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 270 of 301
- View details
agami-save-correctionSkillAI & models
Saves a user correction so future queries learn from it. Always appends a (question, corrected_sql) pair to the subject area's example library under <artifacts_dir>/<profile>/prompt_examples/<area>/. Additionally, classifies the correction and — when applicable — applies a surgical edit to the seman
Ready to connect
- View details
agent-strivingSkillAI & models
🏹 Keep authorized pursuits alive through interruption.
Ready to connect
- View details
agent-tddSkillAI & models
Test-Driven Development for the Reactive Agents codebase. Effect-TS aware TDD with mandatory timeout flags, Effect.flip error testing, Layer isolation, and dangling-server prevention. Use when implementing any feature or fixing any bug.
Ready to connect
- View details
- View details
agrSkillAI & models
AGR: Artificial General Research — autonomous iterative optimization framework for Claude Code. Generalizes Karpathy's autoresearch to any measurable problem with variance-aware acceptance, correctness verification, and fresh-context-per-iteration (Ralph Loop). Use when setting up autoresearch, crea
Ready to connect
- View details
anti-ai-writing-styleSkillAI & models
Follow these guidelines when writing copy to avoid LLM frequently used styles and structures, and create more human sounding copy.
Ready to connect
- View details
application-packSkillAI & models
Turns one pasted job post into an application folder built only from the student's own career vault: a tailored resume, a cover letter under 250 words, and an HR call sheet with the answers already drafted. Reads career-vault/01 to 06 first and refuses to run while the positioning, portfolio story o
Ready to connect
- View details
architecture-referenceSkillAI & models
Reactive Agents framework architecture — layer stack, dependency graph, build order, and package structure. Use when planning work, understanding package relationships, or determining build dependencies.
Ready to connect
- View details
astro-7SkillAI & models
Use when building Astro 7 sites, choosing an output mode (static/server/hybrid), configuring middleware, or upgrading from Astro 5/6.
Ready to connect
- View details
astro-actionsSkillAI & models
Use when handling form submissions, mutations, or server-side logic with type safety in Astro via defineAction / astro:actions.
Ready to connect
- View details
astro-contentSkillAI & models
Use when managing structured content, blog posts, or typed data collections in Astro via the Content Layer API (content.config.ts).
Ready to connect
- View details
astro-i18nSkillAI & models
Use when implementing i18n in Astro — locale routing strategies, getRelativeLocaleUrl/getAbsoluteLocaleUrl, Astro.currentLocale, or hreflang with sitemap.
Ready to connect
- View details
astro-integrationsSkillAI & models
Use when adding React, Vue, Svelte, Solid, Preact, or another UI framework to an Astro project via @astrojs/* integrations.
Ready to connect
- View details
astro-seoSkillAI & models
Use when optimizing SEO for an Astro site — meta tags, Open Graph, JSON-LD structured data, sitemap/RSS, canonical URLs, hreflang, Core Web Vitals.
Ready to connect
- View details
astro-stylingSkillAI & models
Use when styling Astro components — scoped CSS, CSS Modules, Tailwind CSS, UnoCSS, Sass, the class:list directive, or global styles.
Ready to connect
- View details
breaking-changesSkillAI & models
Use when checking whether a Claude Code update breaks our plugin ecosystem — hooks, agent frontmatter, manifest schema, or skill format.
Ready to connect
- View details
build-packageSkillAI & models
Add a new package to the Reactive Agents monorepo. Covers scaffolding, package.json, tsconfig, layer wiring, and index exports. Use when creating a net-new @reactive-agents/* package.
Ready to connect
- View details
builder-api-referenceSkillAI & models
Configure a ReactiveAgentBuilder with the correct layer composition for any agent use case.
Ready to connect
- View details
building-chat-widgetsSkillAI & models
Build interactive AI chat widgets with buttons, forms, and bidirectional actions. Use when creating agentic UIs with clickable widgets, entity tagging (@mentions), composer tools, or server-handled widget actions. Covers full widget lifecycle. NOT when building simple text-only chat without interact
Ready to connect
- View details
building-chatgpt-appsSkillAI & models
Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Develo
Ready to connect
- View details
changelog-scanSkillAI & models
Use when checking for new Claude Code versions, features, or changes since the last known release.
Ready to connect
- View details
chatkit-actionsSkillAI & models
Implements interactive widget actions and bidirectional communication patterns for ChatKit. This skill should be used when building AI-driven interactive UIs with buttons, forms, entity tagging (@mentions), composer tools, and server-handled widget actions. Covers the full widget lifecycle from crea
Ready to connect
- View details
chatkit-streamingSkillAI & models
Implements real-time streaming UI patterns for ChatKit applications. This skill should be used when adding response lifecycle management, progress indicators, client effects, and thread state synchronization. Covers onResponseStart/End, onEffect, ProgressUpdateEvent, and thread lifecycle events.
Ready to connect
- View details
checkpointSkillAI & models
Review and approval for work made by AI agents. Fair Source, self-hostable, and MCP-native.
Ready to connect
- View details
codebase-health-sweepSkillAI & models
Use when the codebase may have accumulated bugs, failing tests, type errors, dead code, inefficiencies, or drift from known quality standards — before a release, after a large feature merge, or on a recurring maintenance cadence. Also triggers when build is red, `bun test` has unexpected failures, o
Ready to connect
- View details
commit-detectionSkillAI & models
Detects optimal commit type from git changes. Use when analyzing commits, determining commit type, or before committing.
Ready to connect
- View details
commit-optimizationSkillAI & models
Use when configuring settings.json to reduce fuse-commit-pro's context token usage.
Ready to connect
- View details
cortex-lab-testSkillAI & models
Smoke-test skill for the Cortex desk. Use to verify Living skills paths (e.g. apps/cortex/.agents/skills) load via withSkills. No side effects.
Ready to connect
- View details
cost-budget-enforcementSkillAI & models
Set per-request, per-session, daily, and monthly spend limits, configure rate limiting and circuit breakers, and isolate costs per user or tenant.
Ready to connect
- View details
css-protipsSkillAI & models
Use when writing, reviewing, refactoring, or modernizing CSS/Tailwind. Apply a policy-first approach: semantic tokens, explicit cascade order, static CSS, intrinsic component layouts, accessible state, measured performance, and progressive enhancement backed by current sources.
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.