code-review
Code Review executes a systematic multi-phase examination of pull requests and code diffs, starting with scope and intent identification before conducting a critical pass for logic errors, injection vulnerabilities, and resource leaks. Specialist lenses then apply targeted checks based on change type—tests, data access, auth, or UI—with each finding assigned a confidence level to guide merge decisions.
Code Review performs structured multi-pass analysis of diffs and PRs to identify bugs, security issues, and defects with confidence ratings.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-05-31
Code Review performs structured multi-pass analysis of diffs and PRs to identify bugs, security issues, and defects with confidence ratings. Code Review executes a systematic multi-phase examination of pull requests and code diffs, starting with scope and intent identification before conducting a critical pass for logic errors, injection vulnerabilities, and resource leaks. Specialist lenses then apply targeted checks based on change type—tests, data access, auth, or UI—with each finding assigned a confidence level to guide merge decisions.
Use it when
- Yes.
- Code Review audits code changes through a confidence-gated findings approach.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
blueberrycongee/termcanvas/code-review · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does Code Review do when I ask it to review a PR?
Code Review executes a systematic multi-phase examination of your pull request, starting with scope and intent identification before conducting a critical pass for logic errors, injection vulnerabilities, and resource leaks. Specialist lenses then apply targeted checks based on change type—tests, data access, auth, or UI—with each finding assigned a confidence level to guide merge decisions.
Can Code Review check my code for bugs and security issues?
Yes. Code Review performs structured multi-pass analysis that identifies both bugs and security vulnerabilities. It checks for logic errors, injection vulnerabilities, resource leaks, and applies specialist focus to critical areas like authentication, data access, and UI code. Each finding includes a confidence level so you can prioritize high-confidence issues before merge.
How does Code Review review code changes before merge?
Code Review audits code changes through a confidence-gated findings approach. It systematically examines your diff or pull request across multiple specialist lenses tailored to your change type, then surfaces issues with confidence ratings. This structured methodology helps you merge with confidence by highlighting critical problems in tests, data access, auth, and UI code.
What can I review this code for using Code Review?
Code Review analyzes your code for logic errors, security vulnerabilities including injection attacks, resource leaks, and type mismatches. It also performs specialized audits depending on your code type: test coverage and assertions for tests, SQL injection and parameterization for data access, credential handling for auth, and accessibility for UI. Each finding is confidence-rated.
Does Code Review find bugs in my code automatically?
Code Review is designed to find bugs through systematic analysis. It conducts a critical pass examining logic errors, injection vulnerabilities, and resource leaks, then applies specialist lenses to identify issues specific to your code's purpose—whether tests, data access, authentication, or user interface. Confidence levels help you distinguish high-certainty bugs from lower-confidence observations.
What makes Code Review different from a basic code review?
Code Review performs structured multi-pass examination rather than surface-level review. It combines a critical pass for common defects with specialist focus areas tailored to your change type, assigns confidence levels to each finding, and systematically checks for both logic errors and security vulnerabilities. This multi-phase approach helps catch issues a basic review might miss.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Code Review
Structured multi-pass review. Read the full diff before commenting on anything.
Phase 1: Orient
- Determine the review scope:
- If reviewing a PR:
git diff <base>..HEAD - If reviewing staged changes:
git diff --cached - If reviewing a file: read the file
- Understand the intent: read the commit messages, PR description, or task description to understand what the change is supposed to do
- Identify the change type: feature, bugfix, refactor, config, dependency update
Phase 2: Critical Pass
Read the diff line by line. Flag only real issues:
Always check: - Logic errors (wrong conditions, off-by-one, missing null checks on external data) - SQL injection, XSS, command injection, path traversal - Race conditions in concurrent code - Resource leaks (unclosed handles, missing cleanup) - Missing error handling at system boundaries (network, file I/O, user input) -
(truncated - see the full file via the links below)
File tree — 1 file
skills/skills/code-review/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Review a pull request or code diff for bugs and defects”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
QA skill uses real browser automation to test websites end-to-end, capturing visual evidence and validating user flows. It audits pages systematically, scores site health across console errors and interactivity, then fixes issues atomically with commit-per-fix discipline.
Investigate guides you through a disciplined five-phase debugging process: collect evidence, form ranked hypotheses, verify each one methodically, apply a minimal fix only after confirming root cause, then verify resolution. The workflow prevents guess-and-fix cycles by enforcing evidence gathering before hypothesis formation and a three-strike rule that forces re-collection rather than endless speculation.
Hydra is a Lead-driven orchestration toolkit that lets you coordinate multiple agents through structured workflows. The Lead makes strategic decisions while workers report semantic outcomes (done, needs_rework, replan) via a typed result contract, enabling parallel task execution with explicit decision points and intervention capabilities.
This skill integrates with App Genesis Forge to execute system integration tests in your local environment, catching component interaction issues before they reach code review. Part of a structured 19-role development workflow that enforces quality gates at each stage, it helps ensure defects don't propagate downstream.
Validates WooCommerce code changes for compliance with project standards, including PHP architecture patterns, naming conventions, documentation requirements, and UI copy guidelines. Flags violations with references to relevant standard documentation and provides corrective examples.
This skill executes a comprehensive design review by comparing your built application against the design brief and aesthetic direction. It captures screenshots across responsive breakpoints, analyzes visual hierarchy and consistency, and produces a prioritized refinement list organized by severity.