skills.rest
daikichiba9511
daikichiba9511COMMUNITY
Explore all skills by this author →
Website𝕏@nnc_5522GitHub

skill-creator

Automate the creation, evaluation, and iteration of Claude skills with SKILL.md.

1|Updated Jan 3, 2022
Search Tags:#automation#workflow#evaluation#iteration#skill#claude-code#frontmatter
One-click install
npx skills add https://github.com/daikichiba9511/dotfiles --skill skill-creator-daikichiba9511
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/daikichiba9511/dotfiles/tree/main/private_dot_claude/skills/skill-creator
Command: npx skills add https://github.com/daikichiba9511/dotfiles --skill skill-creator-daikichiba9511

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automates the end-to-end process of creating, evaluating, and iterating on skills for Claude, turning ad-hoc prompts into robust, measurable capabilities.

Core Features & Use Cases

  • Draft new skills from user goals and convert them into SKILL.md frontmatter plus actionable body instructions.
  • Run evaluation loops (trigger evals, compare with baselines, and collect metrics) to measure skill performance.
  • Generate and apply improvements to skill descriptions based on evaluation results, then re-run tests to converge on a strong triggering description.

Quick Start

Describe your skill goal and I will generate a starter SKILL.md, script the eval prompts, and begin iterative optimization.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create and iterate on Claude skills end-to-end?▼

To create Claude skills end-to-end, you define the skill intent, generate a SKILL.md file with frontmatter, run trigger evals, and iterate on the description until performance stabilizes.

What is the process for evaluating and refining a SKILL.md triggering description?▼

Evaluating a SKILL.md triggering description involves running evaluation loops, comparing results against baselines, and applying generated improvements to the skill frontmatter until trigger accuracy converges.

Can I automate the workflow for generating and testing Claude code skill frontmatter?▼

Yes, you can automate the workflow for Claude code skill frontmatter by using bundled scripts to test, evaluate, and package the skill instructions after drafting the initial file.

Do I need YAML to define frontmatter for Claude skills?▼

Yes, YAML is required as a dependency to define the frontmatter structure in your SKILL.md file when generating and packaging Claude skills.

Why are my Claude skill trigger evals not converging during iteration?▼

Trigger evals may not converge if the initial skill description lacks clarity, requiring you to analyze the evaluation metrics and apply generated description improvements before re-running the tests.

What's the best way to turn ad-hoc prompts into measurable Claude skills?▼

The best way to turn ad-hoc prompts into measurable Claude skills is to apply a structured workflow that automates drafting, evaluation, and iterative refinement of the skill instructions.

Related Skills

Explore More Software Engineering Skills→
ArtemisAIArtemisAI
3

template-skill

Generate a standardized SKILL.md template for new Claude skills.

Community
Basic
dariopalminiodariopalminio
1

skill-creator

Orchestrate Claude skill creation, evaluation, and packaging into .skill files.

Community
Advanced
yibozhongyibozhong

skill-creator

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

Community
Advanced
coreyjacoreyja
12

skill-writer

Draft SKILL.md frontmatter and structure guidance for Claude Code skills.

Community
Basic