Skip to main content
skill CX Codex

nature-response · galaxy-dawn — Claude Code skill: reviewer replies and setup

nature-response is a Claude Code skill that drafts and audits point-by-point replies during Nature-family manuscript revisions.

MIT 276 installs ★ 6,082 updated 2026-10-19

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

What nature-response does

nature-response turns an editor letter, reviewer reports, author notes, or an existing rebuttal into a traceable revision package. It extracts editor instructions, assigns IDs such as E.1 and R1.1, classifies each concern, and links the proposed reply to a manuscript change, figure, table, citation, or open action.

Its workflow covers draft, audit, revise, triage-only, and appeal-like modes. The output includes a response strategy, a comment-response tracker, a draft letter, a manuscript change checklist, and QA for completeness and risk. It can also read skills/ml-paper-writing/references/knowledge/paper-miner-writing-memory.md when that file is available.

The skill labels package readiness as ready_to_submit, draft_with_placeholders, needs_author_input, or blocked. It refuses to invent experiments, citations, line numbers, figures, or claimed revisions; missing details become AUTHOR_INPUT_NEEDED. Platforms listed for the skill are Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.

What it helps with

  • parse an editor decision letter into action items
  • map reviewer concerns to manuscript revisions
  • draft a response for major or minor revision
  • flag author details needed before submission
  • audit a rebuttal for missing responses and unsupported claims

Example prompts for the agent

  • Turn this editor letter and the reviewer reports into a response strategy, tracker, and point-by-point draft.
  • Audit my rebuttal for unanswered comments, invented manuscript changes, and places that need AUTHOR_INPUT_NEEDED.
  • Prepare a major-revision response package with reviewer IDs, change mapping, and risk checks.

How to install nature-response

1Skills CLI (Vercel)

npx skills add Galaxy-Dawn/claude-scholar --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/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about nature-response

How do I install nature-response in Claude Code?

Run npx skills add Galaxy-Dawn/claude-scholar --skill nature-response -a claude-code. The skill file is placed at ~/.claude/skills/nature-response/SKILL.md.

What does nature-response do?

It converts editorial and reviewer material into a traceable package with a response strategy, comment tracker, draft letter, manuscript change checklist, and risk flags.

How does it handle missing author information?

It does not fabricate experiments, citations, line numbers, figures, or revisions. It marks the item AUTHOR_INPUT_NEEDED and carries it into the risk and missing-information section.

Source text

SKILL.md · MIT
---
name: nature-response
description: >-
  Draft, audit, or revise point-by-point reviewer response letters for Nature-family
  manuscript revisions. Use when the user provides reviewer comments, editor decision
  letters, revision notes, response drafts, or asks how to respond to major/minor
  revision requests, rebuttal letters, response to reviewers, peer-review reports,
  审稿意见回复, 逐点回复, 修回信, 大修回复, 小修回复, or 如何回复 reviewer.
version: 0.1.0
status: Beta
---

# Nature Reviewer Response Skill

Use this skill to convert editor decision letters, reviewer comments, author notes, or
draft rebuttals into an auditable point-by-point response package for manuscript revisions.

The response letter is an editor-facing verification document. The goal is to show that every
reviewer concern has been understood, addressed, and mapped to a concrete manuscript change,
justified scientific response, or unresolved author action.

## Default stance

- Preserve each reviewer comment faithfully before responding.
- Every reviewer concern must be answered, cross-referenced, or explicitly marked as unresolved.
- Map every response to manuscript evidence, a revision location, a justified disagreement, or `AUTHOR_INPUT_NEEDED`.
- Do not invent experiments, analyses, citations, line numbers, figure panels, supplementary materials, editor instructions, reviewer identities, or manuscript changes.
- Prefer concise, evidence-linked replies over long defensive explanations.
- When disagreeing, acknowledge the concern first, then give a scientific or scope-based reason.
- When a reviewer misunderstood the manuscript, first consider whether the manuscript presentation caused the misunderstanding.
- Treat rebuttal letters as potentially public review artifacts; write with professional tone and traceability.

