Code Review Agent Skills

Identifies common software anti-patterns in code and suggests refactoring solutions to improve code quality.

Analyzes codebases to understand existing features, tracing entry points, execution paths, architecture layers, patterns, and dependencies before new development.

Runs a multi-perspective review of a pull request, including code quality, tests, and potential silent failures, then reports findings ranked by severity.

Analyzes codebases to map entry points, execution flows, architecture layers, patterns, and dependencies before new development begins.

Analyzes type design for encapsulation, invariant expression, usefulness, and enforcement, providing scores and improvement suggestions.

Runs independent AI CLI reviewers over phase plans and merges their feedback into a REVIEWS.md file.

Guides technical evaluation of code review feedback, emphasizing verification before implementation and reasoned pushback over performative agreement.

Dispatches a code-reviewer subagent to evaluate work against requirements and plan, then acts on the feedback before merging.

Blocks Edit/Write/Bash actions until the agent presents concrete facts about imports, data schemas, and the user's instruction, improving output quality.

Produces a maintainer-grade review of a pull request or large contribution, explaining the change tutorial-style and delivering a polished HTML or Markdown report with a concrete merge recommendation.

Resolves legacy references to the code-reviewer capability by routing to the current runtime agent or skill.

Resolves legacy references to the pr-review-expert capability by routing to the current runtime agent or skill.

Resolves legacy references to the code-review-expert capability by routing to the current runtime agent or skill.

Provides guidelines for writing conventional commit messages and pull request descriptions, including merge strategy and GitHub username verification.

Runs an evidence-first, read-only workflow over large codebases via an external JSONL REPL server, retrieving only minimal file slices and greps to produce cited architecture and audit reports.

Applies four disciplined mindsets—audit, debt, help, review—to cut complexity, track deferrals, surface reference, and catch over-engineering in codebases.

Interact with GitLab via helper functions for merge requests, issues, pipelines, and code review comments.

Audits WordPress plugin or theme PHP code for common security mistakes including missing nonce checks, capability checks, input sanitization, output escaping, SQL preparation, AJAX exposure, file traversal, and unsafe redirects.

Runs three parallel reviewers to find code reuse, quality, and efficiency issues in a diff, then applies safe fixes and reports risky ones.

Reviews local git changes and GitHub pull requests, leaving inline comments and formal reviews.

Verifies a code change before it lands by scanning the staged diff, running tests, and delegating to an independent reviewer.

Generates a pull request title and body from local git history, writing them to a draft file for review before publishing.

Enforces principal-engineer-level Python code quality: formatting, type safety, idiomatic patterns, class and function design, and anti-pattern prevention.

Enforces complexity analysis, correct data structure selection, vectorization, and algorithm implementation discipline at principal-engineer level.

Guides incremental code improvements, error-proofing through types and validation, and standardization for higher quality and fewer defects.

Enforces an algorithm-first discipline: state Big-O, data structure, and algorithm family before writing loops, queries, or recursion, catching O(n^2), N+1, and brute-force defaults.

Answer repository questions grounded entirely in source code evidence, with inline citations and key file tables.

Guides incremental code improvements, error-proofing through types and validation, and standardization for higher code quality.

Answers questions about a code repository by analyzing source files and citing evidence with linked citations.

Design, review, debug, and test Python static types including Protocol, generics, variance, overloads, TypedDict, ParamSpec, TypeGuard, and narrowing.

Forces investigation of file dependencies before editing code to prevent cascade failures.

Reviews local branch changes for bugs, security vulnerabilities, and code quality issues using a structured checklist and attack surface mapping.

Audit Django code for validated performance issues including N+1 queries, unbounded querysets, missing indexes, and write loops.

Remove assigned mypy exclusion modules in small batches, fix typing issues, run validation, and produce a structured completion summary.

Ask an AI coding agent to identify which files it needs to examine before answering a question.

Runs a structured code review as a pre-commit or pre-ship gate, supporting multiple review engines and scope governance.