claude

pra

Review a manuscript PDF with N core reviewers, six specialist tracks and an editor, every finding anchored to a quotation, on a Claude Code subscription login

6 on GitHubby PeerReviewAgentsv0.9.0updated todayresearch
/

Plugin pra from marketplace peer-review-agents-local in pgarrett-scripps/PeerReviewAgents. Commands read from the repo's manifest — today.

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 (3)

  • check-draft

    Run chosen specialists over a draft of your own - statistics, the paper's own numbers and methods reporting by default - with no reviewer track and no editor. Use when asked to check, audit or sanity-check a draft or manuscript before submission, rather than to peer review it.

  • follow-up

    Re-review a revised manuscript against an earlier run and say which findings are resolved, which are still open and which have changed. Use when asked to check a revision, re-review after revisions, or compare a new version of a paper against a previous review.

  • peer-review-manuscript

    Run a full two-track peer review of one manuscript PDF - N core reviewers and six specialists, then an editor who pools their findings into one review. Use when asked to peer review, referee or critique a manuscript, or to run PeerReviewAgents on a PDF.

Subagents (10)

  • citation-worker

    One worker on the citation ledger. Claims a batch of in-text citation uses and answers, for each, whether the stored source text supports the sentence that cites it. Files no findings and reads no manuscript.

  • citations

    The citations specialist on a two-track review. Reads the citation ledger the server filled — every reference resolved, every in-text use judged — re-checks each problem row itself, and files only what it has confirmed. Works through the peerreview MCP server only.

  • core-reviewer

    Reviews one manuscript end to end through the peerreview MCP server only. No file, shell, edit or web tools, so it cannot read another reviewer's notes, the run's own files or a benchmark answer key.

  • editor

    Pools the reviewers' and specialists' findings into one review. Merges duplicates, decides body against appendix, rules on every escalated finding and gives an advisory two-axis verdict. Reads findings through the peerreview MCP server only.

  • field

    The field specialist on a two-track review. Audits the paper against the standards of its own field, using the domain pack the server routes to it, through the peerreview MCP server only.

  • figures-tables

    The figures and tables specialist on a two-track review. Checks what each panel and table actually shows against its caption and the sentences that cite it, and whether the display is honest and legible, through the peerreview MCP server only.

  • methods-reporting

    The methods and reporting specialist on a two-track review. Checks whether the work could be repeated from what is written, and whether the required declarations are there, through the peerreview MCP server only.

  • numbers

    The numbers specialist on a two-track review. Audits every quantity the paper prints - whether the same value agrees wherever it appears and whether the arithmetic between printed values holds - through the peerreview MCP server only.

  • recorder

    Opens and closes a review run. Calls ingest at the start and write_review at the end, drives the server's reference lookups, reports the stage ledger, and marks the run blocked when a stage never reported. Makes no judgements.

  • stats

    The statistics specialist on a two-track review. Audits whether the test matches the design and what the result licenses the paper to say - tests, n, multiplicity, effect sizes and inference - through the peerreview MCP server only.

MCP servers (1)

  • peerreview

    runs: ${PEERREVIEW_MCP_COMMAND:-peerreview-plugin-server} -m peerreviewagents.plugin.server --plugin-root ${CLAUDE_PLUGIN_ROOT}

View source on GitHub doi.org

Similar plugins

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer

8 skills · 1 MCP server

ChromeDevTools/chrome-devtools-mcp 55,181

gitnexus

claudecodex

Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.

12 skills · 1 MCP server · hooks

abhigyanpatwari/GitNexus 48,482

Maintain pra?

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 pluginslisted