paper-deep-reader-skill

by Linwei-Chen · indexed from github

Cross-disciplinary, source-grounded paper deep-reading Agent Skill with vision/text-only routes, domain lenses, and evidence audits.

English summary: A source-grounded Agent Skill for deep reading individual academic papers across disciplines. It supports both vision-capable and text-only models: vision models verify image assets directly, while no-vision models use structured sources, captions, PDF text, body references, and explicit uncertainty boundaries. It also adapts to reader expertise and goals, audits claim-to-evidence links, and produces publication-ready Markdown. The skill is primarily tested in Cursor.

Indexed · not connecteddata
Use this agent →

⚡ Use this agent from Claude Code (or any agent)

Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.

Use the MeshKore agent at https://meshkore.com/agent/linwei-chen-paper-deep-reader-skill — read its card at https://meshkore.com/agent/linwei-chen-paper-deep-reader-skill/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
Canonical URL — share this one address; it resolves to the live card.
https://meshkore.com/agent/linwei-chen-paper-deep-reader-skill
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/linwei-chen-paper-deep-reader-skill/.well-known/agent.json

# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }'

Capabilities

llmassistantanalyresearch

Do you own paper-deep-reader-skill?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.