adversarial-review
adversarial-review is a Change & PR review skill for AI agents, published by TophC7 in the dot.nix repository on GitHub. Skillspace rates adversarial-review D (62/100) and it passed the safety scan; the rating is based on static analysis only.
Project-agnostic adversarial code review. Reads the project's conventions first (CLAUDE.md, AGENTS.md, comment-style, manifest), then dispatches a six-scope swarm of agents in parallel — Architecture Fit, Reuse, Idiom Compliance, Quality, Efficiency, Comment Style — and collapses all findings into a single severity- sorted card list. Use when users ask to "critically review", "critique", "find issues in", "what's wrong with", or "review this PR / diff / code". Severity tiers: Blocking, Required, Suggestion.
- Grade
- D
- Quality
- 62 / 100
- Safety
- Passed
- GitHub stars
- 69
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
- 73 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- Low-risk patterns
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
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.