dual-axis-skill-reviewer

1# Dual Axis Skill Reviewer
2 
3Run the dual-axis reviewer script and save reports to `reports/`.
4 
5The script supports:
6- Random or fixed skill selection
7- Auto-axis scoring with optional test execution
8- LLM prompt generation
9- LLM JSON review merge with weighted final score
10- Cross-project review via `--project-root`
11- Non-scoring display of `skills-index.yaml` production verification declarations
12 
13## When to Use
14 
15- Need reproducible scoring for one skill in `skills/*/SKILL.md`.
16- Need improvement items when final score is below 90.
17- Need both deterministic checks and qualitative LLM code/content review.
18- Need to review skills in a **different project** from the command line.
19 
20## Prerequisites
21 
22- Python 3.9+
23- `uv` (recommended — auto-resolves `pyyaml` dependency via inline metadata)
24- For tests: `uv sync --extra dev` or equivalent in the target project
25- For LLM-axis merge: JSON file that follows the LLM review schema (see Resources)
26 
27## Workflow
28 
29Determine the correct script path based on your context:
30 
31- **Same project**: `skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py`
32- **Global install**: `~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py`
33 
34The examples below use `REVIEWER` as a placeholder. Set it once:
35 
36```bash
37# If reviewing from the same project:
38REVIEWER=skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py
39 
40# If reviewing another project (global install):
41…