Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

nature-response — Claude skill: reply to peer review

A skill that drafts, audits and revises responses to peer review, revision cover letters and marked manuscripts.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Yuan1z0825/nature-skills --skill nature-response -a claude-code
Open on GitHub

What nature-response does

nature-response handles the whole reply-to-reviewers job. It reads manifest.yaml and the files under always_load: static/core/stance.md for the editor-facing stance and red lines, static/core/workflow.md for accepted inputs and the output package format. Then it fixes the task mode — draft, audit, revise, triage-only, cover-letter, revision-package, latex-template or appeal-like — and the decision type.

Paste a journal email and the skill parses manuscript metadata, editor instructions, reviewer reports, required files and deadlines. Comments get IDs like E.1, R1.1, R2.1 and are classified by response action and work status. Each blind reviewer gets a separate privacy-filtered reply, and manuscript edits are marked in red on a backed-up copy. Anything the author must supply is flagged AUTHOR_INPUT_NEEDED; experiments, citations and line numbers are never invented.

Deep resources sit in references/ and templates/ and open on demand: comment taxonomy, disagreement wording, difficult cases, LaTeX templates. For a LaTeX package, scripts/check_package_consistency.py runs after the first complete draft, after every manuscript edit and right before delivery. Worth installing if you handle revisions in LaTeX or Word and want the letter and the manuscript to stay in sync. For a one-line wording fix, a plain editor is enough.

What it helps with

  • parse a journal email into editor instructions and reviewer comments
  • build a point-by-point reply for each reviewer
  • map every claimed change to a manuscript location
  • prepare a revision cover letter
  • check that the marked manuscript and the letter agree

Example prompts for the agent

  • Parse this journal email and build a point-by-point response
  • Audit my draft reply to reviewers R1 and R2
  • Produce a LaTeX package with cover letter and redline

How to install nature-response

1Skills CLI (Vercel)

npx skills add Yuan1z0825/nature-skills --skill nature-response -a claude-code

2Manually: put the files in place

~/.claude/skills/nature-response/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/nature-response/

From the same set17

The whole set →
nature-figure Yuan1z0825 A skill that builds, revises and audits scientific figures for manuscripts in Python or R. Useful when plots go to submission, not to a report. Claude Code CX Codex Cursor +1 18,700installs nature-polishing Yuan1z0825 A skill that polishes, translates and tightens existing academic prose. Facts, terminology and evidence boundaries stay intact. Claude Code CX Codex Cursor +1 17,400installs nature-paper2ppt Yuan1z0825 Builds a Chinese academic .pptx from a scientific paper or reading notes, with figures from the source and speaker notes. Claude Code CX Codex Cursor +1 16,000installs nature-citation Yuan1z skill, refactored into static/dynamic layers Finds Nature and CNS-family papers for manuscript claims, maps claims to sources, and prepares a reference-manager export. Use it when the journal scope matters. Claude Code CX Codex Cursor +1 15,600installs nature-writing Yuan1z0825 A skill that drafts and restructures scientific manuscript sections and first-submission materials from evidence you supply. Claude Code CX Codex Cursor +1 15,600installs nature-data Yuan1z skill, refactored into static/dynamic layers nature-data drafts or audits manuscript data and code availability statements, dataset access routes, repository plans, and FAIR metadata. Claude Code CX Codex Cursor +1 15,300installs nature-academic-search Yuan1z0825 Searches research literature, checks citations, and builds MeSH strategies. Useful for source discovery, bibliography work, and citation audits. Claude Code CX Codex Cursor +1 15,200installs nature-reader Community contribution, refactored into static/dynamic layers Creates source-grounded Chinese-English paper readers with aligned text, tables, and equations. Handles full translations, excerpt parsing, and targeted questions. Claude Code CX Codex Cursor +1 14,900installs

Similar

baoyu-danger-x-to-markdown JimLiu Converts X posts, threads, and articles into Markdown files with YAML front matter. Useful for archiving social posts and attached media locally. Claude Code CX Codex Cursor +1 28,000installs baoyu-translate JimLiu Translates articles, files and URLs in three modes: quick, normal and refined. The refined mode adds a review and polish pass before publication. Claude Code CX Codex Cursor +1 25,600installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. Claude Code 1,219,756installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs handoff Matt Pocock Creates a handoff document from the current conversation so another agent can continue the work. Use it when a task moves to a new session or agent. Claude Code 1,038,491installs triage Matt Pocock This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. Claude Code 990,453installs domain-modeling Matt Pocock This skill sharpens project terminology, maintains GLOSSARY.md, and records selected architecture decisions in ADRs. Use it while the domain model is changing. Claude Code 876,391installs

Questions about nature-response

How do I install nature-response in Claude?

Run npx skills add Yuan1z0825/nature-skills --skill nature-response -a claude-code. The skill lands in ~/.claude/skills/nature-response/SKILL.md.

What does nature-response do?

It drafts responses to peer review, revision cover letters and marked manuscripts, and audits existing drafts for completeness and consistency.

How is it different from nature-writing and nature-reviewer?

