Developer Tools & Repos Agent Skills

Automates Cocos Creator development workflows including scene editing, node management, and asset operations via a command-line interface.

Reverse engineer Cocos Creator 2.x / 3.x game builds.

Use when running TypeScript compile check on Cocos Creator 3.x project.

Use when the user mentions Codable review, JSON encoding/decoding issues, data serialization audit, or modernizing legacy code.

Writes production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks…

Map source file structure into navigable sections with line ranges and summaries for efficient agent navigation

Use this skill when the user wants to refactor code or improve documentation structure without changing external behavior.

Find and eliminate code duplication with DRY refactoring strategies

Execute automatically formats and validates code files using Prettier

Builds and queries code knowledge graph for dependency analysis, references, implementations, and architecture overview.

Systematic approach to refactoring code for improved maintainability, performance, and clarity while preserving functionality

Code review of changes on the current branch.

Use when opening a PR for review or when receiving review feedback.

General-purpose code review checklist. Use when reviewing any code change without a narrower specialization. Complements security-review…

Code review requires technical evaluation, not emotional performance.

Full review lifecycle — request reviews, handle feedback with technical rigor, and complete branch integration.

Request effective code reviews—specify focus areas, provide context, ask for architectural feedback, reference Laravel conventions

Elite code review expert specializing in modern AI-powered code

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality.

Refactors and cleans up codebases to improve readability and maintainability without altering functional behavior.

Use after an AI-built feature works but the code has duplicated mechanics, repeated API calls, or messy structure.