tour, migration help, and memory recording.
Ready to connect★ 69k
- View details
opencode-qaSkillDatabases & data
Lets your agent test and debug opencode: check CLI commands, verify plugin events, smoke-test the TUI, and search session records.
Ready to connect★ 69k
- View details
pi-goalSkillAI & models
Lets your agent track a long-running goal across sessions, creating, inspecting, and marking it complete.
Ready to connect★ 69k
- View details
pre-publish-reviewSkillAI & models
Runs a multi-agent review of all code changes since your last npm release before you publish.
Ready to connect★ 69k
- View details
programmingSkillFiles & storage
Guides your agent to write and edit Python, Rust, TypeScript, or Go code following strict typing, test-first, and modern toolchain practices.
Ready to connect★ 69k
- View details
publishSkillCloud & infra
Lets your agent publish package releases by running a GitHub Actions workflow, verifying npm versions, and posting release notes.
Ready to connect★ 69k
- View details
refactorSkillAI & models
Lets your agent plan and carry out code refactoring step by step, with tests run after each change.
Ready to connect★ 69k
- View details
remove-ai-slopsSkillFiles & storage
Lets your agent clean up AI-generated code smells in changed files while locking behavior with regression tests first.
Ready to connect★ 69k
- View details
remove-deadcodeSkillAI & models
Lets your agent find and delete unused code from a project, verifying each removal with language-server references before committing.
Ready to connect★ 69k
- View details
review-workSkillSecurity
Runs a structured review of finished coding work, checking goals, code quality, security, and QA before a PR handoff.
Ready to connect★ 69k
- View details
rulesSkillFiles & storage
Lets your agent answer questions about Codex Rules, like which rule files are supported and how rules get injected.
Ready to connect★ 69k
- View details
security-researchSkillSecurity
Lets your agent run a parallel security audit of a codebase, hunting vulnerabilities and proving which ones are actually exploitable.
Ready to connect★ 69k
- View details
senpi-qaSkillProductivity
Lets your agent run live QA tests on the Senpi adapter and task engine, saving evidence files to a fixed folder.
Ready to connect★ 69k
- View details
teammodeSkillAI & models
Lets your agent run a team of cooperating Codex workers in parallel with shared, saved state on disk.
Ready to connect★ 69k
- View details
tech-debt-auditSkillFiles & storage
Lets your agent audit a codebase for technical debt and write a cited TECH_DEBT_AUDIT.md report with prioritized fixes.
Ready to connect★ 69k
- View details
ultimate-browsingSkillWeb & browsing
Lets your agent read web pages a normal fetch can't: render JavaScript, click, fill forms, screenshot, and keep logins.
Ready to connect★ 69k
- View details
ultraworkSkillFiles & storage
Puts your coding agent into a strict mode that verifies work end-to-end with real tests and captured evidence before calling a task done.
Ready to connect★ 69k
- View details
ulw-executeSkillAI & models
Lets your agent carry out a written work plan by delegating coding tasks to parallel subagents and tracking progress.
Ready to connect★ 69k
- View details
ulw-loopSkillAI & models
Lets your agent run long tasks as checkpointed goal loops with evidence that each step actually worked.
Ready to connect★ 69k
- View details
ulw-planSkillAI & models
Lets your agent explore a codebase and write a detailed work plan before any coding starts.
Ready to connect★ 69k
- View details
ulw-researchSkillAI & models
Lets your agent run deep research projects with a team of sub-agents and get a cited report in PDF or DOCX.
Ready to connect★ 69k
- View details
visual-qaSkillAI & models
Lets your agent visually check that a built or changed UI, terminal app, or document actually looks right.
Ready to connect★ 69k
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.
52,524 of the 52,958 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.