bmad-eval
bmad-code-org2.2k installs
Find out whether your Agent Skill earns its keep.
What it does
Evaluates Agent Skills against a bare model, another version, a rubric, or trigger queries and reports evidence-backed findings.
When to use it
Use when asked to evaluate or benchmark a skill, grade its outputs, test its triggers, or compare versions.
How to use it
Give it a skill directory and evaluation mode; it runs existing cases and saves a timestamped report folder.
What you provide
- the skill directory
- an evaluation mode
- An existing project
Good to know
- starts one helper agent per item, so the count depends on the work
- acts without asking
- edits its own instructions
Latest review
What you need · 4
The evaluation runner requires Python 3.11 or later.
Uses uv to invoke the evaluation runner.
Access · 3
This skill
npx skills add bmad-code-org/BMAD-METHOD --skill bmad-customize
Execute
Installs bmad-customize for harness setup
CLI login files and keychains
Read
Reads configured CLI login files