English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

academic-research-skills Guide: Install to First Paper in One Hour

Forum topic · 小凯 · 2026-05-30

Summary

This comprehensive guide walks through installing and using the academic-research-skills plugin for Claude Code and Codex, a suite that bundles Deep Research, Academic Paper, Reviewer, and Pipeline skills. It covers two installation routes (Claude Code plugin marketplace at /plugin marketplace add Imbad0202/academic-research-skills, and a Git clone plus symlink path), the mandatory .claude/skills/<skill-name>/SKILL.md layout that Claude Code auto-discovers, and the Codex sibling package academic-research-skills-codex with its unified $academic-research-suite alias. The guide recommends a first-hour calibration sequence: run /ars-plan on a familiar topic, narrow Deep Research on a sub-question to watch Semantic Scholar verification, then use the Reviewer skill on a human-reviewed draft before touching the full Pipeline. It also lists 29 anti-patterns with 22 iron rules, highlighting hallucination risks in LLM-generated citations and the need for PRISMA-style systematic reviews in medical and social-science submissions.

This comprehensive guide walks through installing and using the academic-research-skills plugin for Claude Code and Codex, a suite that bundles Deep Research, Academic Paper, Reviewer, and Pipeline skills. It covers two installation routes (Claude Code plugin marketplace at /plugin marketplace add Imbad0202/academic-research-skills, and a Git clone plus symlink path), the mandatory .claude/skills/<skill-name>/SKILL.md layout that Claude Code auto-discovers, and the Codex sibling package academic-research-skills-codex with its unified $academic-research-suite alias. The guide recommends a first-hour calibration sequence: run /ars-plan on a familiar topic, narrow Deep Research on a sub-question to watch Semantic Scholar verification, then use the Reviewer skill on a human-reviewed draft before touching the full Pipeline. It also lists 29 anti-patterns with 22 iron rules, highlighting hallucination risks in LLM-generated citations and the need for PRISMA-style systematic reviews in medical and social-science submissions.

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177980599