ReddRadar
Agent skill
papi-compare
Compare papers for a decision. Use when user asks "which paper should I use", "compare approaches", or needs to choose between methods/algorithms.
Install this agent skill to your Project
npx add-skill https://github.com/hummat/paperpipe/tree/main/skills/papi-compare
SKILL.md
Compare Papers for Decision
You are given paper excerpts (paste papi show ... --level ... output above, or reference exported files).
Project context (optional): $ARGUMENTS
Task
Compare the papers for a decision in this project context.
Axes: objective, assumptions/data regime, compute, latency, robustness, eval metrics, reproducibility, implementation risk.
Output
- Decision matrix (table)
- Recommended choice + assumptions + risks
- Missing evidence / what to fetch next (e.g., ask for
papi show <paper> --level tex)
Citations
For each non-trivial claim, include a short quote snippet (<= 15 words) and cite as: (paper: , arXiv: , source: summary|equations|tex|notes, ref: section/eq/table/figure if present)
End with: Cited papers: <comma-separated paper names and/or arXiv IDs>
For general CLI commands, see /papi.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
hummat/paperpipe
papi-init
Setup paperpipe agent integration. Use when user wants to add papi to a project's CLAUDE.md/AGENTS.md or initialize paper support.
hummat/paperpipe
papi-ask
Query papers using RAG (PaperQA2 or LEANN). Use when user needs synthesized answers from papers, asks "what does paper X say about Y", or needs cited responses.
hummat/paperpipe
papi-curate
Create project notes from papers. Use when user wants to document paper findings, create implementation notes, or summarize papers for a project.
hummat/paperpipe
papi
This skill should be used when the user wants to interact with their paper database — listing papers, searching content, showing paper details, adding papers, or exporting context. Matches queries like "search papers for X", "add this arXiv paper", "show equations from paper Y", "what papers do I have". Prefer CLI over MCP RAG tools for direct lookups.
hummat/paperpipe
papi-verify
Verify code against paper. Use when user asks "does this match the paper", "check my implementation", or is implementing equations/algorithms from literature.
hummat/paperpipe
papi-ground
Ground responses in paper excerpts with citations. Use when user wants cited claims, quotes, or needs to avoid hallucination about paper content.
Didn't find tool you were looking for?