Dual Axis Skill Reviewer

This is a gate-keeping tool for skill quality. It runs deterministic checks on structure, scripts, and tests, then merges those scores with an LLM-based deep review to produce a weighted final score. You'd use it when you want reproducible numbers before merging new skills, especially if you're enforcing a threshold like 90+. The two-axis approach is smart because you get hard pass/fail criteria plus qualitative code review in one number. It works cross-project via a project-root flag and spits out JSON plus markdown reports with concrete improvement items when scores fall short. The workflow is a bit manual since you run the auto axis, feed a generated prompt to an LLM, then merge the results, but that's the tradeoff for keeping the LLM step flexible.

skills.sh installs: 3.5K
GitHub stars: 3.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add tradermonty/claude-trading-skills --skill dual-axis-skill-reviewer --agent claude-code

Installs into .claude/skills of the current project.

Files

Dual Axis Skill Reviewer

Run the dual-axis reviewer script and save reports to reports/.

The script supports:

Random or fixed skill selection
Auto-axis scoring with optional test execution
LLM prompt generation
LLM JSON review merge with weighted final score
Cross-project review via --project-root
Non-scoring display of skills-index.yaml production verification declarations

When to Use

Need reproducible scoring for one skill in skills/*/SKILL.md.
Need improvement items when final score is below 90.
Need both deterministic checks and qualitative LLM code/content review.
Need to review skills in a different project from the command line.

Prerequisites

Python 3.9+
uv (recommended — auto-resolves pyyaml dependency via inline metadata)
For tests: uv sync --extra dev or equivalent in the target project
For LLM-axis merge: JSON file that follows the LLM review schema (see Resources)