Claude Skills

Systematic code refactoring while preserving all external behavior. Use when identifying code smells, planning refactoring sequences, executing safe structural improvements, or validating behavior preservation. Includes code smell catalog (reference.md) and refactoring execution protocol.

Coordinate multi-agent code review with specialized perspectives. Use when conducting code reviews, analyzing PRs, evaluating staged changes, or reviewing specific files. Handles security, performance, quality, and test coverage analysis with confidence scoring and actionable recommendations.

Create and validate project constitutions through discovery-based rule generation. Use when creating governance rules, validating code against constitutional rules, or checking constitution compliance during implementation and review.

Generate structured agent prompts with FOCUS/EXCLUDE templates for task delegation. Use when breaking down complex tasks, launching parallel specialists, coordinating multiple agents, creating agent instructions, determining execution strategy, or preventing file path collisions. Handles task decomposition, parallel vs sequential logic, scope validation, and retry strategies.

Discover patterns, rules, and interfaces through iterative analysis cycles. Use when analyzing business rules, technical patterns, security, performance, integration points, or domain-specific areas. Includes cycle pattern for discovery to documentation to review workflow.

Apply scientific debugging methodology through conversational investigation. Use when investigating bugs, forming hypotheses, tracing error causes, performing root cause analysis, or systematically diagnosing issues. Includes progressive disclosure patterns, observable actions principle, and user-controlled dialogue flow.

Initialize and manage specification directories with auto-incrementing IDs. Use when creating new specs, checking spec status, tracking user decisions, or managing the docs/specs/ directory structure. Maintains README.md in each spec to record decisions (e.g., PRD skipped), context, and progress. Orchestrates the specification workflow across PRD, SDD, and PLAN phases.

Manage git operations for spec-driven development. Use when creating branches for specs/features, generating commits, or creating PRs. Provides consistent git workflow across specify, implement, and refactor commands. Handles branch naming, commit messages, and PR descriptions based on spec context.

Implements NewebPay MPG checkout integration including AES256 encryption, form submission, and payment callback handling. Use when integrating payment gateway, creating checkout flows, or building 藍新金流 payment pages.

Implements NewebPay refund functionality for credit cards and e-wallets. Use when building refund processing, transaction cancellation, or return payment features for 藍新金流.

Implements NewebPay transaction query functionality using QueryTradeInfo API. Use when building order status checking, transaction verification, or payment confirmation features for 藍新金流.

Analyzes user requirements and recommends the best Taiwan payment gateway. Provides comparison between NewebPay, ECPay, and PAYUNi based on specific needs. Use when choosing a payment solution or comparing 金流服務.

Provides NewebPay integration overview and guides users to the appropriate skill. Use when starting NewebPay integration, setting up environment, or needing general guidance about 藍新金流.

Provides PAYUNi (統一金流) integration guide including payment gateway setup and API configuration. Use when integrating PAYUNi payment services or unified payment solutions.

Provides ECPay (綠界科技) integration guide including payment setup and electronic invoice integration. Use when integrating ECPay payment gateway or e-invoice features.

Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.

This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Guides discovery of local skills and enforces minimal documentation style.

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.