Skip to content
Skill Creator

Skill Creator

by Anthropic
Added to Onei
Repository Docs
markdown Development

Summary

Create, edit, and optimize Agent Skills — scaffold new skills, refine existing ones, run evals, and tune descriptions for reliable triggering.

Install This Skill

Add this skill to your favorite AI agent in a few steps.

Any AI agent

This skill is plain instructions — it works with any assistant that accepts custom instructions or system prompts.

  1. Copy the skill content with the button below.
  2. Paste it into your agent's instruction file or system prompt (for example AGENTS.md, .cursorrules, or a custom instructions field).
  3. Ask the agent to apply the skill whenever the task matches.

Skill Content

Markdown Content

Copy this content and use it with your preferred AI agent

# Skill Creator

Use this skill to create a new skill from scratch, or to edit, optimize, and measure an existing one.

## What it does
- Scaffolds the `SKILL.md`, scripts, and resource structure for a new skill
- Improves the wording, scope, and workflow of an existing skill
- Runs evals and benchmarks with variance analysis to measure quality
- Tunes the `description` frontmatter so the skill triggers on the right requests and not on the wrong ones

## Why description quality matters
A skill only helps if it loads at the right moment. This skill treats the trigger `description` as a first-class artifact and iterates on it against test prompts.

Description

A meta-skill for building and improving Agent Skills. It scaffolds a new skill from scratch, edits and optimizes an existing one, runs evaluations to test behavior, benchmarks performance with variance analysis, and optimizes a skill's description so it triggers accurately. Use it whenever you are authoring or tuning a skill.

Install

Related Skills

Skill: SerpApi Agent Usability Test

by SerpApi

A protocol for measuring whether agents can discover and use your tool without being told about it — WITH/WITHOUT trials, binary scoring, and lift as the only metric. The subject under test is your docs, not the model.

Development

Skill: Claude API Reference

by Anthropic

Authoritative reference for the Claude API and Anthropic SDKs — model IDs, pricing, parameters, streaming, tool use, MCP, agents, prompt caching, and token counting.

Development

Skill: Handoff

by Matt Pocock

Compress the current Claude Code session into a portable handoff document so a fresh agent can continue the work without re-reading the whole conversation.

Development
Browse all skills →