← Back to Skills Marketplace

Deep Research Report

Name: Deep Research Report
Author: hayashishungenn

by hayashishungenn · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ Security Clean

133

Downloads

Stars

Active Installs

Versions

Install in OpenClaw

/install deep-research-report

Description

根据用户提供的研究材料，生成结构完整、逻辑严密、观点清晰的正式深度研究报告，适用行业、公司、策略与政策分析。

README (SKILL.md)

deep-research-report - 深度研究报告生成技能

技能描述

将用户提供的研究材料整合为一篇结构完整、逻辑严密、观点清晰的正式研究报告。适用于行业分析、公司研究、政策解读、市场策略等场景。

触发条件

当用户消息中包含以下关键词时自动触发：

深度研究
深度分析
研究报告
行业报告
生成报告

输入要求

用户提供：

研究材料（可以是多段文字、数据、观点等）
可选：指定报告类型（行业/公司/策略/政策）
可选：指定重点关注方向

输出格式

生成正式研究报告，结构如下：

标题
副标题
摘要（300-500 字）
一、研究背景
二、核心问题与分析框架
三、现状与关键事实
四、深层驱动逻辑
五、主要矛盾与争议点
六、未来趋势与情景推演
七、风险因素与反证条件
八、结论与建议

写作要求

提炼核心：从材料中提炼出核心矛盾、关键趋势和主要结论
信息整合：对重复信息进行合并，对冲突信息进行甄别
区分层级：区分"事实"、"推论"、"判断"
逻辑链条：将零散信息组织成清晰的分析逻辑链（背景→现状→驱动因素→瓶颈/风险→未来演化→结论）
解释原因：重要观点都要解释"为什么"
综合判断：不能只复述材料，要体现研究员视角的综合判断

特别要求

每一部分都要有"分析"，不是只有信息罗列
在结论部分，明确写出：
1. 最高确定性的结论（标注置信度）
2. 最值得跟踪的变化变量
3. 最容易出现误判的点
风格要像专业券商/咨询/产业研究报告
如果材料不够支撑某个结论，请明确标注"证据不足"

使用示例

示例 1：行业研究

用户输入：

深度研究：AI 算力产业链

材料：
一、光模块上游・极小器件（隐形刚需）
1. 光隔离器
作用：保护高速光模块激光器，防止回波干扰，1.6T/3.2T 必备。
...

输出：完整行业研究报告

示例 2：公司分析

用户输入：

深度分析：某公司投资价值

材料：
财务数据、业务介绍、竞争优势...

输出：公司深度研究报告

报告保存路径

报告自动保存到：Obsidian-Vault/10_投资金融/12_行业研究/ 文件名格式：YYYY-MM-DD_报告标题.md

依赖技能

无

版本历史

v1.0 (2026-04-05): 初始版本，支持深度研究报告生成

Usage Guidance

This skill appears coherent and limited in scope, but consider: 1) It will automatically trigger on messages containing the listed keywords and will save generated reports to /root/.openclaw/workspace/Obsidian-Vault/10_投资金融/12_行业研究/ (check that this path is appropriate and that sensitive material is acceptable to be written there). 2) If you want to avoid automatic saves, edit SKILL.md or the script to require explicit confirmation before writing files. 3) Review the bundled generate_report.py if you need different naming, location, or to remove the default '内部参考' confidentiality label. 4) No network calls or credentials are used by the skill as provided.

Capability Analysis

Type: OpenClaw Skill Name: deep-research-report Version: 1.0.0 The skill bundle is a legitimate tool for generating structured research reports from user-provided text. The Python script `generate_report.py` performs basic text analysis using regular expressions and saves the output to a local workspace directory. There are no signs of data exfiltration, malicious execution, or harmful prompt injections in `SKILL.md` or the code logic.

Capability Assessment

✓ Purpose & Capability

Name/description (深度研究报告) align with the included code and SKILL.md: both generate structured research reports from user-provided materials and save them to an Obsidian vault. There are no unrelated env vars, binaries, or external services required.

ℹ Instruction Scope

SKILL.md instructs automated triggering on specific Chinese keywords and specifies automatic saving to an Obsidian path. The included Python implements report generation and writes to a local workspace. This stays within the stated purpose, but the auto-trigger behavior and automatic file write are notable (may run/save without an explicit 'save' confirmation).

✓ Install Mechanism

No install spec and no external downloads; the skill is instruction-only with a benign bundled script. Nothing is written to system locations beyond the skill's workspace path.

✓ Credentials

No environment variables, credentials, or external config paths are requested. The code writes to a local path under the agent workspace but does not access secrets or other system configs.

✓ Persistence & Privilege

always:false and normal model invocation settings. The skill can be invoked automatically based on keyword triggers (as declared); it does not request permanent system-wide privileges or modify other skills' configs.

How to Use

Make sure OpenClaw is installed (local or Docker)
Run the install command in chat: /install deep-research-report
After installation, invoke the skill by name or use /deep-research-report
Provide required inputs per the skill's parameter spec and get structured output

Version History

v1.0.0

deep-research-report v1.0.0 - Initial release: Generates comprehensive, logically-structured research reports from user-provided materials. - Supports topics such as industry analysis, company research, policy review, and market strategy. - Output follows a standardized report structure, including sections: background, core issues, trends, risks, and conclusions. - Automatically extracts and synthesizes core points, differentiates facts from judgments, and requires analyst-level insights. - Ensures each section includes analysis (not just summaries) and clearly highlights key conclusions, trackable variables, and uncertainties. - Reports are saved automatically to a dedicated folder with a standardized file naming format.

Metadata

Slug deep-research-report

Version 1.0.0

License MIT-0

All-time Installs 1

Active Installs 1

Total Versions 1

Frequently Asked Questions

What is Deep Research Report?

根据用户提供的研究材料，生成结构完整、逻辑严密、观点清晰的正式深度研究报告，适用行业、公司、策略与政策分析。 It is an AI Agent Skill for Claude Code / OpenClaw, with 133 downloads so far.

How do I install Deep Research Report?

Run "/install deep-research-report" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Deep Research Report free?

Yes, Deep Research Report is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Deep Research Report support?

Deep Research Report is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Deep Research Report?

It is built and maintained by hayashishungenn (@hayashishungenn); the current version is v1.0.0.

More Skills