bmad-spec
bmad-spec is an Engineering planning & specs skill for AI agents, published by bmad-code-org in the BMAD-METHOD repository on GitHub. Skillspace rates bmad-spec C (73/100) and it passed the safety scan; a judge model has also reviewed it.
Distill any intent input into the SPEC kernel + companions — the canonical, preservation-validated machine contract for downstream work. Use when the user says "create a spec", "distill this into a spec", "validate this spec", "update the spec", or "break this into stories".
- Grade
- C
- Quality
- 73 / 100
- Safety
- Passed
- GitHub stars
- 50,646
Placed #5 of 6 in the judged category final for Engineering planning & specs.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 97 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Vendor-specific: built around one product. Part of the public BMad Method framework that adopters use
Judge review
Placed #5 of 6 in the judged category final for Engineering planning & specs.
- Trigger
80 80 - Instructions
75 75 - Specificity
85 85 - Safety
90 90 - Disclosure
55 55 - Maintenance
65 65
A sound idea (deriving the spec from an append-only memlog so it can never drift), but activation leans on unexplained jargon like {workflow.<name>} and layered customize.toml files before any real work starts.
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.