Code Review & Quality

Use when creating a PR description. Triggers include "PR 작성", "PR description", "make PR", "PR 만들어", "풀리퀘", "pull request 작성".

Use when asked to analyze architecture, debug issues, identify root cause, or provide technical recommendations. Triggers include "analyze", "diagnose", "debug", "root cause", "what's wrong", "architecture review", "investigate", "아키텍처 분석", "디버깅", "원인 분석", "뭐가 문제", "조사해".

Use when reviewing code changes for quality, correctness, and production readiness before merge

Use when facing trade-offs, subjective judgments, uncertain decisions, or when diverse viewpoints would improve judgment quality. Triggers include "council", "다른 의견", "perspectives", "what do others think".

Guide for continuous improvement, error proofing, and standardization. Use this skill when the user wants to improve code quality, refactor, or discuss process improvements.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Detect unnecessary complexity, speculative generality, and over-engineered solutions in code

Run comprehensive code review before commits, PRs, or releases. Uses code-reviewer agent with tiered security, performance, and quality checks.

Deep codebase analysis using codebase-analyst agent for patterns, architecture, and implementation details

Improve and optimize prompts using Anthropic's 4-step prompt improvement workflow

Audit Claude Code subagents for quality, compliance, and maintainability. Use after creating or modifying agents, before releases, or for periodic quality checks.

MoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (plan, run, sync, fix, loop, project, feedback) to specialized agents. Use for any development task from planning to deployment.

MoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (plan, run, sync, fix, loop, project, feedback) to specialized agents. Use for any development task from planning to deployment.

Persistent personality for AI agents — define, evolve, and share your soul

Metacognitive pre-execution analysis — teaches the agent to see what ISN'T there before acting on what IS. Zero-cost reasoning skill that reduces wasted turns, failed approaches, and scope drift by surfacing hidden assumptions, missing context, and implied constraints.

"Adds a machine-readable intent layer to OpenClaw agents. Creates

Deterministic rule-based system for classifying clarified input into a single primary task category and assigning execution complexity. Use when the Main Agent needs to categorize user requests before task decomposition, route tasks to appropriate handlers, assess complexity and risk levels, or determine if clarification is needed. Triggers after clarification is complete and before decomposition begins.

Use for AI music generation via IMA Open API. Supports text_to_music with 3 models. IMPORTANT — Default model selection rule: always recommend the NEWEST and most POPULAR model, NOT the cheapest. Default: Suno (model_id=sonic, model_version=sonic-v5, 25pts) — latest engine, full-featured with custom mode, lyrics, vocal gender, style tags. Alternative: DouBao BGM (model=GenBGM, 30pts) for background music; DouBao Song (model=GenSong, 30pts) for songs. Use Suno sonic by default unless user asks...

Use for AI image generation via IMA Open API. Supports text-to-image and image-to-image. IMPORTANT — Default model selection rule: always recommend the NEWEST and most POPULAR model, NOT the cheapest. Default for text_to_image: SeeDream 4.5 (doubao-seedream-4.5, 5pts) — latest doubao flagship, balanced choice. Budget option: Nano Banana2 (gemini-3.1-flash-image, 4pts) — fastest and cheapest. Premium: Nano Banana Pro (gemini-3-pro-image, 10-18pts) — premium quality with size options (1K/2K/4K)...

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.

Complete mastery guide for smart contract security auditing — from first principles of EVM bytecode to advanced exploit patterns. Covers manual code review methodology, automated tooling (Slither, Mythril, Foundry fuzz), common vulnerability taxonomy (reentrancy, flash-loan attacks, oracle manipulation, access control, integer math), audit report writing, severity classification (Critical/High/Medium/Low/Informational), gas optimization reviews, upgrade safety, and DeFi-specific audit checkli...

Analyze DAO governance structures, proposals, voting patterns, and power distribution to assess governance health and participation quality.

Systematically reproduces, locates, and diagnoses frontend bugs using steps, hypotheses, DevTools, and minimal repro. Use when 排查bug, bug定位, 调试, debugging, 复现问题, or investigating frontend issues.