行動開發

Your approach to handling testing sybil. Use this skill when working on files where testing sybil comes into play.

Build cross-platform mobile apps with React Native.

Convert subtitle files (WebVTT .vtt and SubRip .srt) into clean, readable text documents with multi-language support (English, Traditional Chinese, Simplified Chinese). Auto-detects format and language, removes timestamps and formatting, merges captions into natural paragraphs, strips annotations, and fixes spacing appropriately for each language. Use when the user provides a subtitle file or asks to convert captions to text.

Guide for managing and optimizing context in Claude Code. Use when experiencing slow responses, context warnings, or planning large tasks. Covers /compact, /clear, context budgeting, subagent delegation, and efficient session workflows.

Apply systematic debugging methodology. Use when investigating bugs, unexpected behavior, or when user reports issues. Auto-apply when conversation includes "bug", "broken", "not working", "wrong", "glitch", "flickering".

Use when debugging web applications or automating browser tasks. Leverage Chrome DevTools MCP for inspection, performance analysis, and automated testing.

Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.

Manages, consolidates, and optimizes project documentation following research-backed docs-as-code principles. Use this skill when documentation becomes scattered, duplicated, or contradictory after development work. Also use when user explicitly requests "tidy docs", "consolidate documentation", "clean up docs", or "organize documentation". Applies Diátaxis framework, enforces YAML front matter, resolves conflicts using evidence-based rules, and generates machine-readable manifest for AI agents. NEVER modifies CLAUDE.md.

Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).

Enterprise SSRF Security Protection with AI-powered request validation, Context7 integration, and intelligent URL filtering for web application security

Security best practices for Go applications. Use when writing security-sensitive code.

Start the iPhone screen capture app to mirror a connected iPhone's screen on macOS. Use when the user wants to view their iPhone screen, mirror their device, or start screen capture.

Use when you need SVGs with selectable/customisable appearance: multiple palettes (WLILO / Obsidian / light), consistent typography, and repeatable agent-friendly pipelines. Triggers: svg theme, tokens, palette, WLILO, obsidian, design system, dark mode, diagram styling.

Official Anthropic SDK for Claude AI with chat, streaming, function calling, and vision capabilities. Use when integrating Claude AI into applications, implementing AI-powered features, using tool use patterns, or processing images with vision models.

Analyze LangGraph application architecture, identify bottlenecks, and propose multiple improvement strategies

Generate behavioral unit tests from functional specifications using PreDB/PostDB pattern. Use when user provides specs with PreDB/Workflow/PostDB structure or asks to write tests for a specification before implementation (TDD approach).

Use when designing animations for shopping apps, product catalogs, checkout flows, or retail experiences

Autonomous multi-agent code evolution system for optimization problems. Use when solving complex optimization problems (packing, geometry, scheduling, search) through evolutionary approaches with multiple independent AI agents. Multi-start hybrid heuristic+SLSQP methods significantly outperform single approaches. Triggers include genetic algorithms, evolutionary optimization, multi-agent problem solving, parameter tuning at scale, AlphaEvolve-style research, or evolving code solutions across generations.

Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or automating code vulnerability detection.

Perform a repo-wide, evidence-based audit of documentation against the current codebase and recent changes. Produces a proposed, fully rewritten documentation set in TempDoc-ForUserReview and asks for approval before any changes are applied to the existing docs.