All skills
bmad-eval
Run a skill's evals and report baseline, variant, quality, and trigger results with cited evidence.
- Part of bmad-code-org/BMAD-METHOD
- 9.1k installs
- Developer Tools · Coding skills
When to use it
You have a skill with eval cases or trigger queries and need to know whether it beats the bare model or fires on the right prompts.
For example
You say
Use bmad-eval to run baseline and trigger evals on my skill at ./skills/pdf-summarizer and tell me if it beats the bare model.
You get
- Timestamped run folder
- run.json with harness command
- Per-case transcripts and grading
How it works
- Each case runs in a clean room outside the project so host config and installed skills can't bias results.
- A result counts as settled only at 3 or more runs per case; fewer is reported as a quick look.
Before installing
Trigger mode and description optimization need the harness command recorded in the skill's customization; without it, run bmad-customize first.
This skill includes 11 scripts your assistant may run on your computer.
More Coding skills
See all- lark-skill-maker486kTurns Lark API operations into reusable custom skills for the CLI.
- feature-forge4.7kRuns requirements workshops that produce feature specs, user stories, acceptance criteria and checklists.
- dual-axis-skill-reviewer3.7kScores project skills with automated checks plus an LLM review and lists concrete improvements.
- skill-designer3.5kTurns a structured idea into a complete new skill folder with instructions, references, scripts and tests.
Also in this pack
- bmad-build18.8kImplements a story, feature or bug fix end to end: plan, code, review, verify.
- bmad-code-review18.4kRuns several independent reviewers in parallel on code changes and triages the findings.
- bmad-brainstorming18.1kFacilitates a brainstorming session using varied creative techniques to generate ideas.
- bmad-agent-architect18kActs as Winston the system architect to lead technical design decisions.