Code Review Agent Skills

Review, triage, validate, and discuss ClawHub GitHub issues and pull requests with structured evidence, best-fix analysis, and maintainer handoff.

Provides production-grade TypeScript guidance for React and Next.js, covering type narrowing, component props, generics, runtime validation, data fetching, state management, performance, accessibility, and code review.

Adds concise Chinese comments to C++ code snippets, inferring meaning from variable and function names while preserving the original code structure.

Reviews a PR or diff through three independent lenses—correctness, security, and test coverage—then deduplicates and validates findings before persisting them, reducing noise while catching more real bugs.

Runs ESLint to review code for style and correctness issues, with setup and documentation references.

Chains architecture review, implementation, and pull request creation to take a story from design through to a convention-compliant PR.

Gates a git branch before merge by running code review, security, test, and accessibility passes on the diff, then emits a single verdict.

Runs a deeper code review with the GLM-5 model via glm-review, validates findings against the actual code, and reports only confirmed issues.

Reviews local branch changes for bugs, security vulnerabilities, and code quality issues, using a structured checklist and verification process.

Establishes baseline cross-project coding conventions for naming, readability, immutability, and code-quality review, with pointers to framework-specific skills.

Adversarially verify an implementation against its objective, acceptance criteria, definition of done, and prohibitions using fresh evidence. Use for completion gates, release readiness, or independent verification after implementation and review.

Provides Git commands and workflows for commits, branches, rebases, merges, conflict resolution, history recovery, and team collaboration, with safety rules for force-pushing and destructive operations.

Provides a structured code review checklist covering security, performance, correctness, maintainability, testing, accessibility, and documentation, with a three-pass review process and guidance on severity levels and anti-patterns.

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

Reviews staged and unstaged code changes for security vulnerabilities, code quality issues, and adherence to project conventions, reporting findings by severity.

Provides grep-based patterns to verify that code artifacts are real implementations rather than stubs or placeholders, covering React components, API routes, database schemas, and hooks.

Creates a pull request from completed phase work, generates a rich PR body from planning artifacts, optionally runs code review, and prepares for merge.

Audits source code across C++, Android, iOS, and Web to classify files, detect embedded third-party libraries, and produce four-level verdicts with interactive HTML reports.

Prevents AI agents from calling methods, imports, or variables that do not provably exist in the user's installed version, reducing hallucinated code.

Create, update, and comment on GitHub pull requests with a focus on material impact, safety, and human reviewability.

Surveys a codebase as a senior advisor and produces prioritized, self-contained implementation plans for other models or agents to execute, without modifying source code.

Executes GitHub CLI and git commands with proper authentication, enforcing the --repo flag and providing helper functions for code review comments with suggestion blocks.

Audits WordPress plugin or theme PHP code for internationalization (i18n) correctness, including text-domain consistency, escaped translation helpers, placeholder usage, plurals, context, and text-domain loading. Produces a severity-ranked report of issues to fix before release.

Defines naming conventions for Apex classes, methods, variables, constants, custom objects, triggers, and test classes.

Analyze repositories for lines of code, language breakdown, file counts, and code-vs-comment ratios using pygount, with guidance on using language servers for symbol navigation.

Creates or edits a GitHub pull request in draft state from a reviewed draft file, with strict safeguards against merging, pushing, or modifying tracked files.

Enforces a principal-engineer self-review checklist on every code block before output, covering correctness, performance, security, naming, and testability.

Implements a code change on a feature branch, opens a single pull request to main, and runs a code review loop before handoff.

Reviews local branch changes for bugs, security vulnerabilities, and code quality issues, producing a prioritized report with severity ratings and concrete fixes.

Dispatch a code reviewer subagent to catch issues before they cascade, with precisely crafted context for evaluation.

Prevents AI agents from calling methods, imports, or variables that do not provably exist in the user's installed version, reducing hallucinated API usage.

Reviews code through the lens of 12 classic software engineering books, catching design smells, coupling issues, and architectural risks that linters miss.

Triggers a code-review subagent after tasks, features, or before merging to catch issues early.

Builds a local knowledge graph of a codebase using tree-sitter and graph algorithms, then answers architecture questions by querying the graph instead of reading many files, saving tokens.

Reviews code changes with a second AI reviewer, validates reported issues against the actual code, and reports only confirmed findings.

Evaluates iOS, macOS, tvOS, watchOS, and visionOS app code against Apple's App Store Review Guidelines to identify potential rejection issues before submission.