Initial-submission materials belong to nature-writing and simulated peer review to nature-reviewer. nature-response works on replies to comments you already received.

Source text

SKILL.md · Apache-2.0
---
name: nature-response
description: >-
  Draft, audit, or revise responses to peer review, revision cover letters, and
  marked-manuscript or LaTeX revision packages. Use for 审稿意见回复、逐点回复、返修信、
  rebuttals and edits to existing response drafts. Initial-submission materials
  belong to nature-writing; simulated peer review belongs to nature-reviewer.
---

# Nature Reviewer Response — Router

## Routing protocol

For a new task, load the core and matching resources below. Reuse already loaded guidance on follow-ups; load more only when the task needs it.

### 1. Load the manifest and the core layer

Read [manifest.yaml](manifest.yaml). Then read every file listed under `always_load`:

- `static/core/stance.md` — the editor-facing purpose, the default stance, the red lines, and the source hierarchy that apply to every response job.
- `static/core/workflow.md` — accepted inputs, the revision correspondence workflow, and the output package format.

### 2. No content axis — identify mode and language inline

Unlike nature-writing or nature-figure, nature-response has no fragment axis. Its variation is identified at runtime, not by loading different content bodies:

- **task mode** — `draft` / `audit` / `revise` / `triage-only` / `cover-letter` / `revision-package` / `latex-template` / `appeal-like`.
- **decision type** — minor revision, major revision, revise-and-resubmit, transfer after review, or unclear.
- **user language** — if the user writes Chinese, also produce the 中文核对 block.

Decision type is required for a new package-level revision strategy or complete response package.
First extract it from the editor letter or task context. If it remains unclear, ask whether this
is a `Major Revision` or `Minor Revision` and pause only decision-dependent work. A local wording
edit, audit of an existing reply, or comment-level triage may proceed with decision type marked
unknown. Do not infer the decision from the number, tone, or difficulty of reviewer comments.

Use `references/intake-and-routing.md` to fix the task mode, minimum inputs, and readiness state before drafting. Route appeal-like cases separately; do not draft an appeal as the default path.

For a local edit or bounded audit, return the revised passage or findings and relevant missing
facts. Do not expand it into a master tracker, cover letter, or complete revision package unless
requested. Apply the package workflow below only to the parts needed for the requested output.

### 3. Run the workflow

Follow the workflow in `core/workflow.md`: if the user pasted a journal email, first parse manuscript metadata, decision type, editor instructions, reviewer reports, required files, deadlines, and reviewer-visibility rules from the email; identify mode and pass the decision-type gate; apply the Major- or Minor-Revision strategy without downgrading the severity of individual comments; extract editor instructions (IDs `E.1`) then reviewer comments (`R1.1`, `R2.1`) when present; classify each item by response action and independently verified work status; build an internal/editor master strategy and tracker; draft a standalone privacy-filtered response for each mutually blind reviewer; when a reviewer missed material already present in the manuscript, treat that as a clarity signal and revise the presentation instead of replying that the point was already stated; draft a revision cover letter when required; map every claimed change to a manuscript location or explicit placeholder; mark changed manuscript text in red on a backed-up copy when editing; format quoted revised manuscript text in the response letter in italics; flag missing author input; run QA; and derive package readiness from the per-item statuses and blocking state.

Whenever a response proposes or performs a manuscript main-text edit, also load
`../nature-shared/core/main-text-discipline.md`. Answer the reviewer completely
in the letter, but keep the manuscript change to the shortest text needed for
the reader. Prefer replacement or compression over appending, and route
non-central robustness or reconciliation detail to SI unless it changes the
central interpretation.

Never invent experiments, citations, line numbers, figure panels, supplementary items, editor instructions, or manuscript changes. Mark anything the author must supply as `AUTHOR_INPUT_NEEDED`.

### 4. Reach for references only when needed

The files under `references/` and `templates/` are deep resources, not defaults. Open them on demand per the `references.on_demand` table in the manifest — for example `references/comment-taxonomy.md` to classify comments, `references/action-mapping.md` for tracker fields, `references/tone-and-stance.md` for disagreement wording, `references/difficult-cases.md` for impossible experiments / conflicting reviewers / appeal-like cases, `references/chinese-author-alignment.md` for Chinese author notes, `references/latex-templates.md` for `.tex` cover/response/redline outputs, `../nature-shared/core/main-text-discipline.md` for reviewer-driven manuscript additions and evidence relocation, `references/package-consistency-audit.md` whenever the manuscript is edited alongside the letter or the package is about to be compiled and delivered, and `references/qa-checklist.md` before finalizing.

`qa-checklist.md` and `package-consistency-audit.md` are complementary and both apply to a final package: the first asks whether the response is complete, honest, and well-toned; the second asks whether the marked manuscript, the clean manuscript, and the letter actually agree with each other after editing. For a LaTeX package, run `scripts/check_package_consistency.py` after the first complete draft, after every manuscript edit, and immediately before delivery. Any manuscript edit invalidates the letter's verbatim quotes and page references, so re-run the audit rather than treating it as a one-time final check.

© Yuan1z0825 · Apache-2.0 · Yuan1z0825/nature-skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor