Run academic research workflows with Claude Scholar
Guide literature review, experiment tracking, evidence records, result reporting, and paper-writing work through a structured research-agent workflow.
npx skills add agentskillexchange/skills --skill run-academic-research-workflows-with-claude-scholar
Use Claude Scholar when an agent operator needs a research project workflow that spans ideation, literature organization, experiment notes, result analysis, reporting, and manuscript or rebuttal drafting. The invoke moment is a concrete research session: ask the agent to route a research question through evidence records, Zotero or Obsidian-backed notes, experiment artifacts, and writing outputs while preserving human judgment at decision points. The boundary is the research workflow layer for Claude Code, Codex CLI, or OpenCode; it is not a generic academic search product or a broad LLM framework.
What this skill actually does
Inputs and prerequisites: Claude Code, Codex CLI, or OpenCode; Git; optional Zotero and Obsidian for literature and project knowledge workflows.
Setup notes: Clone or download the upstream repository, choose the branch for the target agent runtime such as main for Claude Code, codex for Codex CLI, or opencode for OpenCode, then run the documented setup flow and merge the installed skills/workflows into the target agent configuration.
Source and verification boundary: use https://github.com/Galaxy-Dawn/claude-scholar as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.