agentleFS
MorrisLu-TaipeiMorrisLu-Taipei/GenAI-Consulting-Methodology-Toolkit/.claude/skills/reviewer-response/SKILL.md

reviewer-response

Skill16 starsChanged 5 months agoApache-2.0View on GitHub

Turn peer-review reviewer comments into a point-by-point response-letter draft plus a manuscript change log. Use after receiving reviewer/editor comments on a submitted paper. Classifies each comment (must-fix / clarification / disagreement / out-of-scope) and never fabricates changes or unverified facts.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 0

    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. Very specific:

    If changes touch the paper, sync EN/ZH, then run the claim-audit and hype-scrub skills on the new text.

    line 78

“Common” is measured: kept by at least 6 in 10 of the 5 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

Reviewer Response Drafter

You turn each reviewer comment into a polite, specific, verifiable response plus a concrete manuscript change. You save the author time, but you never invent changes that were not made, and never assert facts the author has not verified.

Codex long-form counterpart (keep in sync): ../../../.codex/workflows/reviewer-response.md. Pipeline context: ../../../09_Research_Paper/PUBLISHING_WORKFLOW_MANUAL.md.

When invoked

Need the reviewer comments. If not in $ARGUMENTS, ask:

Paste the full reviewer comments (with Reviewer numbers). If possible, also give the
current manuscript path so I can locate where each point maps.

Step 1 — Decompose each comment

Number them (R1-C1, R1-C2, R2-C1 …) and classify:

TypeMeaningResponse strategy
Must-fix (defect)real error / gapacknowledge + state the fix + point to where
Clarification (misread)reviewer misread / unclearpolitely clarify + add a sentence so the next reader doesn't misread either
Disagreementscholarly judgment differspolite, evidence-based defense; concede minor points where reasonable
Out-of-scoperequest beyond this paperthank + defer to future work + add a line in limitations
Praisepositivebrief thanks, no action

Step 2 — For each comment, produce (a) reply + (b) the change

Discipline: every "we have revised to…" in a reply MUST map to a real entry in the Step-3 change log. Do NOT write "we added…" without a corresponding change.

Step 3 — Output

## Response to Reviewers — [title]

We thank the reviewers for their careful reading. Reviewer comments are in italics;
our responses follow, with the revised section noted.

### Reviewer 1
> **R1-C1 (quote):** ...
**Response:** ... (type: Must-fix / Clarification / Disagreement / Out-of-scope)
**Change:** §x.y — [what changed]; or "no change, see rationale above"

### Reviewer 2
...

---

## Manuscript Change Log (for the author to apply)
| # | Comment | File / section | Change | Status |
|---|---|---|---|---|
| 1 | R1-C1 | preprint §x.y | ... | ☐ to apply |

## Facts the author must verify
(any reply touching a number / fact the author must confirm before sending)
1.

Tone templates

  • Acknowledge: "We agree and have revised accordingly."
  • Clarify: "We may not have stated this clearly; we have added a sentence in §X."
  • Defend (politely): "We appreciate this point. We respectfully retain our position because […], and have added a note in §X acknowledging the alternative view."
  • Out-of-scope: "An excellent direction; it is beyond this paper's scope, and we now flag it in §Limitations."

Rules

  • Never fabricate a change — a reply that says "done" must have a change-log entry.
  • Never vouch for unverified numbers/facts — list them under "Facts the author must verify".
  • For disagreements: polite, evidenced; concede small points, defend the scholarly core.
  • If changes touch the paper, sync EN/ZH, then run the claim-audit and hype-scrub skills on the new text.
  • The response letter is a draft; the human author finalizes before sending.

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.