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
54,680 results · page 528 of 1,823
- View details
phx-mix-compressionSkillAI & models
Lets your agent cut noise from mix command output to save tokens when working on Elixir projects.
Ready to connect★ 553
- View details
phx-perfSkillAI & models
Lets your agent find performance problems in Elixir Phoenix apps, like slow database queries and memory bloat.
Ready to connect★ 553
- View details
phx-permissionsSkillAI & models
Lets your agent recommend safe Bash permissions for Elixir mix commands in settings.json.
Ready to connect★ 553
- View details
phx-planSkillCommerce & finance
Lets your agent plan features that span billing, logins, and permissions in Phoenix web apps.
Ready to connect★ 553
- View details
phx-pr-reviewSkillAI & models
Lets your agent find and address unresolved review feedback on a GitHub pull request.
Ready to connect★ 553
- View details
phx-quickSkillAI & models
Lets your agent make small Phoenix code edits like adding validations without a planning step.
Ready to connect★ 553
- View details
phx-recallSkillAI & models
Lets your agent recall details from past coding sessions, like how a bug was fixed.
Ready to connect★ 553
- View details
phx-researchSkillAI & models
Lets your agent research Elixir, Phoenix, and Ecto questions and evaluate Hex libraries.
Ready to connect★ 553
- View details
phx-reviewSkillAI & models
Lets your agent review changed Elixir and Phoenix code against requirements and cite what it finds.
Ready to connect★ 553
- View details
phx-techdebtSkillAI & models
Analyzes your Elixir/Phoenix code for duplicates and refactoring opportunities to spot technical debt.
Ready to connect★ 553
- View details
phx-traceSkillAI & models
Lets your agent trace Elixir call trees from entry points using mix xref to help debug code.
Ready to connect★ 553
- View details
phx-triageSkillAI & models
Lets your agent go through review findings one by one, approving, skipping, or prioritizing each.
Ready to connect★ 553
- View details
phx-verifySkillAI & models
Lets your agent compile, format, and test Elixir/Phoenix code changes in one loop.
Ready to connect★ 553
- View details
phx-watch-prSkillAI & models
Lets your agent watch an Elixir/Phoenix pull request for new review comments from bots and humans.
Ready to connect★ 553
- View details
phx-workSkillProductivity
Lets your agent carry out planned Elixir and Phoenix coding tasks step by step with progress tracking.
Ready to connect★ 553
- View details
plugin-dev-workflowSkillFiles & storage
Guides your agent through editing skills, agents, hooks, and eval files in this repo, checking eval, lint, and tests.
Ready to connect★ 553
- View details
quickSkillFiles & storage
Lets your agent make small Phoenix code edits like adding validations, updating routes, or creating migrations without planning.
Ready to connect★ 553
- View details
session-deep-diveSkillAI & models
Lets your agent deeply analyze recorded sessions, find patterns, and compare them against earlier findings.
Ready to connect★ 553
- View details
session-scanSkillMonitoring & ops
Lets your agent analyze coding session logs and score them for friction and improvement opportunities.
Ready to connect★ 553
- View details
session-trendsSkillDocs & knowledge
Lets your agent compute trends and deltas across session metrics and compare them with past findings.
Ready to connect★ 553
- View details
skill-monitorSkillMonitoring & ops
Lets your agent analyze how well its skills perform across sessions and get improvement recommendations.
Ready to connect★ 553
- View details
techdebtSkillAI & models
Lets your agent analyze Elixir/Phoenix code for technical debt like duplicates, refactoring opportunities, and credo issues.
Ready to connect★ 553
- View details
tidewave-integrationSkillAI & models
Lets your agent debug your Phoenix app, inspect its live state, and run smoke tests.
Ready to connect★ 553
- View details
watch-prSkillCloud & infra
Lets your agent monitor a pull request until its CI checks pass and review comments are resolved.
Ready to connect★ 553
- View details
components-architectureSkillDev tools
Guides your agent on where to place and organize UI components when coding in the Operately app.
Ready to connect★ 554
- View details
ecto-migrationsSkillDatabases & data
Lets your agent add, review, and generate database migrations for the Operately codebase following its rules.
Ready to connect★ 554
- View details
help-docsSkillDocs & knowledge
Lets your agent find code changes since a release that still need help documentation.
Ready to connect★ 554
- View details
mcp-toolsSkillAI & models
Guides your agent in creating and reviewing Operately MCP tool wrappers in the codebase.
Ready to connect★ 554
- View details
tanstack-querySkillAI & models
Guides your coding agent to write and migrate the app's frontend data fetching to TanStack Query conventions.
Ready to connect★ 554
- View details
ui-copySkillCommunication
Helps your agent write and edit user-facing product text like button labels, error messages, and onboarding copy.
Ready to connect★ 554
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.
54,249 of the 54,680 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.