An automated tool for parsing, summarizing, and extracting structured intelligence from PDF and TXT research reports.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install report-processor
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install report-processor using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Report Processor?
The Report Processor is a robust utility designed to transform dense research documents into structured, actionable data. By utilizing local large language models, this skill specializes in identifying core viewpoints, quantitative data points, investment recommendations, and risk factors from complex documents. It is a vital component for developers and analysts looking to build a private knowledge base using Openclaw Skills without relying on external cloud processing.
Built for efficiency, it handles the heavy lifting of document parsing and semantic analysis, ensuring that critical information is never lost in a sea of text. Whether you are dealing with institutional PDF reports or simple TXT files, this tool provides a standardized output format suitable for integration into larger financial analysis pipelines.
Report Processor Use Cases
- Automating the extraction of investment recommendations from a library of PDF research reports.
- Building a local knowledge base of financial insights for private quantitative analysis.
- Summarizing long-form industry reports into structured JSON for database ingestion.
- Batch processing historical research data to identify recurring market risk factors.
How Report Processor Works
- The user points the processor to a single file or a directory containing research reports.
- The system uses poppler-utils to convert PDF content into a text-based format suitable for LLM processing.
- The extracted text is sent to a locally hosted qwen2.5:14b model via Ollama.
- The model identifies and categorizes key information including core arguments, data statistics, and risk assessments.
- The skill generates an automated summary and saves the structured result as a JSON file in the local workspace.
Report Processor Setup
To get started with this skill, ensure you have the necessary model and system utilities installed:
# Install the required LLM via Ollama
ollama pull qwen2.5:14b
# Install poppler for PDF support on macOS
brew install poppler
# Install poppler for PDF support on Linux
sudo apt install poppler-utils
Run the processor using the provided Python script:
# Process a specific report
python3 scripts/report_processor.py /path/to/report.pdf
Report Processor Data Schema & Taxonomy
The Report Processor saves structured data to ~/.openclaw/workspace/data/reports/. The output utilizes a clean JSON schema for easy programmatic access:
| Property | Description |
|---|---|
core_views |
The primary thesis and arguments of the researcher. |
data |
Quantitative figures, market stats, and financial metrics. |
investment_advice |
Specific buy, sell, or hold recommendations and price targets. |
risks |
Potential market or company-specific risks identified in the text. |
summary |
A concise, auto-generated overview of the entire report. |
Report Processor Advanced Features
- Multi-format Support: Seamlessly switches between PDF and TXT processing engines.
- Batch Processing: Optimized to handle entire directories of documents in a single execution loop.
- Custom Model Integration: Easily switch the OLLAMA_MODEL configuration to experiment with different LLMs within the Openclaw Skills framework.
- Automated Knowledge Ingestion: Directly populates the local workspace data directory for immediate use in RAG (Retrieval-Augmented Generation) workflows.
SKILL.md
Loading
Related Openclaw Skills
Zhouyi Bazi Classical Reference
A specialized knowledge retrieval and interpretation engine for traditional Chinese metaphysical classics like Bazi and Qimen Dunjia.
Playwright MCP Automation
A specialized skill for controlling real browser sessions via the Playwright MCP server to perform complex web interactions and UI automation.
EvoMap Auto Maintainer
A specialized automation tool designed to maintain 24/7 uptime for EvoMap nodes to maximize point earnings and passive rewards.
CRM Add Record
An automated browser skill that parses natural language input to create and save records in the Fractal CRM system.
GSData Qingbo Article Search
A powerful AI-driven article search tool utilizing the GSData Qingbo Open Platform to track public opinion and media trends across the web.
Image Generate
A streamlined utility for generating images from textual descriptions using specialized Python scripts and API integrations.
Featured*