## Mined writing memory

For response structure or tone, check the active installed
`skills/ml-paper-writing/references/knowledge/paper-miner-writing-memory.md`
under the current client's skill home. Read only relevant rebuttal and venue
entries. Reviewer comments, manuscript changes, and journal instructions remain
the source of truth. Do not borrow claims or copy source phrasing. If the memory
is absent or has no relevant entries, continue with this skill's references.

## Accepted inputs

The skill may receive:

- editor decision letter
- reviewer comments
- previous response draft
- manuscript change notes
- tracked-change summary
- line or page numbers
- figure, table, and supplement list
- author notes in Chinese or English
- journal name and article type

If reviewer boundaries or comment segmentation are ambiguous, flag the ambiguity instead of
inventing reviewer structure.

## Workflow

1. Identify task mode and input readiness: `draft`, `audit`, `revise`, `triage-only`, or `appeal-like`.
2. Identify decision type: minor revision, major revision, revise-and-resubmit, transfer after review, or unclear.
3. Extract editor instructions first and assign IDs such as `E.1`, then split reviewer comments with IDs such as `R1.1`, `R1.2`, and `R2.1`.
4. Classify each item by category, severity, action label, missing input, readiness state, and risk.
5. Create a response strategy summary before drafting prose.
6. Draft responses using preserved reviewer comments unless the mode is `triage-only` or `appeal-like`.
7. Map each claimed change to manuscript location, figure, table, supplement, citation, or explicit placeholder.
8. Flag missing author input rather than fabricating details.
9. Run QA for completeness, traceability, factuality, tone, and unresolved risk.
10. Return the response package with package readiness: `ready_to_submit`, `draft_with_placeholders`, `needs_author_input`, or `blocked`.

## Output format

Unless the user asks for another format, return:

```text
Response strategy summary
- Decision type:
- Overall posture:
- Major risks:
- Suggested ordering:

Comment-response tracker
| ID | Reviewer concern | Type | Severity | Proposed action | Missing author input |
|---|---|---|---|---|---|

Draft point-by-point response letter
[editor-readable English response]

Manuscript change checklist
- [specific manuscript changes or placeholders]

Missing information / risk flags
- [specific unresolved items or "None"]

中文核对
- [when the user writes in Chinese; otherwise omit unless useful]
```

## Red lines

- Do not ignore any reviewer comment.
- Do not rephrase reviewer comments in a way that changes their meaning.
- Do not claim a revision was made unless the user supplied it.
- Do not invent line numbers, figure panels, citations, statistical results, or supplementary items.
- Do not use hostile or accusatory language.
- Do not cite time, money, or convenience as the primary reason for not doing a requested experiment.
- Do not hide limitations.
- Do not generate an appeal letter as the default path. Route appeal-like cases separately.
- Do not generate a cover letter in the MVP. Mention it only as adjacent revision-package material when relevant.

## Related files

| File | Open when |
|---|---|
| [references/intake-and-routing.md](references/intake-and-routing.md) | Before drafting, to identify task mode, minimum inputs, editor IDs, readiness state, and clarifying-question need |
| [references/source-basis.md](references/source-basis.md) | You need source hierarchy, rule provenance, or policy-vs-advice boundaries |
| [references/response-structure.md](references/response-structure.md) | You need the response package format or point-by-point letter anatomy |
| [references/comment-taxonomy.md](references/comment-taxonomy.md) | You need to classify reviewer comments by category and severity |
| [references/action-mapping.md](references/action-mapping.md) | You need action labels, tracker fields, and missing-input states |
| [references/tone-and-stance.md](references/tone-and-stance.md) | You need recommended language, forbidden phrasing, or disagreement tone |
| [references/chinese-author-alignment.md](references/chinese-author-alignment.md) | The user writes in Chinese or provides Chinese author notes |
| [references/difficult-cases.md](references/difficult-cases.md) | The comments involve impossible experiments, factual errors, conflicting reviewers, citations, statistics, compliance, transfer, or appeal-like cases |
| [references/qa-checklist.md](references/qa-checklist.md) | Before finalizing an output or auditing a draft response |

