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
9,017 results · page 272 of 301
- View details
git-flowSkillAI & models
Use when committing, branching, opening PRs, or deciding merge/branch strategy.
Ready to connect
- View details
github-cliSkillAI & models
Safety-first GitHub CLI skill wrapping `gh` (v2.86+). Use when performing GitHub operations — PRs, issues, releases, repos, Actions, API calls. Enforces risk classification with mandatory confirmation for destructive/forbidden operations.
Ready to connect
- View details
go-architectureSkillAI & models
Use when laying out a new Go service, choosing an HTTP router or DB layer, or wiring dependencies. Not for concurrency (go-concurrency) or language idioms (go-core-idioms).
Ready to connect
- View details
grill-meSkillAI & models
One move you can run on anything: point grill-me at a target and it makes you defend your thinking from first principles until the true matter is clear. Point it at your working contract and it rewrites the weak lines in place. Point it at a brief and it produces a Requirements Handshake. Point it a
Ready to connect
- View details
harness-improvement-loopSkillAI & models
Agentic harness diagnostic + improvement loop. Probes the framework with real model runs, uses the rax-diagnose CLI to root-cause failures from structured trace data, ships ONE coordinated architectural fix, verifies via before/after diff, commits with empirical evidence. Use at the start of any har
Ready to connect
- View details
implement-serviceSkillAI & models
Create a new Effect-TS service following the mandatory Reactive Agents patterns. Use when adding a service to any package.
Ready to connect
- View details
implement-testSkillAI & models
Write tests for a Reactive Agents package or service using Bun test runner and Effect-TS patterns. Use when creating tests for any module in this project.
Ready to connect
- View details
installing-skill-trackerSkillAI & models
Installs Claude Code hooks for automatic skill usage measurement. Use when setting up skill tracking infrastructure in a new project. NOT when hooks are already installed (run verify.py to check).
Ready to connect
- View details
interaction-autonomySkillAI & models
Control agent autonomy with durable human-in-the-loop approval gates, agent-initiated user-input pauses, and runtime pause/resume/stop controls.
Ready to connect
- View details
interactive-fictionSkillAI & models
Complete specification for creating option-driven interactive fiction: supports transmigration/custom/worldbuilding/random openings, with built-in POV consistency, word count ranges, option mechanics, save system, and character card system.
Ready to connect
- View details
kappa_review_workflowSkillAI & models
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
Ready to connect
- View details
kernel-extensionSkillAI & models
Add new behavior to the composable kernel — new Phase, Guard, MetaTool, or custom kernel variant. Use when extending agent reasoning, adding tool call filtering, or building a custom kernel for a new strategy.
Ready to connect
- View details
laravel-ai-sdkSkillAI & models
Use when integrating AI agents, tool calling, embeddings, structured output, or streaming in Laravel 13 via the `laravel/ai` package.
Ready to connect
- View details
laravel-architectureSkillAI & models
Use when structuring a Laravel project, creating services/repositories/actions, implementing dependency injection, or organizing code layers.
Ready to connect
- View details
laravel-attributesSkillAI & models
Use when migrating Eloquent models, Jobs, Console commands, Controllers, API Resources, Validation, Factories or Seeders to Laravel 13 PHP attributes.
Ready to connect
- View details
laravel-bladeSkillAI & models
Create Blade templates with components, slots, layouts, and directives. Use when building views, reusable components, or templating.
Ready to connect
- View details
laravel-livewireSkillAI & models
Livewire 4 reactive components on Laravel 13 - wire:model, actions, events, Volt, Folio. Use when building reactive UI without JavaScript.
Ready to connect
- View details
laravel-permissionSkillAI & models
Use when implementing RBAC, role-based access control, or user authorization with Spatie Laravel Permission.
Ready to connect
- View details
laravel-queuesSkillAI & models
Use when implementing Laravel 13 background jobs — queue attributes, workers, batching, chaining, middleware, or Queue::route() routing.
Ready to connect
- View details
laravel-testingSkillAI & models
Use when testing controllers, services, or models, or implementing TDD on Laravel 13 with Pest 4 / PHPUnit 12.
Ready to connect
- View details
laravel-upgrade-v13SkillAI & models
Use when upgrading a Laravel 12 application to Laravel 13.0 — composer bump, breaking changes, and Attributes migration.
Ready to connect
- View details
laravel-viteSkillAI & models
Complete Vite bundling for Laravel - assets, HMR, SSR, frameworks, optimization. Use when configuring frontend build pipeline.
Ready to connect
- View details
llm-api-contractSkillAI & models
LLMService API contract — the correct signatures for complete(), stream(), embed(), and response types. Use when calling LLMService from any layer, writing reasoning strategies, or building LLM-dependent features.
Ready to connect
- View details
local-llm-claude-codeSkillAI & models
Set up a FREE local LLM (via Ollama) and connect Claude Code to it so it runs offline with no API costs. Use this whenever the user wants to run Claude Code on a local/self-hosted model, use Ollama/Qwen/Llama/Mistral/DeepSeek with Claude Code, get a "free" or "offline" coding agent, avoid Anthropic
Ready to connect
- View details
map-ecosystemSkillAI & models
Use when cartography index descriptions are truncated, a new plugin/skill was just added, or after SessionStart regenerates the map.
Ready to connect
- View details
materialreacttable-masterySkillAI & models
Material React Table V3 expert skill. Use when building feature-rich data tables w/ MUI styling, server-side ops, CRUD editing, virtualization, or complex filtering/sorting.
Ready to connect
- View details
mission-briefSkillAI & models
Compose a MissionBrief YAML block to prepend to any Agent dispatch during the team-ownership dev-contract pilot (2026-05-23 → 2026-06-15). Use BEFORE spawning kernel-warden or any future warden. Fails if missing end-state, why, authority-bounds, or success-criteria.
Ready to connect
- View details
modularizeSkillAI & models
Use when converting existing code to modular architecture (Laravel, Next.js, React). Triggers: \"modularize\", \"convert to modules\", \"migrate to modular\", \"restructure modules\".
Ready to connect
- View details
multi-agent-patternsSkillAI & models
Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures
Ready to connect
- View details
n8n-cliSkillAI & models
Safety-first n8n management skill — list/inspect workflows, executions, credentials, tags, projects, variables, source-control status; trigger runs (CLI/webhook); activate/deactivate; backup/restore; audit; diff. Two backends auto-detect: REST API (cloud + remote self-hosted, urllib stdlib) & `n8n`
Ready to connect
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.
55,004 of the 55,435 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.