skills.rest
oabdelmaksoud
oabdelmaksoudCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Draft, test, evaluate, and iterate on OpenClaw SKILL.md-based skills.

4|Updated Feb 26, 2026
Search Tags:#automation#benchmarking#evaluation#packaging#iteration#skill-creation#OpenClaw
One-click install
npx skills add https://github.com/oabdelmaksoud/Openclaw-skills-Compilations --skill skill-creator-oabdelmaksoud
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/oabdelmaksoud/Openclaw-skills-Compilations/tree/main/skill-creator
Command: npx skills add https://github.com/oabdelmaksoud/Openclaw-skills-Compilations --skill skill-creator-oabdelmaksoud

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automates the end-to-end process of creating, refining, and evaluating OpenClaw skills. It helps teams transform ideas into testable SKILL.md definitions, run structured eval loops, and iterate toward higher triggering accuracy and reliability.

Core Features & Use Cases

  • Draft SKILL.md frontmatter and body content from user interviews
  • Run trigger-eval and looped improvements using the eval and loop tooling
  • Benchmark skill variants and package final skills for distribution

Quick Start

Draft a new skill, configure its evaluation, and kick off the evaluation loop to begin iterative improvement.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate OpenClaw skill creation and evaluation?▼

OpenClaw skill creation uses a structured workflow to draft SKILL.md files, run trigger-evaluation loops, and benchmark skill variants to improve triggering accuracy and reliability for distribution.

What is the best way to benchmark and iterate on SKILL.md definitions?▼

Benchmarking SKILL.md definitions uses structured evaluation loops to compare skill variants, measure triggering accuracy, and apply iterative improvements until the skill reaches the required reliability threshold for packaging.

Can I package OpenClaw skills for distribution after evaluation?▼

Packaging OpenClaw skills for distribution is supported after completing the evaluation loops and benchmarking, allowing teams to transform tested SKILL.md definitions into ready-to-distribute skill packages.

Do I need pyyaml and anthropic dependencies to draft and test OpenClaw skills?▼

Drafting and testing OpenClaw skills requires the anthropic and pyyaml dependencies to process SKILL.md frontmatter configurations and run the evaluation loops that benchmark triggering accuracy.

How does an evaluation loop improve trigger accuracy for skill creation?▼

Evaluation loops improve trigger accuracy by repeatedly testing SKILL.md definitions against benchmarks, measuring results, and applying automated iterative improvements to refine the skill's triggering behavior.

When should I not use automated skill benchmarking for OpenClaw?▼

Automated skill benchmarking is not suited for skills lacking testable trigger conditions or when SKILL.md definitions are too preliminary for structured evaluation loops to measure and iterate on triggering accuracy effectively.

Related Skills

Explore More Software Engineering Skills→
lemulemu

skill-creator

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

Community
Advanced
saahilvasdevsaahilvasdev

skill-creator

Automate Claude Skill creation and iterative improvement via eval-driven loops.

Community
Advanced
SuperPaulySuperPauly

skill-creator

Builds .skill packages with automated AST-based conflict detection.

Community
Advanced
PatrickjoshanedezPatrickjoshanedez

skill-creator

Create, refine, and benchmark AI skills with SKILL.md files and test suites.

Official
Advanced