darwin-skill

Analyze SKILL.md files with an 8-dimension rubric and optimize via git-backed hill-climbing.

Updated Mar 24, 2026

Search Tags:#git #optimization #prompts #rubric #skill #tests

Ready to run

npx skills add https://github.com/pingqLIN/UniText --skill darwin-skill-pingqlin

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: darwin-skill
Source: https://github.com/pingqLIN/UniText/tree/main/runtime/skills/darwin-skill
Command: npx skills add https://github.com/pingqLIN/UniText --skill darwin-skill-pingqlin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

Darwin.skill tackles the challenge of optimizing and vetting AI agent Skills by combining structural evaluation with live, test-driven feedback, ensuring improvements are measurable and auditable.

Core Features & Use Cases

Dual evaluation: static structure scoring plus real-world effectiveness testing using test prompts.
Independent scoring: a sub-agent evaluates outputs to avoid self-reporting bias.
Git-backed optimization: a ratchet mechanism that keeps only improvements via commits and reverts regressions.
Test prompts design: phase-appropriate prompts ensure evaluations reflect typical usage.
Human-in-the-loop: human confirmation at key milestones before applying changes.
Result Card generation: after optimization, automatic visual cards summarize improvements.

Quick Start

Install this skill and run the optimizer on your target skills to begin the evaluation loop.

Frequently Asked Questions about darwin-skill

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

FAQPage Schema

How do I optimize AI agent skills using test prompts?▼

To optimize AI agent skills, you run test prompts comparing Skill-enabled versus baseline performance. This process uses an 8-dimension rubric and a git-backed ratchet mechanism to keep improvements and revert regressions.

What is git-backed hill-climbing optimization for skill evaluation?▼

Git-backed hill-climbing optimization for skill evaluation is a ratchet mechanism that commits only proven improvements to your skills. It automatically reverts any regressions identified during live testing with test prompts.

How does an independent sub-agent prevent self-reporting bias in skill testing?▼

An independent sub-agent prevents self-reporting bias in skill testing by separately evaluating the outputs generated by the agent. This ensures structural scoring and real-world effectiveness assessments remain objective and measurable.

Can I use human-in-the-loop checkpoints to vet AI skill improvements?▼

Yes, you can use human-in-the-loop checkpoints to vet AI skill improvements. The optimizer requires human confirmation at key milestones before applying any changes, ensuring all modifications are auditable and manually approved.

Do I need git to run structural scoring and live testing on agent skills?▼

Yes, you need git to run structural scoring and live testing on agent skills. The optimizer relies on a git-backed ratchet mechanism to commit approved improvements, revert regressions, and generate visual result cards for each change.

What is the 8-dimension rubric used for evaluating SKILL.md files?▼

The 8-dimension rubric used for evaluating SKILL.md files is a static structural scoring framework combined with phase-appropriate test prompts. It measures real-world effectiveness to ensure skill improvements are measurable and auditable.