Code Review Agent Skills

Runs an adversarial code review with two blind judges analyzing the same code from opposing perspectives to find flaws before production.

Answers questions about a codebase by searching and reading source files, then synthesizing answers with inline citations and a key files table.

Create pull requests following Sentry's engineering practices, including drafting descriptions, titles, and issue references.

Audits Claude skills and commands for quality, offering Quick Scan for changed skills and Full Stocktake modes with sequential subagent batch evaluation.

Delivers a small, bounded code change through inspection, a mini-plan, implementation, testing, review, and adversarial verification. Use for bug fixes, configuration changes, and features expected to touch no more than five files.

Audits Vue 3 components for design-system consistency, legacy patterns, and missing states, producing a component log.

Reviews a codebase for structural smells and refactors them with provable safety, using micro commits and green-bar discipline.

Performs structured code reviews of git branches, tracking findings in a living document and optionally running deep architectural analysis with subagents.

Reviews and repairs risky or unclear code with minimal validated changes, running a fixed-point loop until the diff is clean across two consecutive review cycles.

Analyzes a local codebase to infer its actual architecture from code-first evidence, producing a dominant architecture label, coexisting patterns, drift, and repo-fit advice for downstream agents.

Generates a concise bullet-point summary of branch changes for a pull request description, grouping related commits by theme and verifying details against actual files.

Mines a codebase for evidence-backed improvement opportunities, forcing two escalation gates to surface breakthrough ideas, and outputs a ranked portfolio with a plan seed without implementing.

Reviews development plans for gaps, hidden assumptions, critical misses, and XP violations, then presents prioritized findings for confirmation.

Classifies code review findings to choose the smallest correct response, preventing one-patch-per-comment churn.

Define owned inductive invariants and enforce them at parse, construct, API, DB, lock, or transaction boundaries, with counterexample-driven verification.

Reviews all uncommitted changes in the current Git repository and produces a structured code review report with findings and a verdict.

Drafts GitHub pull request titles, bodies, issue-closing footers, and maintainer ping comments, tailored to repo-specific commitlint or semantic PR conventions.

Applies universal TypeScript, JavaScript, React, and Node.js quality conventions for this repo. Use when reviewing or writing TS/TSX, refactoring for clarity, or enforcing naming, immutability, and error-handling patterns.

Scans Python and JavaScript codebases for bugs, security vulnerabilities, code smells, and anti-patterns, producing a prioritized fix list with line numbers, severity ratings, and suggested corrections.

Runs a structured quality control audit on codebases, covering tests, imports, static analysis, type checking, smoke tests, UI verification, file consistency, and documentation, producing a PASS/WARN/FAIL report.

Provides shared C language infrastructure for OpenClaw skills, including AST parsing, CMake analysis, Unity test generation, and security rule checking.

Guides contributors through creating pull requests that add or fix skills, with a checklist covering metadata validation, risk labeling, and security disclaimers.

Answers questions about a code repository by searching and reading source files, then synthesizing answers with inline citations and a key files table.

Runs a structured bug-fix pipeline: scouts evidence, diagnoses root cause, applies minimal fixes, and reviews before committing.

Audits code quality against a shared contract, producing structured findings and blocking pipeline phases on critical issues without modifying code.

Query a pre-indexed codebase via CLI to understand structure, find symbols, assess change impact, debug failures, and evaluate PR risk.

Scans recently changed code for tech debt: duplicated logic, dead code, magic numbers, deep nesting, and TODOs, then proposes fixes.

Guides a structured feature-development workflow: explore the codebase with subagents, draft a plan for approval, implement step by step, verify with parallel checks, and record conventions.

Runs a structured code review using four parallel subagents covering style, correctness, security, and performance, then synthesizes findings by severity and gives an approve/needs-changes recommendation.

Launches four parallel adversarial review agents covering security, scope, fidelity, and test gaps, then synthesizes findings into a ranked verdict for plans or feature branches.

Reviews CUDA, OpenMP, and OpenCL code for parallel correctness, covering data races, memory model violations, synchronization bugs, numerical precision issues, and API-specific pitfalls.

Scopes code-review blast radius and detects architectural hotspots using Tree-sitter AST analysis and GraphRAG, with an MCP server for graph-based analysis.

Dispatch a code-reviewer subagent to catch issues before they cascade, with guidance on when to request review and how to act on feedback.

Executes implementation plans by dispatching a fresh subagent per task and running two-stage reviews for spec compliance and code quality.

Provides code review best practices, checklists, and example feedback for quality, security, performance, and maintainability.

Measures code quality, identifies code smells, and implements quality gates using static analysis and technical debt tracking.