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 273 of 301
- View details
natural-languageSkillAI & models
Shapes how every reply to the user gets written - plain everyday words instead of corporate or AI-sounding phrasing, real sentences instead of bullet-heavy formatting, no forced dash punctuation, and at most a rare bit of dry humor when it genuinely fits. Use this for every conversational response w
Ready to connect
- View details
next-cache-componentsSkillAI & models
Next.js 16 Cache Components - PPR, use cache directive, cacheLife, cacheTag, updateTag
Ready to connect
- View details
next-upgradeSkillAI & models
Upgrade Next.js to the latest version following official migration guides and codemods
Ready to connect
- View details
nextjs-16SkillAI & models
Use when building Next.js 16 apps — Turbopack, App Router, Cache Components, proxy.ts, v15 migration. Not for stack scaffolding (nextjs-stack) or React SPA (react-expert).
Ready to connect
- View details
nextjs-devtoolsSkillAI & models
Next.js development tooling via MCP. Inspect routes, components, build info, and debug Next.js apps. Use when working on Next.js applications, debugging routing, or inspecting app structure. NOT for general React or non-Next.js projects.
Ready to connect
- View details
nextjs-i18nSkillAI & models
Use when implementing i18n in Next.js 16 — next-intl or DIY dictionaries, locale routing, language switch, or formatters.
Ready to connect
- View details
nextjs-senior-devSkillAI & models
Senior Next.js 15+/16 Engineer skill for App Router. Use when scaffolding production apps, enforcing RSC patterns, auditing codebases, or optimizing performance.
Ready to connect
- View details
nextjs-server-componentsSkillAI & models
Use when deciding Server vs Client Component boundaries in Next.js 16, fetching data directly in components, or streaming with Suspense.
Ready to connect
- View details
nextjs-stackSkillAI & models
Use as the master reference for a full Next.js 16+ stack — Prisma 7, Better Auth, shadcn/ui, TanStack Form, Zustand. Not for core framework API details (use nextjs-16).
Ready to connect
- View details
nextjs-tanstack-formSkillAI & models
Use when building forms in Next.js 16 with TanStack Form v1 — Server Actions, Zod validation, multi-step wizards, field arrays.
Ready to connect
- View details
nextjs-tanstack-querySkillAI & models
Use when implementing client-side data fetching, server prefetching with hydration, or optimistic mutations in Next.js 16 with TanStack Query.
Ready to connect
- View details
nextjs-zustandSkillAI & models
Use when implementing global state, stores, persist, or hydration in Next.js 16 App Router Client Components with Zustand v5.
Ready to connect
- View details
nix-oss-cacheSkillAI & models
Use this when setting up a GitHub repo to push its Nix builds to Juspay's shared OSS Attic cache (cache.nixos.asia/oss) — adds the substituter to flake.nix, a nix-cache.yml GitHub Actions workflow, and prompts for the ATTIC_TOKEN secret.
Ready to connect
- View details
nx-monorepoSkillAI & models
Nx monorepo management skill for AI-native development. This skill should be used when working with Nx workspaces, project graphs, affected detection, code generation, and caching. Use when: analyzing dependencies, running affected commands, generating code, configuring Nx Cloud, or optimizing build
Ready to connect
- View details
nz-parliament-votesSkillAI & models
Query official New Zealand Parliament weekly Journals for recorded divisions, preserving printed party counts and ambiguous singleton labels without identity inference.
Ready to connect
- View details
oncall_handoff_lookupSkillAI & models
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
Ready to connect
- View details
opcodeSkillAI & models
Use when working with Opcode command catalogs such as op.conf or agent.op.conf; edit and run user-controlled op commands, and maintain agent-owned reusable commands only when the local agent executable is an Opcode alias.
Ready to connect
- View details
php-ecosystem-referenceSkillAI & models
Use when picking a non-Laravel PHP tool — Symfony components, API Platform, or Slim — and routing to implementation. Do NOT use for Laravel (laravel-expert).
Ready to connect
- View details
php-quality-toolingSkillAI & models
Use when setting up PHPStan, Rector, or PHP-CS-Fixer on a non-Laravel PHP project, incl. CI wiring. Do NOT use for Laravel (Pint/Larastan), tests, or syntax.
Ready to connect
- View details
php-standardsSkillAI & models
Use when setting up PHP-package autoloading, coding style, or PSR interfaces — PSR-4, PER Coding Style 3.0, composer.json. Do NOT use for syntax or Laravel.
Ready to connect
- View details
php-testingSkillAI & models
Use when writing/configuring tests on a non-Laravel PHP project — PHPUnit vs Pest. Do NOT use for Laravel test helpers or quality tooling (php-quality-tooling).
Ready to connect
- View details
plan-handoffSkillAI & models
Execute an approved plan from .agents/plans/Plan.md in a fresh session. Use when handed an approved plan to implement.
Ready to connect
- View details
plan-to-tddSkillAI & models
Transform feature plans into test-driven implementation using Outside-In methodology. This skill should be used when converting documented plans from docs/plan/ into testable code w/ proper test structure (Unit, Integration, E2E).
Ready to connect
- View details
post-commitSkillAI & models
Use when a code commit just landed (not wip/amend/undo) and CHANGELOG or plugin-version post-commit actions are needed.
Ready to connect
- View details
prepare-releaseSkillAI & models
Use when cutting, tagging, or publishing a new Reactive Agents version, or when a release/publish run fails and needs resuming. Covers the tag-driven lockstep flow (scripts/release.ts + .github/workflows/publish.yml).
Ready to connect
- View details
prompt-creationSkillAI & models
Use when writing a new system prompt from scratch, structuring it with Anthropic's 9-element format, or choosing emphasis levels and few-shot examples.
Ready to connect
- View details
- View details
provider-patternsSkillAI & models
Configure per-provider behavior, understand streaming quirks, and use the 5-hook adapter system for optimal performance across LLM providers.
Ready to connect
- View details
provider-streamingSkillAI & models
LLM provider streaming patterns and per-provider quirks. Use when adding a new provider, implementing adapter hooks, or debugging streaming tool call behavior in packages/llm-provider.
Ready to connect
- View details
quality-assuranceSkillAI & models
Enable output verification (hallucination detection, semantic entropy, self-consistency), add post-run verification steps, and run LLM-scored evals across 5 quality dimensions.
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.