{"skill":{"slug":"deep-research-skill","displayName":"Deep Research","summary":"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...","tags":{"latest":"0.1.0"},"stats":{"comments":0,"downloads":445,"installsAllTime":2,"installsCurrent":2,"stars":1,"versions":1},"createdAt":1772248068670,"updatedAt":1777525457789},"latestVersion":{"version":"0.1.0","createdAt":1772248068670,"changelog":"deep-research-skill v0.1.0\n\n- Initial release of a multi-Agent workflow for in-depth research tasks, supporting automated goal decomposition and parallel execution using Claude Code's non-interactive mode.\n- Enforces a step-by-step process: goal clarification, parallel subgoal scheduling, data collection/aggregation, section-based refinement, and structured report delivery as files.\n- Prioritizes internet access through installed skills, then MCP (firecrawl > exa), with fallback to basic web fetch/search only if necessary.\n- Implements strict logging, permission control, and mandatory user confirmation before task execution.\n- Requires all outputs to be saved as files; does not post complete reports in chat.\n- Designed for reproducible, systematized research use cases such as web/material analysis, competitive/industry analysis, bulk retrieval, and long-form evidence-integrated writing.","license":null},"metadata":null,"owner":{"handle":"feiskyer","userId":"s174q6bx170bf0qb9wjqhqfv6x83vv3e","displayName":"Pengfei Ni","image":"https://avatars.githubusercontent.com/u/676637?v=4"},"moderation":null}