Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Research technical projects/papers and generate comprehensive reports with PDF export. Modes: lite (analysis + writing) or full (+ environment setup + experi...
Research technical projects/papers and generate comprehensive reports with PDF export. Modes: lite (analysis + writing) or full (+ environment setup + experi...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Analyze technical projects/papers and produce comprehensive reports with PDF export.
Literature search + paper analysis Code reading (local or remote) Multi-iteration report writing PDF generation via md2pdf skill No environment setup or experiment runs
Everything in lite mode + Conda/virtualenv setup Dependency installation Experiment execution Result analysis
bash {baseDir}/scripts/research-report.sh \ --topic "Spatial Forcing" \ --mode lite \ --iterations 3 \ --output both
ParameterDefaultDescription--topic(required)Paper/project name or arXiv ID--modelitelite or full--iterations3Report revision iterations--outputbothmd, pdf, or both--project-path(auto)Local code directory (optional)--workspace(current)Workspace directory
Search arXiv + project pages Fetch related papers (citations + references) Identify key technologies and dependencies
Read source code (if --project-path provided) Analyze architecture from docs/code Map technology stack
Draft outline Write sections iteratively Add diagrams (Mermaid/ASCII) Refine explanations
Setup conda env Install dependencies Run experiments Append results to report
Call md2pdf skill Send to user via Telegram
<workspace>/ โโโ reports/ โ โโโ <topic>_report_v1.md โ โโโ <topic>_report_v2.md โ โโโ <topic>_report_final.md โ โโโ <topic>_report_final.pdf โโโ memory/YYYY-MM-DD.md (appended) โโโ logs/<topic>_research.log
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
Required: pandoc (for PDF export) texlive-xetex (CJK + math support) Full mode only: conda/miniconda CUDA toolkit (if GPU experiments)
This skill automatically: Uses md2pdf skill for PDF conversion Appends to memory/YYYY-MM-DD.md Creates structured report directory
Lite mode, 5 iterations: research-report --topic "VGGT" --iterations 5 --mode lite Full mode with local code: research-report --topic "Spatial Forcing" \ --project-path ~/Spatial-Forcing/openvla-SF \ --mode full \ --iterations 3 PDF only output: research-report --topic "OpenVLA" --output pdf
IssueFixPDF generation failsCheck pandoc --version, install texlive-xetexCJK characters missingInstall fonts-noto-cjk, verify with fc-list :lang=zhMath formulas not renderedEnsure markdown uses $...$ / $$...$$ syntaxFull mode conda failsRun conda update -n base conda first
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.