✓ Verified
🌐 Web Scrapers
✓ Enhanced Data
Research Report
Research technical projects/papers and generate comprehensive reports with PDF export.
- Rating
- 4.8 (365 reviews)
- Downloads
- 651 downloads
- Version
- 1.0.0
Overview
Research technical projects/papers and generate comprehensive reports with PDF export.
Complete Documentation
View Source →
Research Report Generator
Analyze technical projects/papers and produce comprehensive reports with PDF export.
Modes
Lite Mode (default)
- Literature search + paper analysis
- Code reading (local or remote)
- Multi-iteration report writing
- PDF generation via md2pdf skill
- No environment setup or experiment runs
Full Mode
- Everything in lite mode +
- Conda/virtualenv setup
- Dependency installation
- Experiment execution
- Result analysis
Usage
bash
bash {baseDir}/scripts/research-report.sh \
--topic "Spatial Forcing" \
--mode lite \
--iterations 3 \
--output both
Parameters
| Parameter | Default | Description |
|---|---|---|
| --topic | (required) | Paper/project name or arXiv ID |
| --mode | lite | lite or full |
| --iterations | 3 | Report revision iterations |
| --output | both | md, pdf, or both |
| --project-path | (auto) | Local code directory (optional) |
| --workspace | (current) | Workspace directory |
Workflow
Phase 1: Discovery
- Search arXiv + project pages
- Fetch related papers (citations + references)
- Identify key technologies and dependencies
Phase 2: Analysis
- Read source code (if
--project-pathprovided) - Analyze architecture from docs/code
- Map technology stack
Phase 3: Report Writing (× iterations)
- Draft outline
- Write sections iteratively
- Add diagrams (Mermaid/ASCII)
- Refine explanations
Phase 4: Export (Full mode only)
- Setup conda env
- Install dependencies
- Run experiments
- Append results to report
Phase 5: PDF Generation
- Call md2pdf skill
- Send to user via Telegram
Output Structure
text
<workspace>/
├── reports/
│ ├── <topic>_report_v1.md
│ ├── <topic>_report_v2.md
│ ├── <topic>_report_final.md
│ └── <topic>_report_final.pdf
├── memory/YYYY-MM-DD.md (appended)
└── logs/<topic>_research.log
Report Template
The generated report follows this structure:
- Executive Summary - 100-word overview
- Motivation - Problem statement + why it matters
- Background - Prerequisites explained intuitively
- Core Method - Technical details with analogies
- Code Analysis - Key files walkthrough
- Experiments - Setup + results (full mode)
- Troubleshooting - Common issues + fixes
- References - Papers + repos + docs
Dependencies
Required:
- pandoc (for PDF export)
- texlive-xetex (CJK + math support)
- conda/miniconda
- CUDA toolkit (if GPU experiments)
Integration
This skill automatically:
- Uses
md2pdfskill for PDF conversion - Appends to
memory/YYYY-MM-DD.md - Creates structured report directory
Examples
Lite mode, 5 iterations:
bash
research-report --topic "VGGT" --iterations 5 --mode lite
Full mode with local code:
bash
research-report --topic "Spatial Forcing" \
--project-path ~/Spatial-Forcing/openvla-SF \
--mode full \
--iterations 3
PDF only output:
bash
research-report --topic "OpenVLA" --output pdf
Troubleshooting
| Issue | Fix |
|---|---|
| PDF generation fails | Check pandoc --version, install texlive-xetex |
| CJK characters missing | Install fonts-noto-cjk, verify with fc-list :lang=zh |
| Math formulas not rendered | Ensure markdown uses $...$ / $$...$$ syntax |
| Full mode conda fails | Run conda update -n base conda first |
Installation
Terminal bash
openclaw install research-report
Copied!
💻Code Examples
--output both
---output-both.txt
## Parameters
| Parameter | Default | Description |
|-----------|---------|-------------|
| `--topic` | (required) | Paper/project name or arXiv ID |
| `--mode` | `lite` | `lite` or `full` |
| `--iterations` | `3` | Report revision iterations |
| `--output` | `both` | `md`, `pdf`, or `both` |
| `--project-path` | (auto) | Local code directory (optional) |
| `--workspace` | (current) | Workspace directory |
## Workflow
### Phase 1: Discovery
1. Search arXiv + project pages
2. Fetch related papers (citations + references)
3. Identify key technologies and dependencies
### Phase 2: Analysis
1. Read source code (if `--project-path` provided)
2. Analyze architecture from docs/code
3. Map technology stack
### Phase 3: Report Writing (× iterations)
1. Draft outline
2. Write sections iteratively
3. Add diagrams (Mermaid/ASCII)
4. Refine explanations
### Phase 4: Export (Full mode only)
1. Setup conda env
2. Install dependencies
3. Run experiments
4. Append results to report
### Phase 5: PDF Generation
1. Call md2pdf skill
2. Send to user via Telegram
## Output Structure└── logs/<topic>_research.log
-logstopicresearchlog.txt
## Report Template
The generated report follows this structure:
1. **Executive Summary** - 100-word overview
2. **Motivation** - Problem statement + why it matters
3. **Background** - Prerequisites explained intuitively
4. **Core Method** - Technical details with analogies
5. **Code Analysis** - Key files walkthrough
6. **Experiments** - Setup + results (full mode)
7. **Troubleshooting** - Common issues + fixes
8. **References** - Papers + repos + docs
## Dependencies
**Required:**
- pandoc (for PDF export)
- texlive-xetex (CJK + math support)
**Full mode only:**
- conda/miniconda
- CUDA toolkit (if GPU experiments)
## Integration
This skill automatically:
- Uses `md2pdf` skill for PDF conversion
- Appends to `memory/YYYY-MM-DD.md`
- Creates structured report directory
## Examples
**Lite mode, 5 iterations:**example.sh
bash {baseDir}/scripts/research-report.sh \
--topic "Spatial Forcing" \
--mode lite \
--iterations 3 \
--output bothexample.txt
<workspace>/
├── reports/
│ ├── <topic>_report_v1.md
│ ├── <topic>_report_v2.md
│ ├── <topic>_report_final.md
│ └── <topic>_report_final.pdf
├── memory/YYYY-MM-DD.md (appended)
└── logs/<topic>_research.logexample.sh
research-report --topic "Spatial Forcing" \
--project-path ~/Spatial-Forcing/openvla-SF \
--mode full \
--iterations 3Tags
#search_and-research
Quick Info
Category Web Scrapers
Model Claude 3.5
Complexity One-Click
Author huaruoji
Last Updated 3/10/2026
🚀
Optimized for
Claude 3.5
Ready to Install?
Get started with this skill in seconds
openclaw install research-report
Related Skills
✓ Verified
💻 Development
4claw
4claw — a moderated imageboard for AI agents.
🧠 Claude-Ready
)}
★ 4.4 (118)
↓ 4,990
v1.0.0
✓ Verified
💻 Development
Aap Passport
Agent Attestation Protocol - The Reverse Turing Test.
🧠 Claude-Ready
)}
★ 4.3 (89)
↓ 4,621
v1.0.0
✓ Verified
💻 Development
Adaptive Suite
A continuously adaptive skill suite that empowers Clawdbot.
🧠 Claude-Ready
)}
★ 4.7 (88)
↓ 1,625
v1.0.0
✓ Verified
💻 Development
Adversarial Prompting
Adversarial analysis to critique, fix.
🧠 Claude-Ready
)}
★ 4.6 (372)
↓ 28,222
v1.0.0