yqi96
UserMake AI research agents accountable — give every conclusion a traceable argument graph. MCP server + Claude Code plugin for paper reproduction, hypothesis verification, and auditable scientific reasoning.
Categories
Indexed Skills (4)
literature-survey
Synthesize what a body of literature says about a research question. Builds an argument graph where external findings are Grounds (with paper attachments) and your independent conclusions are Claims. Use when surveying a topic, synthesizing evidence across papers, or assessing whether a research claim is settled.
overleaf-setup
One-time setup skill. Configures automatic Overleaf push for a LaTeX directory — installs leaf, authenticates, inits the project, and writes the auto-push hook to settings.local.json. After setup, every .tex edit in the configured directory triggers a push automatically. Run this skill once; restart Claude Code when done.
declare-barrier
Use this to officially close out a task you cannot complete. Generates the required documentation to formally mark something as blocked and move on.
paper-reproduce
Build and verify an independent argument graph to assess whether a paper's claims hold. Use for reproducing published experimental results, validating paper claims, or building argument graphs from academic literature.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.