Agent skills
Skills for AI coding agents, each with what it costs to load, how much of it is scripts and what it touches on your machine.
How to read a skill
What it costs to keep
Idle in context, in use when it runs, and up to with its linked files.
Scripts or instructions
Script-led, mixed or model-led: how much the model has to work out itself.
What it can reach
Shell, network, file writes, git and credentials, declared or detected.
Quality, security, repo health
Out of 100, each with what it is made of. Turn a card over to see them.
frontend-design
198,136Design And Visual Art · Developer Tools · Frontend And UI Engineering
Design guidance that pushes Claude toward distinctive, intentional UI instead of templated defaults, from palette and type to layout and copy.
mcp-builder
198,136Developer Tools
Anthropic's skill for building MCP servers: research the API, implement tools in TypeScript or Python, test with the Inspector, then measure the server with an LLM evaluation harness.
skill-creator
198,136Agent Workflows · Developer Tools
Anthropic's skill for making skills: Claude drafts a SKILL.md, runs test prompts with and without it, shows the results in a review viewer and tunes the description that triggers it.
webapp-testing
198,136Code Review And Quality · Developer Tools
Anthropic's skill for testing local web apps: Claude writes native Python Playwright scripts, starts the dev servers with a helper, then inspects screenshots, the DOM and console logs.
context-engineering
119,431Agent Workflows
Control what an AI coding agent sees with rules files, a context hierarchy, packing strategies and budget management.
using-agent-skills
119,431Agent Workflows
Map incoming work to the right agent skill and follow six operating behaviors that apply across all of them.
Neat Freak
22,434Agent Workflows
End-of-session cleanup that aligns project docs, CLAUDE.md or AGENTS.md rule files and agent memory with what the code and running services do today.
SkillOpt Sleep for Claude Code
19,174Agent Workflows
Gives Claude Code a sleep cycle: it reads past sessions, replays recurring tasks and stages CLAUDE.md and SKILL.md edits that beat a held-out score.
SkillOpt Sleep for Codex
19,174Agent Workflows
Gives Codex a sleep cycle: it reviews past sessions, replays recurring tasks and stages skill and CLAUDE.md edits that pass a held-out score gate.
SkillOpt Sleep for Cursor
19,174Agent Workflows
Reviews recent Cursor sessions, replays recurring tasks and stages edits to a project Cursor skill that pass a held-out score gate.
prompt-engineer
12,473Agent Workflows
Designs, tests and refines LLM prompts with few-shot and chain-of-thought patterns, structured output schemas, system prompts and eval suites.
dbs-install-skill
11,518Agent Workflows
Links one skill, or a folder of skills, into every agent installed on the machine with a single script, and cleans up duplicate entries.
react-vite-dashboard
11,108Developer Tools · Frontend And UI Engineering
Converts Stitch screens into React and Vite dashboards with TanStack Query, DESIGN.md tokens and read-only Web3 patterns.
shadcn-ui
11,108Developer Tools
Guides agents through shadcn/ui work: finding components, installing them with the CLI, theming with CSS variables and extending them with cva.
goal-prompt
8,320Agent Workflows
Drafts one-line /goal commands for Claude Code and Codex that have a checkable end state, a stated check, invariants and a stop bound.
Skill Improver
8,320Agent Workflows
Loops the plugin-dev skill-reviewer agent and a fixer over a Claude Code skill until its review comes back clean, with a ledger and scope guard.
Dual Axis Skill Reviewer
7,471Agent Workflows
Scores agent skills on two axes, deterministic code checks and an LLM review, then merges them into a weighted score with improvement items.
skill-designer
7,471Agent Workflows
Builds a prompt from a JSON skill idea that tells Claude CLI to create a full skill folder with SKILL.md, references, scripts and tests.
n8n Agents
6,689Developer Tools
A guide for designing n8n AI agents: which AI node to use, how to name tools, wire memory, force structured output and gate risky actions behind human review.
n8n Binary and Data
6,689Developer Tools
A guide to files in n8n: where bytes live, how to read and write them, how to stop transforms from dropping them, and how to pass files to agent tools and chat apps.
n8n Code JavaScript
6,689Developer Tools
A guide to writing JavaScript in n8n Code nodes: a gate that checks native nodes first, data access, return format, webhook body, sandbox limits and loop pitfalls.
n8n Code Python
6,689Developer Tools
A guide to native Python in n8n 2.x Code nodes: the two input variables, blocked imports, denied builtins, accepted return shapes and how errors interact with onError.
n8n Code Tool
6,689Developer Tools
A guide to the n8n Custom Code Tool that AI agents call: string in and string out, the query variable, input schemas, sandbox limits and the three signature errors.
n8n Error Handling
6,689Developer Tools
A guide to n8n error handling: the two-step per-node error output, retryOnFail, 4xx and 5xx webhook responses and Error Trigger workflows for unattended runs.