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.
Category: AI & models
8,868 results · page 86 of 296
- View details
constraint-debugSkillAI & models
Compatibility alias for the Elixir/Phoenix plugin's Ecto constraint debugger. Invoke explicitly with /ecto:constraint-debug.
Ready to connect★ 551
- View details
deps-updateSkillAI & models
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (/phx:investigate).
Ready to connect★ 551
- View details
ecto-constraint-debugSkillAI & models
Debug Ecto constraint violations - trace triggers, check migrations,
Ready to connect★ 551
- View details
ecto-n1-checkSkillAI & models
Detect N+1 query anti-patterns specifically — Repo calls inside Enum/for
Ready to connect★ 551
- View details
ecto-patternsSkillAI & models
Ecto patterns — schemas, changesets, queries, migrations, Multi, associations,
Ready to connect★ 551
- View details
examplesSkillAI & models
Provide Phoenix, LiveView, Ecto, OTP, or Oban examples. Use when asked for sample code, a walkthrough, a proper implementation, or expected workflow output. Pair with domain skills. NOT for debugging, direct changes, best-practice advice, or audits.
Ready to connect★ 551
- View details
fullSkillAI & models
Deliver a large, cross-domain Phoenix feature or complete end-to-end system through planning, implementation, verification, and review. Use when several coordinated workflows or contexts must ship together. NOT for an existing plan; use /phx:work.
Ready to connect★ 551
- View details
initSkillAI & models
Initialize plugin in a project — install Iron Laws, auto-activation rules, and reference auto-loading into CLAUDE.md. Use when setting up or updating the plugin.
Ready to connect★ 551
- View details
intent-detectionSkillAI & models
Route ambiguous or mixed Phoenix/LiveView/Ecto requests before choosing
Ready to connect★ 551
- View details
investigateSkillAI & models
Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.
Ready to connect★ 551
- View details
ketchupSkillAI & models
Easter-egg alias for /catchup. Same return-from-absence briefing, squeezier name. Use exactly like /catchup — all flags pass through unchanged.
Ready to connect★ 551
- View details
lab:autoresearchSkillAI & models
Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs.
Ready to connect★ 551
- View details
liveview-patternsSkillAI & models
'Build LiveView: async data (assign_async), PubSub (check connected?),
Ready to connect★ 551
- View details
mix-compressionSkillAI & models
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
Ready to connect★ 551
- View details
n1-checkSkillAI & models
Compatibility alias for the Elixir/Phoenix plugin's N+1 query checker. Invoke explicitly with /ecto:n1-check.
Ready to connect★ 551
- View details
narrow-bare-rescueSkillAI & models
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate
Ready to connect★ 551
- View details
obanSkillAI & models
Oban job processing — workers, perform/1 (OSS) and process/1 (Pro), queues,
Ready to connect★ 551
- View details
phx-auditSkillAI & models
Project health audit and health check — architecture, performance, tests,
Ready to connect★ 551
- View details
phx-boundariesSkillAI & models
Analyze Phoenix context boundaries and module coupling via mix xref.
Ready to connect★ 551
- View details
phx-brainstormSkillAI & models
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches,
Ready to connect★ 551
- View details
phx-challengeSkillAI & models
Challenge mode reviews - rigorous questioning before approving changes.
Ready to connect★ 551
- View details
phx-codex-loopSkillAI & models
Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded
Ready to connect★ 551
- View details
phx-compoundSkillAI & models
Capture solved problems as searchable solution docs. Use after fixing
Ready to connect★ 551
- View details
phx-deps-updateSkillAI & models
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix
Ready to connect★ 551
- View details
phx-examplesSkillAI & models
Provide Phoenix, LiveView, Ecto, OTP, or Oban examples. Use when asked
Ready to connect★ 551
- View details
phx-freezeSkillAI & models
Apply an advisory edit scope in this session. Use for read-only or directory-scoped
Ready to connect★ 551
- View details
phx-fullSkillAI & models
Run a portable sequential plan-work-verify-review-compound lifecycle.
Ready to connect★ 551
- View details
phx-helpSkillAI & models
Choose Phoenix review, plan, debug, or test command. Use when user asks
Ready to connect★ 551
- View details
phx-initSkillAI & models
Initialize plugin in a project — install Iron Laws, auto-activation rules,
Ready to connect★ 551
- View details
phx-introSkillAI & models
Walk through the Elixir/Phoenix plugin commands, workflow, and features
Ready to connect★ 551
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.
53,585 of the 54,017 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.