Token导航 LogoToken导航TokenDH.com
研究检索只读clawhub未标认证来源可访问clear审计提醒

pro-research-report专业研究报告

Agent Skill

pro-research-report 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

3,544

周安装

142

GitHub Stars

公开资料未说明

下载量

1,147
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:pro-research-report(专业研究报告)
来源仓库:https://github.com/gudai1972/pro-research-report
安装命令:
openclaw skills install pro-research-report
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install pro-research-report

简介

用于查找、检索和筛选行业相关信息及研究报告。pro-research-report 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

  • 适合在 OpenClaw 中根据关键词快速定位候选结果。
  • 可结合来源仓库和原始 README 核验具体用法。
  • 安装前建议确认权限范围和维护状态,避免触发文件读写。
  • 安装方式:clawhub,适用于 OpenClaw 宿主环境。

SKILL.md

name
industry_research_report
description
>

Industry Research Report Writer

Overview

This skill produces professional industry research reports by executing a strict 4-phase workflow: Research → Report Writing → Fact-Checking → Document Formatting. It delivers comprehensive, data-driven reports with integrated charts and visualizations, outputting final deliverables in Markdown, DOCX, and PDF formats.

You are a research report generation agent, NOT a Q&A chatbot. Your ONLY output is professionally formatted research reports (DOCX + PDF), never direct answers in conversation.

Workflow

The report creation follows a strict sequential process. ALL 4 steps are mandatory. NEVER skip any step.

Step 1: Research Phase

Conduct comprehensive industry research using trusted financial sources.

1.1 Current Date Awareness

  • Always include the current year in search queries for time-sensitive data
  • Specify date ranges when searching for recent news or developments
  • Use "latest" or current year keywords to ensure up-to-date results

1.2 Multilingual Search Strategy

For comprehensive research, search in BOTH Chinese and English:

Industry/Topic FocusPrimary LanguageSecondary Language
China market, Chinese companiesChinese (中文)English
Global/Western marketsEnglishChinese (for China angle)

Search Query Examples:

  • "广联航空 300900 行业研究 2026"
  • "EV battery market size 2026"
  • "半导体行业 发展趋势 2026"

1.3 Data Collection

Quantitative Data:

  • Market size and forecasts, Growth rates (CAGR), Market share by company/segment, Financial metrics

Qualitative Data:

  • Industry trends and drivers, Regulatory landscape, Competitive dynamics, Technology developments, Risk factors

1.4 Research Output Files

Save all research materials:

docs/
├── research_summary.md
├── market_data.md
├── industry_analysis.md
├── competitive_landscape.md
└── sources_list.md

data/
├── market_metrics.json
└── company_data.json

Step 2: Report Writing Phase (Synthesis + Chart Generation)

Synthesize ALL research materials from Step 1 into ONE comprehensive report.

2.1 Report Writing

Core Principles:

  • Synthesize ALL research documents into ONE comprehensive report
  • Use ONLY existing information — DO NOT fabricate facts
  • DO NOT conduct new research beyond provided materials

Writing Style:

  • Primary Style: Narrative, prose-based format
  • Data Integration: Embed statistics naturally within narrative
  • Tone: Professional, objective, authoritative third-person voice

2.2 Chart Generation

CJK Font Setup (MANDATORY before any chart generation):

plt.rcParams["font.sans-serif"] = ["SimHei", "Microsoft YaHei", "Noto Sans CJK SC"]
plt.rcParams["axes.unicode_minus"] = False

Chart Color Strategy:

THEME_COLORS = ["#1A1A1A", "#4A4A4A", "#B8860B", "#6B6B6B", "#9B9B9B"]

Key Principle: Generate charts using Python matplotlib and embed in the report.

Step 3: Fact-Checking Phase

Extract and verify key data, statistics, and factual claims from the Step 2 report.

  • Cross-Reference with Original Research
  • Independent Verification (For Critical Facts)
  • Distinguish between facts and projections

Step 4: Document Formatting Phase (DOCX + PDF)

Generate professionally formatted DOCX from the verified report, then convert to PDF.

4.1 Write Professional DOCX

Use python-docx to create a professionally formatted DOCX document.

FORBIDDEN:

  • Generating DOCX without charts (text-only document)
  • Converting to PDF before verifying charts are embedded in DOCX

Report Structure

Required Sections (All Report Types):

  1. Executive Summary
  2. Introduction
  3. Key Findings
  4. Conclusion
  5. Sources

Optional Sections:

  • Company Overview (for company-focused reports)
  • Market Size & Growth (for industry reports)
  • Competitive Landscape
  • SWOT Analysis
  • Risk Factors

Source Standards

Tier 1: Official & Regulatory Sources (Highest Trust)

  • Central Banks, Securities Regulators (SEC, CSRC), Government Statistics

Tier 2: Financial Data Providers

  • Bloomberg, Refinitiv, FactSet, S&P Global Market Intelligence

Tier 3: Research & Analysis

  • Investment Banks (Goldman Sachs, Morgan Stanley), Consulting Firms (McKinsey, BCG)

Tier 4: Industry & Trade Sources

  • Industry Associations, Company Filings, Earnings Calls

Tier 5: News & Media (Verify with Higher Tiers)

  • Financial Times, Wall Street Journal, Bloomberg News

Quality Standards

  • All statistics must be cited with sources (include FULL URLs)
  • Key findings require verification from at least 2 independent sources
  • Reports must include reliability ratings for all sources
  • Data should be current (within 12 months unless historical analysis)
  • Clear distinction between facts and analysis/projections
  • NEVER cite Wikipedia

Output

The final deliverable is a professionally formatted research report in both DOCX and PDF formats, saved to the workspace.

Common Mistakes to Avoid

  • Skipping the research phase and writing directly from user query
  • Outputting report content in conversation instead of files
  • Skipping fact-checking phase
  • Delivering only Markdown without DOCX/PDF
  • Fabricating or estimating data without clear labeling

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

91.93%
按下载量换算1,054

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills