skills.rest
brunoreinstein-cloud
brunoreinstein-cloudCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Coordinate end-to-end creation, evaluation, and optimization of Claude Code skills.

Updated Aug 23, 2026
Search Tags:#automation#workflow#cli#evaluation#iteration#creation#skill
One-click install
npx skills add https://github.com/brunoreinstein-cloud/chat-assitjur --skill skill-creator-brunoreinstein-cloud
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/brunoreinstein-cloud/chat-assitjur/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/brunoreinstein-cloud/chat-assitjur --skill skill-creator-brunoreinstein-cloud

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, pyyaml.

What problem does it solve?

This Skill provides an end-to-end workflow for creating, testing, and improving Claude skills. It covers drafting SKILL.md frontmatter, running iterative eval loops, benchmarking, and maintaining history to drive continuous improvement.

Core Features & Use Cases

  • Skill creation & iteration: Draft a new skill and iteratively refine prompts, tests, and outputs.
  • Evals, benchmarking & history: Run evaluations, generate benchmarks, and preserve iteration history to guide improvements.
  • Trigger optimization: Tune skill descriptions to improve triggering accuracy and reduce false positives.

Quick Start

Start by drafting a SKILL.md with a descriptive name and frontmatter, then run an initial evaluation loop to iterate toward a stable skill.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I build and test Claude skills end-to-end?▼

To build and test Claude skills, draft a SKILL.md with frontmatter, run iterative evaluation loops, benchmark results, and track history to drive data-informed prompt improvements and reliable triggering.

What is the best way to optimize Claude skill triggering and reduce false positives?▼

Optimizing Claude skill triggering requires tuning skill descriptions iteratively, running targeted evaluations to measure accuracy, and refining prompts based on benchmarking history to reduce false positives.

Can I use this workflow to improve existing Claude skills through iteration?▼

Yes, you can improve existing Claude skills through iteration by applying the workflow to run new evaluations, benchmark current outputs, and refine prompts to achieve data-informed optimizations.

Do I need Python and YAML dependencies to create and evaluate Claude skills?▼

Yes, creating and evaluating Claude skills requires Python dependencies including the anthropic SDK and pyyaml to coordinate automated workflows, parse SKILL.md frontmatter, and run evaluation loops.

How does iterative benchmarking work when improving Claude skills?▼

Iterative benchmarking for Claude skills works by running evaluation loops, comparing output metrics across iterations, and maintaining a history of results to guide continuous, data-informed prompt refinements.

Related Skills

Explore More Software Engineering Skills→
lemulemu

skill-creator

Automate Claude skill creation, evaluation, and improvement with provided scripts.

Community
Advanced
stabilefrisurstabilefrisur

skill-creator

Creates, evaluates, and iterates Claude skills with benchmark-driven improvements.

Community
Advanced
sodadatasodadata
35

messydata

Generate validated MessyData YAML configurations for synthetic dirty data pipelines.

Official
Intermediate
Speirsy11Speirsy11

skill-creator

Automate drafting, evaluating, and iterating Claude skills with SKILL.md.

Community
Advanced