Skill Detail

Run academic literature review and paper-output workflows with Aut Sci Write

Use Aut Sci Write to let an agent search scholarly sources, download papers, extract PDF evidence, sync Zotero citations, and produce review or presentation artifacts.

Research & ScrapingMulti-Framework
Research & Scraping Multi-Framework Security Reviewed
⭐ 151 GitHub stars ⬇ 43/wk npm
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill run-academic-literature-review-and-paper-output-workflows-with-aut-sci-write Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
Agent Skills-compatible runtime such as Claude Code, Codex, Cursor, OpenClaw, or opencode; Python 3.10+; Node.js 18+; optional Zotero, Web of Science, NCBI/PubMed, Elsevier, Springer, Anthropic, Moonshot, and Tesseract configuration depending on the selected sub-skill.
Install & setup
Install with the documented plugin flow using /plugin marketplace add ShZhao27208/Aut_Sci_Write and /plugin install academic-skills@shuozhao, or run npx skills add ShZhao27208/Aut_Sci_Write -g -y and then install Python dependencies from the upstream requirements file.
Author
Shuo Zhao
Publisher
Independent
Last updated
Jul 2, 2026
Quick brief

Aut Sci Write is best framed as an academic research operator workflow, not as a generic research app. The agent uses the upstream skill suite to search arXiv, PubMed, Web of Science, Elsevier, Springer, Semantic Scholar, OpenAlex, and related sources, then downloads papers, extracts PDF findings, crops figures, syncs Zotero records, drafts literature review material, and generates PPTX or HTML outputs for human review.

How it works

What this skill actually does

Invoke this when a user wants a repeatable research pass across papers and citations instead of manually searching portals, saving PDFs, copying notes, and assembling slides by hand. Keep the scope bounded to scholarly discovery, evidence extraction, citation handling, and reviewable academic outputs. The operator should verify paper relevance, citation quality, API keys, and generated claims against the source documents before using the artifacts in real research or publication work.

Inputs and prerequisites: Agent Skills-compatible runtime such as Claude Code, Codex, Cursor, OpenClaw, or opencode; Python 3.10+; Node.js 18+; optional Zotero, Web of Science, NCBI/PubMed, Elsevier, Springer, Anthropic, Moonshot, and Tesseract configuration depending on the selected sub-skill..

Setup notes: Install with the documented plugin flow using /plugin marketplace add ShZhao27208/Aut_Sci_Write and /plugin install academic-skills@shuozhao, or run npx skills add ShZhao27208/Aut_Sci_Write -g -y and then install Python dependencies from the upstream requirements file.

Source and verification boundary: use https://shzhao27208.github.io/Aut_Sci_Write/ 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.