skill-creator

Automate end-to-end skill creation, evaluation, and iterative refinement.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/ContractorKeith/openclaw-home --skill skill-creator-contractorkeith
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ContractorKeith/openclaw-home/tree/main/workspace-sean/skills/skill-creator
Command: npx skills add https://github.com/ContractorKeith/openclaw-home --skill skill-creator-contractorkeith

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml.

What problem does it solve?

Drafting and refining OpenClaw skills is an iterative, multi-step process. This Skill unit coordinates end-to-end workflows for creating, evaluating, and improving skills, including managing evaluation prompts, results, and descriptions to maximize triggering accuracy.

Core Features & Use Cases

  • End-to-end skill iteration: Draft, test, review, and refine skills with built-in scaffolding and reporting.
  • Trigger optimization: Leverage eval results and history to adjust when and how a skill triggers.
  • Tooling integration: Coordinate scripts (generate_report.py, run_eval.py, improve_description.py) to accelerate maturation and consistency.

Quick Start

Start by drafting a new skill and run the evaluation loop to bootstrap triggering improvements.

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 creation and trigger evaluation?

Automating skill creation involves drafting SKILL.md files, running trigger evaluations via scripts, and iteratively refining descriptions to improve triggering accuracy across the full lifecycle.

What is iterative skill refinement for prompt-engineering?

Iterative skill refinement is the process of evaluating trigger accuracy and applying updates to SKILL.md descriptions and templates to improve deterministic behavior and maximize triggering accuracy over time.

How do I improve skill triggering accuracy after drafting?

Improving skill triggering accuracy requires running evaluation prompts, reviewing history reports, and applying automated description updates to iteratively adjust when and how the skill triggers.

Does skill iteration require external dependencies to run evaluations?

Skill iteration requires the pyyaml dependency to parse configuration files and execute bundled scripts that enforce deterministic behavior during evaluation and improvement workflows.

What's the best way to manage skill evaluation prompts and results?

Managing skill evaluation prompts and results is best handled by coordinating tooling scripts that generate reports and run evaluations, maintaining history for consistent iterative improvements.

Why does my drafted skill fail to trigger correctly in workflows?

Drafted skills fail to trigger correctly when descriptions lack optimization; running trigger evaluations and applying history-based description improvements resolves inaccurate matching behavior.