Individual skill

deep-research

Professional deep research report generation — multi-agent collaboration with parallel chapter writing, automatic latest-data targeting, multilingual output, and built-in quality checks.

deep-research/SKILL.md

Read pinned source

Source commit 91108cf5c608edd1f00a8c5ac635f16504e08a35

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 10, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 514
Repository last updated: Nov 8, 2026
License: Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

claude-code Repository topic
codex Repository topic
cursor Repository topic
skills Repository topic
agent-skills Repository topic
agents-md Repository topic
ai-agents Repository topic
claude-code-skills Repository topic
codex-skills Repository topic
coding-agents Repository topic
writing Derived category
data Derived category
research Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

LICENSEasset · 1,064 bytes
RULES.mddoc · 7,074 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
SKILL.mdcore · 35,513 bytes
TYPES.mddoc · 4,979 bytes
VERSIONasset · 6 bytes
command/research.mddoc · 751 bytes
command/update.mddoc · 1,425 bytes
profiles.jsonasset · 344 bytes
prompts/task1_outline.mddoc · 8,971 bytes
prompts/task2_data_collection.mddoc · 29,545 bytes
prompts/task3_chapter_agent.mddoc · 3,932 bytes
prompts/task4_assembly.mddoc · 6,367 bytes
reports-browser/favicon.svgasset · 241 bytes
reports-browser/html-docx.min.jsruns · 416,073 bytes
reports-browser/html2pdf.bundle.min.jsruns · 905,956 bytes
reports-browser/index.htmlasset · 19,546 bytes
reports-browser/marked.min.jsruns · 52,864 bytes
reports-browser/reports.jsonasset · 2 bytes
scrapling-mcp-server.pyruns · 6,785 bytes
sources.jsonasset · 7,717 bytes
tools/dr_check.pyruns · 21,747 bytes
tools/dr_gen.pyruns · 37,707 bytes
tools/dr_tools.pyruns · 17,579 bytes
tools/generate_pages.pyruns · 29,033 bytes
tools/lang_config.pyruns · 24,632 bytes

Read excerpt



# deep-research

生成对标券商/第三方研究机构标准的深度调研报告。

- **架构**：主 agent 调度 4 个子 agent Task（大纲/数据/预检/装配）+ 1 轮主控并行派发章节，中间数据走临时文件
- **数据源**：在线模式 → 工具内置引擎（Layer 0，如有）+ 大纲建议源定向搜索（Layer 1） + sources.json 优质源搜索（Layer 2）并行 → 按质量触发免费源补强（Layer 3 兜底）→ Scrapling 批量抓取；离线模式 → 用户指定的本地文件（md/txt/pdf/docx）
- **安装**：见下方「安装与配置」
- **输出**：`$TMPDIR/outline.json`（临时，非最终报告）
- **最终报告**：保存到 skill 目录下的 `reports/`
- **参考文件**：`RULES.md`（硬约束/反模式）、`TYPES.md`（分类标准/编号规范）、**`profiles.json`（三档模式参数，修改后重启软件即全局生效）**
- **容错原则**：调研不阻塞。所有脚本/命令调用必须有兜底路径。主路径失败 → 自动尝试替代方案（换 `sys.executable`/检查路径/直接 Python 实现）→ 三次失败后向用户报告具体问题。详见「容错原则」。

---