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
54,510 results · page 526 of 1,817
- View details
05-negotiation-persuasionSkillDev tools
Coaches your agent to teach you negotiation and persuasion skills through role-play practice and structured preparation.
Ready to connect★ 554
- View details
05-social-intelligenceSkillDev tools
Lets your agent coach you through social situations like workplace dynamics, gift-giving, and dining etiquette using role-play practice.
Ready to connect★ 554
- View details
06-creativity-innovationSkillDev tools
Lets your agent coach you through creative thinking techniques like SCAMPER, Design Thinking, and brainstorming to generate new ideas.
Ready to connect★ 554
- View details
06-critical-thinkingSkillDev tools
Turns your agent into a critical thinking coach that helps you analyze arguments, spot logical fallacies, and question evidence.
Ready to connect★ 554
- View details
06-financial-literacySkillCommerce & finance
Lets your agent teach you personal finance topics like budgeting, saving, investing basics, debt, insurance, and taxes.
Ready to connect★ 554
- View details
06-health-wellnessSkillDev tools
Lets your agent coach you on sleep, nutrition, exercise, and stress habits using evidence-based wellness guidance.
Ready to connect★ 554
- View details
anti-defensive-writingSkillDev tools
Lets your agent rewrite drafts to remove unnecessary caveats, hedges, and apologies while keeping needed limits.
Ready to connect★ 543
- View details
qiaomu-designSkillMedia
Lets your agent review, improve, and build UI designs, including visual previews, design systems, and design QA.
Ready to connect★ 553
- View details
ash-frameworkSkillAI & models
Lets your agent work with Elixir's Ash Framework to define resources, actions, policies, aggregates, and calculations.
Ready to connect★ 553
- View details
assignsSkillAI & models
Lets your agent audit LiveView assigns in an Elixir Phoenix project via the /lv:assigns command.
Ready to connect★ 553
- View details
assigns-auditSkillDocs & knowledge
Lets your agent inspect Phoenix LiveView assigns to find memory bloat and suggest fixes like temporary_assigns.
Ready to connect★ 553
- View details
boundariesSkillAI & models
Lets your agent analyze how Phoenix contexts depend on each other and flag cross-context module calls.
Ready to connect★ 553
- View details
catchupSkillProductivity
Summarizes the PRs, commits, tickets, and meetings you missed while away into one brief.
Ready to connect★ 553
- View details
cc-changelogSkillAI & models
Lets your agent track changelog updates and analyze how new versions affect your plugin.
Ready to connect★ 553
- View details
codex-abSkillSecurity
Lets your agent run an A/B code review comparing holistic review versus three focused passes on a branch diff.
Ready to connect★ 553
- View details
codex-loopSkillAI & models
Lets your agent fix Elixir/Phoenix code and verify it with Codex CLI review until it passes before opening a PR.
Ready to connect★ 553
- View details
compoundSkillAI & models
Lets your agent save solved problems as searchable solution documents for later reuse.
Ready to connect★ 553
- View details
compound-docsSkillDocs & knowledge
Lets your agent search curated Elixir, Phoenix, and Ecto solutions stored in YAML docs.
Ready to connect★ 553
- View details
constraint-debugSkillAI & models
Lets your agent debug Ecto database constraint errors in Elixir and Phoenix projects.
Ready to connect★ 553
- View details
deps-updateSkillAI & models
Lets your agent update outdated Elixir dependencies and open reviewable pull requests.
Ready to connect★ 553
- View details
deps-vetSkillSecurity
Lets your agent record approved Elixir package versions in a hex_vet.exs audit file after security review.
Ready to connect★ 553
- View details
docs-checkSkillDocs & knowledge
CONTRIBUTOR TOOL - Validate plugin against latest Claude Code documentation. Catches breaking changes, deprecations, discovers new features. Run before releases or periodically. NOT part of the distributed plugin.
Ready to connect★ 553
- View details
ecto-constraint-debugSkillAI & models
Lets your agent debug Ecto constraint violations by tracing triggers and checking migrations.
Ready to connect★ 553
- View details
ecto-n1-checkSkillAI & models
Lets your agent scan Elixir code for N+1 query problems, like Repo calls inside Enum or for loops.
Ready to connect★ 553
- View details
ecto-patternsSkillAI & models
Gives your agent proven Elixir Ecto patterns for schemas, changesets, queries, migrations, Multi, and associations.
Ready to connect★ 553
- View details
elixir-idiomsSkillProductivity
Lets your agent write Elixir code using common patterns like GenServer, Supervisor, Task, and Registry.
Ready to connect★ 553
- View details
examplesSkillAI & models
Lets your agent fetch sample Elixir code for Phoenix, LiveView, Ecto, OTP, and Oban.
Ready to connect★ 553
- View details
freezeSkillFiles & storage
Lets your agent lock down which files it can edit, including a fully read-only mode for investigation.
Ready to connect★ 553
- View details
fullSkillAI & models
Lets your agent build and verify large Phoenix web app features end to end, from planning through code review.
Ready to connect★ 553
- View details
hexdocs-fetcherSkillDocs & knowledge
Lets your agent fetch documentation for Elixir libraries and convert it to readable markdown.
Ready to connect★ 553
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.
54,078 of the 54,510 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.