skills.rest
rajivhasija79-bit
rajivhasija79-bitCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Draft, test, and evaluate Claude skills through iterative refinement.

3|4|Updated Mar 21, 2026
Search Tags:#tooling#evaluation#iteration#skill-development#workflow-automation#prompt-engineering
One-click install
npx skills add https://github.com/rajivhasija79-bit/DV-Skills --skill skill-creator-rajivhasija79-bit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/rajivhasija79-bit/DV-Skills/tree/main/skill-creator
Command: npx skills add https://github.com/rajivhasija79-bit/DV-Skills --skill skill-creator-rajivhasija79-bit

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Skill Creator enables teams to design, implement, and continuously improve Claude skills by guiding the drafting, testing, evaluation, and iteration workflow.

Core Features & Use Cases

  • End-to-end skill lifecycle: capture intent, draft SKILL.md, run trigger evaluations, review results, and iterate based on feedback.
  • Built-in evaluation loop: leverage the eval/viewer tooling (eval-viewer/generate_review.py) to visualize results and inform optimization.
  • Flexible resource model: optional bundled resources (scripts/, references/, assets/) that can be used to automate deterministic tasks, provide documentation, and template outputs.

Quick Start

Draft a new skill, create a few test prompts, run evaluations, review the results, and repeat until you are satisfied.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate skill development and prompt engineering for Claude?▼

Iterating on Claude skills requires running trigger evaluations and reviewing structured feedback. This skill automates that lifecycle, using bundled scripts to generate review data that informs workflow automation and prompt optimization until performance goals are met.

What is the best way to evaluate and measure Claude skill performance?▼

The best way to measure Claude skill performance is through a structured evaluation loop. This skill leverages an eval-viewer script to visualize test results, allowing you to assess trigger criteria and guide iterative refinements based on structured feedback.

Do I need pyyaml to run skill refinement and evaluation scripts?▼

Yes, pyyaml is required as a dependency. It supports the underlying scripts that execute the skill refinement workflow, enabling you to define triggering criteria and run the evaluation loop effectively.

How does an iterative workflow improve prompt engineering outcomes?▼

Iterative workflows improve prompt engineering by applying structured feedback from continuous testing. Repeatedly drafting, evaluating trigger criteria, and reviewing results allows you to measure performance and guide targeted optimizations to the skill.

Can I bundle custom scripts and references within my skill development process?▼

Yes, the skill supports a flexible resource model allowing you to bundle optional scripts, references, and assets. These components automate deterministic tasks, provide documentation, and template outputs to streamline the skill development process.

Related Skills

Explore More Software Engineering Skills→
LortunateLortunate
1

skill-creator

Design and validate Claude skills with SKILL.md and evaluation loops.

Community
Advanced
ligianehualigianehua

canary

Monitor a live URL for errors, performance, and page health after deployment.

Community
Advanced
Eva813Eva813
2

skill-creator

Create and improve Claude-compatible skills with SKILL.md and eval runs.

Community
Advanced
duotifyduotify
252

skill-creator

Design and refine Claude skills through automated evaluation and iteration.

Official
Advanced