科研 Skill
评审意见回应撰写
responding-to-peer-review
Interprets reviewer comments and produces a point-by-point response grounded in actual changes. Use when authors must decide how to revise after peer review.
SKILL.md
Responding to Peer Review
Purpose
Convert reviewer reports into a traceable revision process. This skill separates what the reviewer explicitly requested from what the author infers, classifies the scholarly issue behind each comment, and links every response to an actual manuscript change or a reasoned decision not to change.
The goal is neither automatic compliance nor rhetorical resistance. It is accountable revision.
Contract
Accepts authentic reviewer or editor comments, the submitted manuscript, revision files, journal instructions, prior audit reports, and author decisions.
Requires the exact comments and enough manuscript context to locate the issue. A point-by-point response requires either completed revisions or an explicit planned-action status.
Produces normalized ReviewerComment and RevisionAction records, a comment classification, response strategy, manuscript change log, point-by-point response draft, unresolved conflicts, and a peer-review-response gate report.
May produce a revision plan, editor cover note, disagreement rationale, grouped response to overlapping comments, or requests for clarification.
Fails when comments are invented, reviewer identities or motives are guessed, claimed revisions do not exist, contradictory reviewer requests remain unresolved without an editor decision, or the author asks to conceal noncompliance.
Guarantees that each reviewer comment is accounted for and connected to a response status, manuscript location, and evidence of change or reasoned non-change.
Does not guarantee reviewer satisfaction, acceptance, correct interpretation of ambiguous comments, or resolution of conflicting editorial demands.
When to use
Use after receiving formal reviewer or editor reports, during revision planning, while drafting the response letter, and before resubmission to verify that claimed changes are present.
Do not simulate peer review with this skill. Use reviewing-manuscript or stress-testing-argument for internal review. This skill requires real comments or clearly labeled hypothetical training material.
Inputs required
Provide:
- Full reviewer and editor comments, preserving numbering and wording.
- The submitted manuscript and current revised version.
- Journal instructions and deadline constraints.
- Any editor prioritization among conflicting comments.
- Author decisions, especially where revision would alter the thesis or exceed scope.
- Existing citation, terminology, or manuscript review reports.
Redact personal data if necessary, but do not paraphrase away the substance of the comments before classification.
Procedure
1. Preserve and identify each comment
Assign a stable ID such as R1-C3. Preserve the original wording. Separate bundled comments into sub-items while retaining their parent comment. Distinguish editor instructions from reviewer suggestions.
2. Classify the comment
Classify each item as one or more of:
- clarification;
- evidence request;
- citation or literature request;
- concept definition;
- scope challenge;
- argument objection;
- method concern;
- interpretation challenge;
- structural revision;
- terminology or translation;
- style or format;
- ethical or disclosure issue;
- misunderstanding caused by manuscript presentation;
- recommendation outside current scope.
This classification determines the appropriate skill and evidence needed.
3. Distinguish explicit request from inferred concern
Record:
- what the reviewer literally asks;
- the likely scholarly concern;
- confidence in that interpretation;
- whether clarification from the editor is needed.
Do not attribute hostility, ideology, incompetence, or hidden motives.
4. Assess validity and consequence
Evaluate the comment against the manuscript. Use one response strategy:
- accept and revise;
- accept in part and narrow;
- clarify without substantive change;
- disagree with evidence;
- defer as limitation;
- request editor clarification;
- mark outside scope with a bounded explanation.
“Reviewer is wrong” is not a sufficient strategy. A disagreement must identify the manuscript evidence, relevant source, scope, or methodological reason.
5. Plan revisions in dependency order
Some comments affect the thesis, scope, or terminology and therefore change responses to later comments. Build a revision sequence before editing. Route issues to appropriate skills:
scope -> concepts -> evidence -> argument -> structure -> citations -> terminology -> style
Merge overlapping comments carefully, but answer each reviewer ID separately in the response letter.
6. Make or verify manuscript changes
For each action record:
- original location;
- revised location;
- old function or wording;
- new function or wording;
- reason for the change;
- evidence added or removed;
- status: planned, completed, verified, or blocked.
Do not say “revised as suggested” until the change is present in the current file.
7. Draft the response
A strong response normally contains:
- Thanks or acknowledgement without excessive flattery.
- A concise statement of the action or decision.
- The reason where needed.
- Exact manuscript location.
- A brief quotation or summary of the revised text when useful.
Keep tone professional and specific. Avoid defensive biography, speculation about the reviewer, or claims that the change “fully resolves” the issue unless verified.