## Source hierarchy

Use sources in this order:

1. Target journal instructions and the editor decision letter.
2. Nature / Nature Portfolio / Springer Nature revision and peer-review process guidance.
3. Springer Nature editorial advice on rebuttal letters.
4. Local manuscript facts supplied by the author.

If a policy detail may have changed, verify the current journal page before giving final
submission advice.

© Galaxy-Dawn · MIT · Galaxy-Dawn/claude-scholar

Similar skills

SKILL.md skills catalog →

nature-response by other authors comes first.

nature-response Yuan1z0825 nature-response — a skill that drafts, audits and revises responses to peer review, revision cover letters and marked manuscripts. CX Codex +1 16,700installs nature-figure Yuan1z0825 nature-figure is a Claude Code skill that creates, revises, audits, and exports scientific figures in Python or R. It routes manuscript plots, multi-panel layouts, and requested AI-generated schematics to separate workflows. CX Codex +1 20,700installs nature-polishing Yuan1z0825 nature-polishing — a skill that polishes, translates and tightens existing academic prose. Facts, terminology and evidence boundaries stay intact. CX Codex +1 19,400installs gws-modelarmor-sanitize-response official googleworkspace The gws-modelarmor-sanitize-response skill sends a model response to Google Model Armor for filtering with a template. Use it to check output before showing it to a user. CX Codex +1 30,600installs incident-response official anthropics incident-response walks an incident from detection to review: severity triage, status updates, timeline and a blameless postmortem. CX Codex +1 6,100installs legal-response official anthropics The legal-response skill drafts replies to common legal inquiries from configured templates and checks when a matter needs counsel. Use it for DSRs, NDAs, vendor questions, and subpoenas. CX Codex +1 3,600installs crisis-response-planner aaron-he-zhu crisis-response-planner is a Claude Code skill that builds a social crisis protocol and guides incident response, from severity levels and posting pauses to approved statements and return to publishing. CX Codex +1 1,100installs

From the same set31

The whole set →
agent-identifier The agent-identifier skill helps create and configure Claude Code agents, from frontmatter to system prompts. Use it for autonomous multi-step work. CX Codex +1 352installs nature-polishing nature-polishing is a Claude Code skill that adapts academic manuscripts to Nature publishing standards. It restructures draft sections, abstracts, and section arguments. CX Codex +1 337installs obsidian-project-kb-core The obsidian-project-kb-core skill manages a project-scoped Obsidian research vault: it builds the structure, routes notes, and keeps indexes, the registry, and checks up to date. CX Codex +1 332installs obsidian-source-ingestion obsidian-source-ingestion turns outside material into source notes inside a project-scoped Obsidian vault: papers, web pages, data, interviews. Useful when sources need a shelf, not a summary. CX Codex +1 329installs obsidian-kb-artifacts obsidian-kb-artifacts — a skill for Obsidian formatting and derived artifacts: wikilinks, registry tables, canvas files, Bases, and link repair. Works in Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. CX Codex +1 328installs nature-writing The nature-writing skill drafts and restructures Nature-style research writing from claims, results, figures, notes, or Chinese drafts. Use it for a section, outline, or full manuscript argument. CX Codex +1 306installs expression-skill The expression-skill skill shapes concise, decision-ready answers with evidence, risks, and next steps. Use it for reports, plans, research notes, and writing feedback. CX Codex +1 284installs nature-data nature-data is a skill that builds and audits Nature-style Data Availability statements, repository plans, dataset citations, and FAIR metadata checklists. CX Codex +1 272installs

Project sponsors

Companies that keep this analytics open