claude

academic-research

Rule-books and procedures for academic research with AI agents: MCP-grounded citations, empirical integrity, systematic reviews, Zotero operations, and a parallel-critic manuscript revision loop.

32 on GitHubby Mikko Rönkköv0.32.5MITupdated 3 days ago
/

Plugin academic-research from marketplace mronkko in mronkko/claude-academic-research. Commands read from the repo's manifest — 3 days ago.

This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (14)

  • academic-style

    Use when drafting or editing academic prose — topic sentences, paragraph structure, APA-style citations, voice, tense, hedging, term definitions — in a .qmd / .Rmd / .md / .tex file of an academic-research project. Trigger phrases "write this section", "edit this paragraph", "tighten the prose", "AP

  • cluster-screening

    Use when screening or coding papers on a GPU cluster or batch scheduler instead of an LLM API — emitting a request manifest, submitting a SLURM job, collecting responses, applying them to Zotero. Trigger phrases "screen on the cluster", "run this on SLURM", "sbatch", "GPU node", "emit a manifest", "

  • critic-loop

    Use when the user asks to revise, polish, critique, or finalize an existing academic manuscript, chapter, thesis, or paper — runs parallel critic subagents until no MAJOR issue remains. Trigger phrases "/critic-loop", "run critic-loop", "revise this manuscript", "polish this chapter", "critique this

  • demo-slr

    Use when the user wants to demo or try the plugin's whole systematic-review workflow in 5-10 minutes on a topic they choose, ending with a highlighted Zotero PDF. Trigger phrases "/demo-slr", "demo the SLR", "show me a mini systematic review", "run a demo review". Do NOT use for a real review — use

  • empirical-integrity

    Use when writing or editing a manuscript (.qmd, .Rmd, .ipynb, .tex, .md) that states numbers, statistics, tables, test results, or methodology facts (search dates, model names, keyword strings) — every such value must come from a pipeline-generated file via an inline expression. Trigger phrases "add

  • fact-check

    Use when the user asks to fact-check a manuscript, verify or audit its citations, or check that cited papers support the claims attributed to them. Trigger phrases "fact-check", "verify citations", "audit citations", "check the sources", "do these papers actually say that", "verify the numbers in th

  • grounded-citations

    Use when inserting a new citation into academic prose, attributing a finding to a source, or summarising what a paper says. Trigger phrases "cite this", "add a citation for X", "what does Smith (2019) say", "summarise this paper", "attribute this finding". Do NOT use for Zotero library housekeeping

  • manuscript-revision

    Use when the question is how or why an academic draft should be revised rather than running the revision — why parallel critics, what each critic is for, when a revision is finished. Trigger phrases "how should I revise this", "why a critic loop", "what do the critics check", "when is the draft done

  • retrieving-pdfs

    Use when PDFs must be found and attached to Zotero items — planning retrieval with the user, then running the API cascade, paid OpenAlex, the browser or Connector pass, or manual downloads, and diagnosing items still without a PDF. Trigger phrases "attach PDFs", "get the PDFs", "missing PDFs", "down

  • setup

    Use when the user invokes `/setup`, asks to configure the academic-research plugin, add or rotate an API key (Elsevier, WoS, Semantic Scholar, Wiley TDM, OpenAlex, an LLM provider), switch LLM provider or register MCP servers, or when another skill's pre-flight reports `NOT CONFIGURED`. Trigger phra

  • systematic-review

    Use when running a full systematic literature review (SLR) — PRISMA-style search, screening, coding, and export. Trigger phrases "systematic review", "SLR", "PRISMA", "screen papers", "code papers", "full-text screening". Do NOT use for isolated Zotero enrichment — use `zotero-operations`; for PDF r

  • verifying-citations

    Use only when a calling skill names it as a REQUIRED SUB-SKILL — the per-citation rule-book (classification scheme, staged abstract-then-fulltext rule, always-escalate triggers) shared by `fact-check` subagents and the evidence critic in `critic-loop`. Trigger phrases "REQUIRED SUB-SKILL verifying-c

  • word-zotero-track-changes

    Use when editing an existing Word (.docx) manuscript so the edits appear as tracked changes, especially one with live Zotero citation fields or co-authors' pending changes. Trigger phrases "edit the manuscript with track changes", "redline the docx", "insert citations into the Word file". Do NOT use

  • zotero-operations

    Use when the user asks to work with a Zotero library — adding abstracts, enriching metadata, importing items, deduplicating, fixing BBT (Better BibTeX) citation keys, or writing child notes. Trigger phrases "add abstracts to Zotero", "enrich Zotero library", "fix citation keys", "find duplicates in

MCP servers (1)

  • academic-research

    runs: uv run --no-project --quiet ${CLAUDE_PLUGIN_ROOT}/mcp/server.py

View source on GitHub

More from mronkko/claude-academic-research

All 2 plugins →

Editorial workflows for journal editors and associate editors: from an abstract, suggest peer reviewers (editorial-board profiles plus live external-expert search) or recommend a handling associate editor from the journal's sitting AEs.

1 skill

32

Maintain academic-research?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins