Code review
Agent skills, autonomous agents, and MCP-companions for programming
npx -y skills add DROOdotFOO/agent-skills --skill code-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Structured code review with blast radius analysis, security scanning, quality scoring, and a 30+ item checklist. TRIGGER when: user asks to review a PR, diff, changeset, or code for quality/security/breaking changes; user runs /review or /code-review; reviewing staged or committed changes. DO NOT TRIGGER when: writing new code from scratch, refactoring without review context, general debugging.
SKILL.md
3.6 KB, as published. Nobody here has run it
Code Review Skill
Systematic code review following a fixed sequence: scope the change, assess blast radius, scan for security issues, verify tests, detect breaking changes, check performance, and score quality.
Review Workflow
- Scope -- Identify what changed (files, modules, services). Classify as feature, bugfix, refactor, config, or docs.
- Blast radius -- Trace dependencies to determine how far the change reaches. See blast-radius.md.
- Security scan -- Run pattern-based checks for common vulnerabilities. See security-scan.md.
- Test coverage -- Verify new/changed code has tests. Flag untested branches and edge cases.
- Breaking changes -- Detect API, schema, config, and dependency changes that break consumers. See breaking-changes.md.
- Performance -- Flag N+1 queries, unbounded loops, missing pagination, large allocations, blocking I/O on hot paths.
- Quality -- Score SOLID adherence, complexity, and code smells. See quality-checks.md.
Run the full checklist to ensure nothing is missed.
Output Format
Organize findings into four categories with severity:
| Category | Severity | Meaning |
|---|---|---|
| MUST FIX | CRITICAL/HIGH | Bugs, security holes, data loss risks |
| SHOULD FIX | HIGH/MEDIUM | Design issues, missing tests, poor patterns |
| SUGGESTIONS | MEDIUM/LOW | Style, naming, minor improvements |
| LOOKS GOOD | -- | Explicitly call out well-done aspects |
Format each finding as:
[MUST FIX | SHOULD FIX | SUGGESTION] (severity) file:line
Description of the issue.
Recommended fix or alternative.
Always end with a summary: total findings by category, overall quality score (0-100), and a PASS / CONDITIONAL PASS / FAIL verdict.
What You Get
- A structured review report with findings categorized as MUST FIX, SHOULD FIX, SUGGESTIONS, and LOOKS GOOD, each with severity and file location.
- Blast radius analysis showing how far the change reaches through dependency chains.
- A quality score (0-100) and a final verdict (PASS, CONDITIONAL PASS, or FAIL).
Sub-files
| File | Content |
|---|---|
| blast-radius.md | Dependency tracing, severity classification |
| security-scan.md | Vulnerability patterns, polyglot grep rules |
| quality-checks.md | SOLID violations, smells, scoring rubric |
| checklist.md | Full 30+ item review checklist |
| breaking-changes.md | API, schema, config, dependency breakage |
| receiving-review.md | How to evaluate and respond to review feedback |