agentsclimarketplace

Code review

Skill DROOdotFOO/agent-skills/skills/code-review

Agent skills, autonomous agents, and MCP-companions for programming

Install
npx -y skills add DROOdotFOO/agent-skills --skill code-review

Assembled 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

  1. Scope -- Identify what changed (files, modules, services). Classify as feature, bugfix, refactor, config, or docs.
  2. Blast radius -- Trace dependencies to determine how far the change reaches. See blast-radius.md.
  3. Security scan -- Run pattern-based checks for common vulnerabilities. See security-scan.md.
  4. Test coverage -- Verify new/changed code has tests. Flag untested branches and edge cases.
  5. Breaking changes -- Detect API, schema, config, and dependency changes that break consumers. See breaking-changes.md.
  6. Performance -- Flag N+1 queries, unbounded loops, missing pagination, large allocations, blocking I/O on hot paths.
  7. 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:

CategorySeverityMeaning
MUST FIXCRITICAL/HIGHBugs, security holes, data loss risks
SHOULD FIXHIGH/MEDIUMDesign issues, missing tests, poor patterns
SUGGESTIONSMEDIUM/LOWStyle, 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

FileContent
blast-radius.mdDependency tracing, severity classification
security-scan.mdVulnerability patterns, polyglot grep rules
quality-checks.mdSOLID violations, smells, scoring rubric
checklist.mdFull 30+ item review checklist
breaking-changes.mdAPI, schema, config, dependency breakage
receiving-review.mdHow to evaluate and respond to review feedback

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.