agentleFS
jjfroehlichjjfroehlich/agent-skills-for-academic-research/skills/publishing-and-peer-review/SKILL.md

publishing-and-peer-review

Skill2 starsChanged 31 days agoMITView on GitHub

Handle journal submissions, peer reviews, editorial decisions, and reviewer responses. Exclude prose-only edits and work outside an active publication process.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask only for missing facts that change the next action: decision letter, target journal, review invitation, manuscript type, deadline, or …

    line 35
  2. Distinctive:

    Check ethics, confidentiality, reviewer overreach, or unsupported claims when relevant to the requested publication action.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Publishing And Peer Review

Purpose

Help the user make publication-process decisions and produce bounded artifacts for submission, peer review, editorial communication, revision, and response-to-reviewers work.

Use this skill when

  • The user needs a journal submission, presubmission inquiry, cover letter, rejection strategy, transfer decision, or resubmission package.
  • The user is writing, revising, or evaluating a peer-review report.
  • The request concerns reviewer ethics, conflicts of interest, confidentiality, confidential comments, open review, or reviewer overreach.
  • The user needs a response-to-reviewers plan, point-by-point response, or respectful disagreement with reviewer comments.
  • The user asks how to interpret an editorial decision, revision request, or reviewer recommendation.

Do not use this skill when

  • The user primarily wants manuscript prose rewritten; apply a scientific-writing lens instead.
  • The task is figure design, chart choice, or visual communication.
  • The request is about grant review, thesis supervision, career planning, or literature synthesis without a publication-process decision.
  • The user asks for journal rankings or impact-factor strategy without a concrete submission or review artifact.

Core workflow

  1. Identify the role: author, reviewer, editor-facing correspondent, or mixed role.
  2. Identify the next process action: submit, revise, appeal, transfer, decline, review, respond, or ask the editor a focused question.
  3. Ask only for missing facts that change the next action: decision letter, target journal, review invitation, manuscript type, deadline, or policy constraint.
  4. Route to the narrow playbook: journal submission, editorial process, peer reviewing, reviewer ethics, or response to reviewers.
  5. Separate process guidance from manuscript-quality feedback. Reviewers advise; editors decide. Scientific necessity follows the retained claim, while journal fit and actual procedural requirements are separate judgments.
  6. Produce the requested artifact or decision at the needed scale. Use a response map or checklist when it helps track a substantial package; a short process question may need only a direct answer.
  7. Check ethics, confidentiality, reviewer overreach, or unsupported claims when relevant to the requested publication action; a local editor inquiry does not require a full submission or review audit.

Output formats

Select only the format that fits the requested deliverable; these are patterns, not mandatory response sections.

  • Submission-readiness review with journal-fit risks and missing package items.
  • Cover-letter or presubmission-inquiry outline.
  • Editorial-decision diagnosis with next-step options.
  • Peer-review report outline with major/minor comments and confidential-note guidance.
  • Reviewer-ethics decision memo.
  • Point-by-point response-to-reviewers plan or draft.

Reference routing

  • references/journal-submission.md: Use for journal fit, cover letters, submission packages, rejection strategy, appeal, transfer, and resubmission decisions.
  • references/editorial-process.md: Use for interpreting editor decisions, revision expectations, reviewer synthesis, and editor communication.
  • references/peer-reviewing.md: Use for review invitations, manuscript review workflow, review structure, constructive comments, reviewer overreach, and statistical-review triage.
  • references/reviewer-ethics.md: Use for conflict, confidentiality, privileged information, misconduct concerns, confidential comments, open review, or review transfer.
  • references/response-to-reviewers.md: Use for response letters, point-by-point plans, respectful disagreement, reviewer misunderstandings, and out-of-scope requested experiments.
  • Open references/handbook-access.md when a fuller explanation or worked example would help with the current task.

Quick checklist

Apply only the checks relevant to the requested scope and artifact. Inspect supplied context first; treat identify or clarify as analysis when the answer is already available, and ask only for missing information that could change the result.

  • Role and next process action are explicit.
  • Advice is bounded to the current journal, manuscript, review invitation, or decision letter.
  • Major issues are separated from minor polish.
  • Any requested experiment or analysis is tied to a claim that actually needs it.
  • Sensitive process concerns use the appropriate confidential channel; substantive scientific criticism remains visible to authors and consistent with the recommendation.
  • Submission, public release and reuse have the actual coauthor authorization and permissions; one person's signoff is not authority for everyone.
  • The output tells the user what to send, revise, decline, or ask next.

Common pitfalls

  • Treating a rejection as an appeal problem before diagnosing scope, evidence, novelty, or process error.
  • Writing peer reviews as unprioritized reactions instead of evidence-linked major and minor comments.
  • Asking authors for open-ended new projects when a claim limit, analysis clarification, or future-work statement would address the concern.
  • Responding defensively to reviewers without changing the manuscript or giving a clear rationale.

Quality bar

  • The answer must be role-aware, process-aware, and ethically bounded.
  • The answer must produce a concrete next artifact or decision, not generic publication advice.
  • Reviewer and response language must be calm, specific, actionable, and traceable to manuscript claims.
  • Disagreements must state the concern, evidence or constraint, and the bounded change or non-change.

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.