Skill Creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Overview

The Skill Creator is a specialized utility within the anthropics/skills repository designed to manage the full lifecycle of AI agent capabilities. Compatible with Claude and claude-code, this tool enables developers to build new skills from the ground up or refine existing ones through iterative improvements. It provides functional modules for running evaluations and benchmarking performance using variance analysis to ensure reliability. Additionally, the tool focuses on technical optimization by refining skill descriptions to enhance triggering accuracy during agent interactions. As part of the anthropics/skills project, which has gained significant community traction with over 150,000 stars, this skill supports diverse applications ranging from Python development and security reviews to data research and ROS integrations.

Use Cases

Generating new agent skills from scratch with optimized descriptions for improved triggering accuracy.
Benchmarking skill performance and conducting variance analysis to ensure consistent output quality.
Modifying and improving existing skill logic based on automated evaluation results and testing metrics.

Install Notes

# Review source first
open https://github.com/anthropics/skills/blob/main/skills/skill-creator/SKILL.md

Copy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.

Security Notes

When using Skill Creator to develop or modify agent capabilities, users should ensure that the resulting skills adhere to established security protocols for data handling and system access. Reviewing the logic of newly generated skills is essential to prevent unintended execution patterns, especially when the skills interact with external environments, browsers, or sensitive research data.

Related Skills

MCP Builder

anthropics/skills

Coding

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

CodexClaude
typescriptpython
164,398 StarsApache-2.0

Claude API

anthropics/skills

Coding

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthr...

Claude CodeClaude
typescriptpython
164,398 StarsApache-2.0

Source Driven Development

addyosmani/agent-skills

Coding

Grounds every implementation decision in official documentation. Use when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.

typescriptpython
80,654 StarsMIT

Context Engineering

addyosmani/agent-skills

Coding

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

CodexClaude Code
typescriptreact
80,654 StarsMIT

Git Workflow And Versioning

addyosmani/agent-skills

Coding

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog.

securityreview
80,654 StarsMIT

Shipping And Launch

addyosmani/agent-skills

Coding

Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.

typescriptjavascript
80,654 StarsMIT