agentleFS
Agentic-AssetsAgentic-Assets/corbis-mcp/skills/paper-review/SKILL.md

paper-review

Skill0 starsChanged 38 days agoMITView on GitHub

Use for any request to review, critique, or give feedback on a research paper, draft, or manuscript in finance, real estate, economics, or urban studies, including quick feedback on its biggest problems or weaknesses, a referee report, a pre-submission check, or a technical audit. Produces referee-style reviews with literature positioning and reference checks from the Corbis research connector.

27 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use paper-writing.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MLNLP-WorldSkill

    paper-writing

    学术论文写作检查与优化助手。基于 MLNLP-World 社区整理的论文写作技巧,帮助检查和优化学术论文。Use when: (1) 检查论文 LaTeX 格式和排版, (2) 优化公式符号使用, (3) 改进图表设计, (4) 润色英文学术表达, (5) 检查参考文献格式, (6) 投稿前终稿检查, (7) 用户询问论文写作技巧或规范。

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask only if the request fits both.

    line 25
  2. Very specific:

    If your client can read MCP resources, read docs://workflow-packs/referee-report (referee report) or docs://workflow-packs/technical-audit …

    line 37
  3. Distinctive:

    After the local report, on enterprise plans:

    line 49
  4. Distinctive:

    If the tool is unavailable or denied, deliver the local report labeled "Local review" and note once that the scored evaluation needs an …

    line 54

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Paper review

Review a manuscript the user provides, the way a careful referee would, and ground literature and reference findings in Corbis sources.

Ground rules

  • Cite only papers, data, and quotes that a Corbis tool returned in this conversation or that the user supplied. Never invent a DOI, author, year, title, or quote.
  • Say when evidence is thin, old, mixed, or limited to one market or domain. Never describe the output as free of errors or hallucinations.
  • Some optional steps use premium tools that need an enterprise plan. If a premium tool is not in your tool list, or returns an access or plan error, tell the user once that the step needs an enterprise plan (current plans: https://www.corbis.ai/pricing), then continue with the standard tools. Never retry a denied tool.
  • Research tool calls may use Corbis credits. Use a batch tool when one exists, and never re-fetch details for a paper already retrieved in this conversation.
  • Quick mode is the default for a narrow question: at most 5 Corbis tool calls, a short cited answer, then an offer to run the full workflow. Use full mode when the user asks for a review, report, or audit, or accepts that offer.
  • If no Corbis tools are available, or a Corbis call returns a sign-in or connection error, first retry the call once through any other Corbis connection in your tool list (the same tool name from another Corbis server). That retry counts toward the quick-mode limit, so skip it when no calls remain. If none works, ask the user to connect or reconnect Corbis (the plugin's Connectors tab, or /mcp in Claude Code) instead of answering from memory. Do not switch to another source, such as a web search or another citation database, unless the user asks, and label anything from another source as not verified by Corbis.

Before you start

  • You need the manuscript. If none is attached, ask for it. Never review from a title or abstract alone and present it as a paper review.
  • Pick the review type from the request:
    • Referee report: overall assessment, recommendation, must-address issues, and additional comments.
    • Technical audit: specific technical findings, each with an exact quote from the manuscript.
    • Ask only if the request fits both.
  • Send Corbis short search queries and summaries, not the full manuscript text.

Quick (a request for fast feedback, or top issues)

  1. Read the manuscript.
  2. Report the five most important issues. For each: location (section, page, table, or equation), the problem, why it matters, and a concrete fix. For a technical audit, include the exact quote.
  3. Corbis calls are optional here (at most 5). Use one literature_retrieve call only if an issue depends on related work.
  4. Offer the full review.

Full review

If your client can read MCP resources, read docs://workflow-packs/referee-report (referee report) or docs://workflow-packs/technical-audit (technical audit) first; use its phases and contracts, and do not create local files or subagents. Otherwise follow references/referee-report-phases.md or references/technical-audit-phases.md.

Evidence tools during the phases:

  • Related and missing literature: literature_retrieve or search_papers with short queries built from the research question, then get_paper_details_batch on the papers you keep, at most 25 IDs per call.
  • Bibliography health (technical audit): verify_bibtex on the manuscript's references when the user supplies BibTeX.
  • Reference list for papers you cite in the report: render_citations.

Deliver the report in the template from the phase reference.

Scored evaluation (enterprise upgrade)

After the local report, on enterprise plans:

  • Referee report: call referee_report_evaluate with the summary contract in references/referee-report-phases.md.
  • Technical audit: call technical_audit_evaluate with the findings contract in references/technical-audit-phases.md.

If the tool is unavailable or denied, deliver the local report labeled "Local review" and note once that the scored evaluation needs an enterprise plan.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.