Claude Code settings, commands, agent and skills (all in one)
深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（`claude -p`）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付"成品报告文件路径 + 关键结论/建议摘要"。用于：系统性网页/资料调研、竞品/行业分析、批量链接/数据集分片检索、长文写作与证据整合，或用户提及"深度调研/Deep Research/Wide Research/多 Agent 并行调研/多进程调研"等场景。
GitHub Spec-Kit integration for constitution-based spec-driven development (7-phase workflow)
Leverage OpenAI Codex (GPT-5/GPT-5.1) for non-interactive automation mode and hands-off task execution
Interactive feature development workflow from idea to implementation (Requirements → Design → Tasks → Execute)
Extract subtitles/transcripts from YouTube videos via CLI or browser automation
Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Claude Code headless mode with auto-continuation. Trigger phrases: autonomous, long-running task, multi-session, 自主执行, 长时任务, autonomous skill.
No verified skills in this plugin.
Generate or edit images using Google Gemini API via nanobanana
No verified skills in this plugin.