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 87 of 296
- View details
phx-investigateSkillAI & models
Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures,
Ready to connect★ 551
- View details
phx-learn-from-fixSkillAI & models
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections
Ready to connect★ 551
- View details
phx-mix-compressionSkillAI & models
Reduce mix output noise (5-15% token savings) by installing rtk filters
Ready to connect★ 551
- View details
phx-perfSkillAI & models
Analyze Elixir/Phoenix performance — N+1 queries, assign bloat, ecto
Ready to connect★ 551
- View details
phx-permissionsSkillAI & models
Recommend safe Bash permissions for Elixir mix commands in settings.json.
Ready to connect★ 551
- View details
phx-pr-reviewSkillAI & models
'Address feedback left on a GitHub pull request: fetch unresolved review
Ready to connect★ 551
- View details
phx-quickSkillAI & models
Implement small Phoenix changes without planning — add validations, update
Ready to connect★ 551
- View details
phx-recallSkillAI & models
Recall prior work from past sessions — how a bug was fixed, what was
Ready to connect★ 551
- View details
phx-researchSkillAI & models
Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries (--library).
Ready to connect★ 551
- View details
phx-reviewSkillAI & models
Review changed Elixir/Phoenix code read-only. Check requirements, cite
Ready to connect★ 551
- View details
phx-techdebtSkillAI & models
Analyze Elixir/Phoenix technical debt — duplicates, refactoring opportunities,
Ready to connect★ 551
- View details
phx-traceSkillAI & models
Trace Elixir call trees from entry points via mix xref. Use when debugging
Ready to connect★ 551
- View details
phx-triageSkillAI & models
Triage review findings interactively — approve, skip, or prioritize each
Ready to connect★ 551
- View details
phx-verifySkillAI & models
Verify Elixir/Phoenix changes — compile, format, and test in one loop.
Ready to connect★ 551
- View details
phx-watch-prSkillAI & models
Watch an Elixir/Phoenix PR for new review comments (bot + human) and
Ready to connect★ 551
- View details
recallSkillAI & models
Recall prior work from past sessions — how a bug was fixed, what was decided, where a pattern lives. Use when asked 'have we done this before' or 'how did I fix X' in Elixir/Phoenix work. ccrider MCP when available, else git + solution docs.
Ready to connect★ 551
- View details
session-deep-diveSkillAI & models
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
Ready to connect★ 551
- View details
techdebtSkillAI & models
Analyze Elixir/Phoenix technical debt — duplicates, refactoring opportunities, credo issues. Use when asked about code quality, cleanup, or what to improve.
Ready to connect★ 551
- View details
tidewave-integrationSkillAI & models
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection,
Ready to connect★ 551
- View details
traceSkillAI & models
Trace Elixir call trees from entry points via mix xref. Use when debugging data flow, planning signature changes, or understanding how a bug reaches code.
Ready to connect★ 551
- View details
mcp-toolsSkillAI & models
Defines how to add Operately MCP tools (API-first wrappers). Use when creating, changing, or reviewing MCP tools under app/lib/operately_web/mcp/tools/, when the user mentions MCP tools, tool catalog, @expected_tool_names, or when exposing a new Operately capability to ChatGPT/Claude MCP clients.
Ready to connect★ 551
- View details
tanstack-querySkillAI & models
Operately frontend data fetching with TanStack Query. Use when adding or changing page loaders, model hooks, Api.* calls, mutations, useLoadedData, Pages.useRefresh, or any web UI backend request. New code must use TanStack. When fixing or extending an existing surface, migrate that surface's API ca
Ready to connect★ 551
- View details
Maestro Ralph V2SkillAI & models
Adaptive lifecycle orchestrator — compose, dispatch ralph-executor agent, evaluate decision, loop
★ 550
- View details
Maestro Swarm WorkflowSkillAI & models
Parallel workflow accelerator — route intent to fixed Workflow scripts for multi-agent concurrent execution
★ 550
- View details
- View details
- View details
- View details
- View details
- View details
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.