dev-review
dev-review is a Change & PR review skill for AI agents, published by FHIR in the fhir-candle repository on GitHub. Skillspace rates dev-review D (57/100) and it passed the safety scan; the rating is based on static analysis only.
Performs a two-track code-quality and QA review in the role of a staff-level Engineering Lead and a staff-level QA Lead, then synthesizes both critiques into a single `analysis.md` suitable to hand back to the engineering team. USE FOR: pre-PR self-review, post-`dev-do` quality gates, ad-hoc deep reviews of a change set. Accepts either a full path to the analysis file or a short slot number that expands to `scratch/[MMDD]-[##]/analysis.md`. Optional `max_subagents` (default 3) caps parallel sub-agent fan-out. Engineering review covers antipatterns, unoptimized hot paths, consistency errors, dead code, and design issues; QA review covers test coverage, edge cases, regression risk, and verifiability. Read-only with respect to the codebase — never modifies source, never commits, never pushes.
- Grade
- D
- Quality
- 57 / 100
- Safety
- Passed
- GitHub stars
- 20
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 80 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 3 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- 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.