skills.rest
tusosos
tusososCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Draft, test, and evaluate Claude skills with benchmark comparisons.

Updated Apr 3, 2026
Search Tags:#automation#evaluation#iteration#benchmark#skill-creation#prompt-engineering#description-optimization
One-click install
npx skills add https://github.com/tusosos/manus-knowledge-base --skill skill-creator-tusosos
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/tusosos/manus-knowledge-base/tree/main/OKComputer-3D/.agents/skills/skill-creator
Command: npx skills add https://github.com/tusosos/manus-knowledge-base --skill skill-creator-tusosos

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyYAML, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps teams quickly create, refine, and measure Claude skills by guiding end-to-end workflows from drafting to evaluating and updating triggering descriptions.

Core Features & Use Cases

  • Create new skills from scratch, iterate on drafts, and run structured evals to measure performance.
  • Benchmark skill triggering, compare with and without a skill, and use quantitative metrics to drive improvements.
  • Collect, analyze, and rewrite SKILL.md and associated content to maximize triggering accuracy and user outcomes.

Quick Start

Draft a new skill, write a test prompt, run evals, and iterate on the description until triggering is reliable.

Frequently Asked Questions about skill-creator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate and optimize skill triggering descriptions?▼

To evaluate and optimize skill triggering, draft prompts, run structured evals using test sets, and iterate on your SKILL.md frontmatter. Benchmark with-skill versus baseline comparisons to measure improvements reliably.

What is the best way to benchmark skill performance during iteration?▼

Benchmarking skill performance involves running structured evals with test sets to compare with-skill and baseline outcomes. This produces a quantitative benchmark summary to track progress and drive iterative improvements.

How do I create a new skill from scratch and test its prompts?▼

Creating a new skill from scratch requires drafting the SKILL.md file, writing test prompts, and running structured evals. Iterate on the content and triggers until the skill performs reliably across your test cases.

Does skill creation require specific dependencies or environments?▼

Skill creation relies on the PyYAML dependency to parse SKILL.md frontmatter. It also utilizes optional subdirectories for references and assets to implement deterministic tasks within the development environment.

Why does my skill fail to trigger reliably during testing?▼

Unreliable triggering happens when the SKILL.md description lacks accuracy. Run structured evals, analyze baseline versus with-skill benchmark comparisons, and rewrite the triggering descriptions to maximize accuracy.

Can I use structured test sets to measure skill improvements?▼

Yes, you can use structured test sets to measure skill improvements. Run evals comparing baseline and with-skill performance, then analyze the benchmark summary to guide description optimization and iteration.

Related Skills

Explore More Software Engineering Skills→
vuanhtu1993vuanhtu1993

skill-creator

Create, validate, and package Claude Skills into .skill files.

Community
Intermediate
yibozhongyibozhong

skill-creator

Automate creation, testing, and refinement of Claude skills with SKILL.md and evals.

Community
Advanced
mvillmowmvillmow
18

evaluate-model

Evaluate ML model performance on test datasets with classification and regression metrics.

Community
Basic
codeboltaicodeboltai

skill-creator

Create and refine Claude skills with structured SKILL.md templates and packaging workflows.

Official
Intermediate