⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

skill-creator

@elliottzhao⭐ 0 stars

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

Adopt or update this skill from https://proskills.md/skills/other/elliottzhao-skill-creator-openclaw. First identify the installation path supported by this platform, detect whether it is already installed, compare the installed version with the latest stable release, show me what will change, and only then install or update it. If no native installer is available, use the complete package or source fallback described on the page.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars

⭐ 0 on GitHubGitHub ↗

New / niche

🟢ProSkills Score

—

📍

Not yet listed on ClawHub or SkillsMP

// README

Skill Creator

A comprehensive toolkit for creating, testing, optimizing, and managing skills in the OpenClaw environment.

Quick Start

# Create a new skill
cd /path/to/your-workspace
skill-creator

# Run skill evaluation
python -m scripts.run_eval \
  --eval-set evals/evals_example.json \
  --skill-path /path/to/skill-creator \
  --agent-id your-agent

# Improve skill description
python -m scripts.improve_description \
  --eval-results results.json \
  --skill-path /path/to/skill-creator \
  --agent-id your-agent

# Generate HTML report
python -m scripts.generate_report <workspace>

Overview

Skill Creator is a powerful toolkit that helps you:

Create skills from scratch or edit existing ones
Test skill triggering with comprehensive evaluation framework
Optimize descriptions using programmatic agent-based improvement
Benchmark performance with variance analysis and comparison
Generate reports with HTML viewer for qualitative analysis
Package skills for distribution

Key Features

OpenClaw Integration

All evaluation and optimization tools are now fully adapted for the OpenClaw environment:

run_eval.py - Uses openclaw agent --json to run test queries
improve_description.py - Uses OpenClaw agent to analyze failures and suggest improvements
generate_report.py - Generic HTML report generator
Session file parsing - Detects skill invocations via JSONL session files
No platform dependencies - Works directly with OpenClaw CLI

Comprehensive Toolset

Tool	Purpose
`run_eval.py`	Test skill triggering accuracy
`improve_description.py`	Optimize skill descriptions programmatically
`generate_report.py`	Generate HTML reports from eval results
`package_skill.py`	Package skills for distribution
`quick_validate.py`	Quick validation before packaging
`test_skill.sh`	Single query testing
`batch_test_skill.sh`	Batch testing from JSON files

Documentation

Resource	Description
`SKILL.md`	Main skill documentation
`tool-library.md`	Tool usage guide
`schemas.md`	JSON schemas for evals
`TESTING.md`	Comprehensive testing guide

Workflow

Capture Intent - What does the user want to accomplish?
Write SKILL.md - Create the skill structure
Create Test Cases - Define evals in evals/evals_example.json
Run Tests - Use run_eval.py to evaluate
Review Results - Use generate_review.py or analyze manually
Improve - Use improve_description.py if trigger rate is low
Package - Use package_skill.py to create distributable skill

Tool-Specific Guides

Evaluation Tools

run_eval.py - Run skill triggering evals
- --eval-set: Path to eval JSON
- --skill-path: Path to skill directory
- --agent-id: OpenClaw agent ID (default: suchi)
- --runs-per-query: Number of runs per query (default: 1)
- --timeout: Timeout per query in seconds (default: 60)
improve_description.py - Improve skill descriptions
- --eval-results: Path to eval results JSON
- --agent-id: OpenClaw agent ID (default: suchi)
- --log-dir: Directory to save iteration logs

Testing Scripts

test_skill.sh - Single query testing
batch_test_skill.sh - Batch testing from JSON

Contributing

See CONTRIBUTING.md for contribution guidelines.

License

See LICENSE.txt for license information.

Related Resources

Prompt Optimization Framework - Advanced prompt engineering techniques
Tool Library - Complete tool reference guide
Schemas - JSON schema definitions

// HOW IT'S BUILT

KEY FILES

SKILL.mdREADME.md

// REPO STATS

0 stars

// SHARE

Share on X Share on LinkedIn