ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 3/5

research-report

Research technical projects/papers and generate comprehensive reports with PDF export. Modes: lite (analysis + writing) or full (+ environment setup + experiments). Params: iterations, mode, project-path, output. Use for paper analysis, code review, technical reports, research documentation.

Why use this skill?

Use the research-report AI agent to automatically analyze papers, review source code, run experiments, and generate professional PDF technical documentation.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/huaruoji/research-report
Or

What This Skill Does

The research-report skill is an advanced automation agent designed for deep-dive technical research. It acts as an autonomous assistant capable of performing comprehensive literature reviews, analyzing source code, and synthesizing complex information into structured, professional-grade technical documents. Whether you are exploring a new research paper or evaluating a technical project's viability, this agent handles the heavy lifting—from data gathering to documentation.

It features two primary operational modes. The 'Lite' mode focuses on informational synthesis, including multi-iteration draft refinement and PDF exportation. The 'Full' mode expands this capability by automatically preparing a computational environment, managing dependencies, and executing experimental code to validate results empirically, documenting everything from setup to output.

Installation

To install this skill in your OpenClaw environment, run the following command in your terminal: clawhub install openclaw/skills/skills/huaruoji/research-report

Ensure your system has the required dependencies, specifically pandoc and texlive-xetex, installed to support the automated PDF rendering feature. If you intend to use 'Full' mode, verify that conda or miniconda is properly configured in your path.

Use Cases

  • Academic Research: Rapidly summarize arXiv papers, visualize citation networks, and generate formal reviews.
  • Technical Due Diligence: Perform code audits on GitHub repositories to assess architectural patterns and dependency health.
  • Documentation Generation: Automatically create internal project documentation or knowledge-base articles from existing codebases.
  • Reproducibility Testing: Use Full mode to verify the claims made in research papers by running provided scripts and capturing empirical data.

Example Prompts

  1. "Research the paper 'Attention Is All You Need', generate a 5-iteration deep-dive report, and output a PDF summary."
  2. "Perform a code review on the project located at ~/repos/stable-diffusion, analyze the architecture, and document your findings in a report."
  3. "Conduct a full research report on the 'Temporal Fusion Transformer' project, including environment setup and empirical performance testing."

Tips & Limitations

  • Iterations: Increasing the iteration count improves the quality and depth of the refinement process but will consume more AI inference tokens.
  • Environment Isolation: Always use a clean environment for 'Full' mode to prevent dependency conflicts with your host system.
  • PDF Constraints: PDF generation relies on LaTeX; ensure system fonts and math packages are up-to-date to avoid compilation errors.
  • Scope: While the agent is highly autonomous, code analysis is most effective when the project structure adheres to standard documentation practices.

Metadata

Author@huaruoji
Stars2387
Views0
Updated2026-03-09
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-huaruoji-research-report": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#research#documentation#code-analysis#technical-writing#pdf-generation
Safety Score: 3/5

Flags: file-write, file-read, code-execution, network-access