AI Agent
Skills Directory

apple-hig

84Kagent-workflows

Apple Human Interface Guidelines as 14 agent skills covering platforms, foundations, components, patterns, inputs, and technologies for iOS, macOS, visionOS, watchOS, and tvOS.

nexu-io

image-generation

78Kbackend-api

Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.

bytedance

vitest

108Ktesting-qa

Vitest API and config reference (Jest-compatible) — mocking with vi.*, spies, fake timers, coverage configuration, fixtures, snapshots, and test filtering. Use for Vitest API and configuration questions anywhere in the monorepo; for Studio-specific test strategy and component-test setup, start with studio-testing and studio-mock-api-tests.

supabase

fsharp-testing

238Ktesting-qa

F# testing patterns with xUnit, FsUnit, Unquote, FsCheck property-based testing, integration tests, and test organization best practices.

affaan-m

fix

247Kfrontend

Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.

facebook

🆕 New Arrivals

View all →

gog

386Kresearch-knowledge

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

nano-pdf

386Kwriting-content

Edit PDFs with natural-language instructions using the nano-pdf CLI.

openai-whisper

386Kbackend-api

Local speech-to-text with the Whisper CLI (no API key).

ordercli

386Kbrowser-web

Foodora-only CLI for checking past orders and active order status (Deliveroo WIP).

1password

386Kbrowser-web

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

mcporter

386Kmcp-integrations

List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.

peekaboo

386Kdesign-ui

Capture and automate macOS UI with the Peekaboo CLI.

apple-reminders

386Kproductivity

List, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.

coding-agent

386Kagent-workflows

Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.

What is an AI Agent Skill?

An AI Agent Skill (also known as Claude skills or AI skills) is a reusable capability you can add to an agent to automate tasks like writing, social posting, research, or development workflows.

Think of them as "plugins" for your AI. Browse our Claude skills marketplace to find Claude code templates and open-source GitHub repositories. Most come with a simple one-line installation command.

According to Anthropic's documentation on extending Claude with skills, skills package instructions, scripts, and resources so agents can perform specialized tasks more reliably.

Source: Anthropic — Extend Claude with skills

Skill: Research

v1.2.0 • Installed

Skills vs nearby concepts

AI Agent Skill

What it is

Reusable capability package (often a repo with SKILL.md) that teaches an agent a workflow.

When to use it

You want installable, shareable agent behaviors for Claude Code, Codex, or similar agents.

MCP server

What it is

A protocol endpoint that exposes tools/data to an agent over Model Context Protocol.

When to use it

You need live tool access (APIs, browsers, databases) rather than a static skill package.

Slash command

What it is

Built-in or local shortcut inside an agent UI/CLI.

When to use it

Quick in-product actions; less portable than a full skill.

🔥 Trending This Week

View all →

git-guardrails-claude-code

215Kwriting-content

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

mattpocock

orca-per-workspace-env

44Kagent-workflows

Set up, review, debug, or validate Orca per-workspace environment recipes — on-demand, disposable runtimes (cloud sandboxes, VMs, or local) created fresh for each workspace. Covers first-time setup (provider prerequisites, the reusable base snapshot, the coding-agent auth snapshot, credentials, and state), not just the per-workspace lifecycle scripts. Use to stand up per-workspace environments, fix an `environmentRecipes` entry in `orca.yaml`, scaffold provider lifecycle scripts, or resolve an `orca vm recipe doctor` failure.

stablyai

ponytail

102Kcode-generation

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

dietrichgebert

documentation-and-adrs

87Kdatabase

Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

addyosmani

writing-skills

271Kresearch-knowledge

Use when creating new skills, editing existing skills, or verifying skills work before deployment

obra

dogfood

230Ktesting-qa

Exploratory QA of web apps: find bugs, evidence, reports.

nousresearch

brandkit

76Kdesign-ui

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

leonxlnx

herdr

28Kagent-workflows

Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1.

herdrdev

herdr

28Kagent-workflows

Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, terminals, commands, or communication with another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1.

ogulcancelik

Browse by Category

View all

445

Agent Workflows

Reusable agent workflows and orchestration patterns

150

Prompting & Reasoning

Prompt engineering, personas, and reasoning patterns

476

Research & Knowledge

Research, retrieval, summarization, and knowledge work

107

Browser & Web

Browser control, web automation, scraping, and crawling

165

Writing & Content

Writing, editing, publishing, and translation workflows

324

Design & UI

Interface design, visual systems, and product UI

Marketing & SEO

SEO, content marketing, campaigns, and growth workflows

167

Productivity

Task automation, office workflows, and personal productivity

103

Code Generation

Code generation, refactoring, and scaffolding

282

Frontend

Frontend frameworks, UI components, CSS, and web apps

397

Backend & API

Backend services, APIs, webhooks, and server-side tooling

Database

SQL, schema design, migrations, and database operations