skill-doctor

Diagnose and optimize Agent Skills using a structured rubric and Python scripts.

Updated Jun 15, 2026
One-click install
npx skills add https://github.com/stumman/hermes-harness-skills --skill skill-doctor-stumman
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-doctor
Source: https://github.com/stumman/hermes-harness-skills/tree/main/.agents/skills/skill-doctor
Command: npx skills add https://github.com/stumman/hermes-harness-skills --skill skill-doctor-stumman

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill autonomously diagnoses and improves Agent Skills against a shippability rubric, eliminating the need for manual interventions and ensuring consistent quality across skills.

Core Features & Use Cases

  • Skill Diagnosis: Identifies issues and potential improvements in Agent Skills.
  • Autonomous Optimization: Applies a keep-or-revert loop to autonomously improve skills.
  • Use Case: Use the skill-doctor to enhance a code review skill, ensuring it provides accurate and relevant feedback with minimal manual intervention.

Quick Start

Run the diagnostic tool lint_skill.py <target SKILL.md> to check the quality of the skill and initiate the optimization process.

Frequently Asked Questions about skill-doctor

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

FAQPage Schema
How do I automate the diagnosis and improvement of agent skills?

Automate agent skill improvement by running a diagnostic script like lint_skill.py against your target SKILL.md file, which evaluates quality against a structured rubric and applies targeted autonomous optimizations.

What is autonomous skill optimization using a keep-or-revert loop?

Autonomous skill optimization is an iterative process that applies targeted improvements to an agent skill and automatically keeps the changes if they meet quality standards, or reverts them if they fail the diagnostic rubric.

Do I need a Python environment to run skill diagnosis scripts?

Yes, you need a Python environment installed to execute the diagnostic scripts required for evaluating your agent skills and initiating the automated optimization process.

Can I use this tool for one-time code review skill enhancements instead of iterative cycles?

Yes, the tool supports both one-time improvements for quick fixes and iterative optimization cycles for continuously enhancing agent skills like a code review skill against a shippability rubric.

What is the best way to ensure consistent quality across multiple agent skills?

The best way to ensure consistent quality is using an autonomous diagnostic tool that evaluates agent skills against a standardized shippability rubric, eliminating manual interventions and automatically applying necessary improvements.

Why does my agent skill provide inaccurate feedback during code reviews?

Your agent skill may have diagnostic issues identifiable through a structured rubric evaluation; running an autonomous optimization loop can target and resolve these underlying problems to ensure accurate feedback.