8. Handle disagreement transparently
When not following a recommendation:
- restate the concern fairly;
- identify shared ground;
- explain the manuscript's scope or method;
- provide evidence;
- state any compensating clarification or limitation added;
- invite editor guidance if the conflict is consequential.
A reasoned non-change is preferable to cosmetic compliance that damages the argument.
9. Reconcile the response letter and manuscript
Check every page, section, table, note, and reference cited in the response. Ensure numbering matches the revised file. Confirm that deleted passages are not still described as revised and that new sources appear in the bibliography.
10. Issue the gate report
Return PASS when every comment is accounted for, all claimed changes are verified, and no blocking conflict remains. Use CONDITIONAL PASS when an editor decision or specialist check remains but is explicitly documented. Return FAIL when comments are omitted, changes are falsely claimed, or central concerns remain unaddressed.
Stop signals
Stop and request action when:
- the original comment is missing or paraphrased beyond recognition;
- reviewer requests conflict on the same issue and the editor has not prioritized them;
- a requested source cannot be accessed;
- compliance would require data, permissions, languages, or methods not available;
- the author asks to claim a revision that was not made;
- the response would disclose confidential or identifying information;
- the revision changes the thesis without researcher approval.
Completion criteria
Completion requires:
- every comment has a stable ID and status;
- explicit request and inferred concern are distinguished;
- each response strategy is justified;
- claimed manuscript changes are verified at exact locations;
- citations and terminology affected by revision are reconciled;
- disagreements are evidence-based and respectful;
- unresolved editor decisions are explicit;
- the response gate follows from the record.
Anti-fabrication rules
Do not invent reviewer comments, editorial preferences, page locations, revisions, sources, acceptance probabilities, or reviewer motives. Do not fabricate language such as “we have added extensive discussion” when only a sentence changed. Do not create supporting citations solely to appease a reviewer without checking relevance.
When the current manuscript file cannot be inspected, label actions planned, not completed or verified.
Output format
Use templates/reviewer-response.md. For each comment include:
Comment ID:
Original comment:
Issue classification:
Explicit request:
Inferred concern:
Response strategy:
Manuscript action:
Location:
Verification status:
Response text:
Remaining issue:
Gate report
Gate: Peer Review Response
Status: PASS | CONDITIONAL PASS | FAIL
Evidence checked:
Blocking issues:
Non-blocking risks:
Researcher decisions required:
Required next action:
Next skill:
Good invocation
Build a point-by-point response to these real reports. Preserve each comment, distinguish planned from verified changes, and flag the two conflicting requests for an editor decision.
Bad invocation
Invent a persuasive response saying we made all requested changes, even though the revised manuscript is not available.
The bad invocation requires false claims and MUST be refused.
Next skills
scoping-argument-boundaryfor scope conflicts.stress-testing-argumentfor substantive objections.auditing-citationsfor requested sources and quotation checks.checking-terminology-consistencyafter conceptual revisions.verifying-before-submissionbefore resubmission.
Friction triggers
Create reviewer–author friction when a comment conflicts with evidence, another reviewer, project scope, or the researcher's defended interpretation.
Friction checks
Treat reviewer claims as claims, not truth. Preserve accept, rebut, and partial-acceptance alternatives and identify evidence for each.
Judgment boundary
Acceptance, rebuttal, partial acceptance, and core-concept revision require researcher decisions. Agent recommendations remain separate from the response authorization.
Evidence ledger updates
Add evidence introduced by revision and reassess standing for claims affected by reviewer requests; do not add decorative citations.
Interpretation history impact
If a response changes an interpretation, append a version with the reviewer trigger and researcher status. Preserve the submitted reading.
Possible epistemic return
A reviewer-supplied source or defensible interpretation may trigger return when it materially changes inquiry. Mere disagreement or a known manuscript defect does not automatically qualify.
Productive refusal
When comments conflict or evidence is unavailable, state the conflict, bounded response possible, missing authority or source, and need for editor or researcher decision.
Gate impact
Core concept or claim changes invalidate dependent gates and require re-audit. No response gate may pass on planned but unverified revisions.
Limitations
Reviewer comments may be ambiguous, inconsistent, or based on disciplinary assumptions not fully stated. The skill cannot know reviewer intentions or guarantee acceptance. Editors retain authority over conflicting requests, and authors retain responsibility for intellectual decisions and accurate claims about revisions.
示例提示词
帮我针对这几条评审意见逐条撰写修改说明并给出透明的修订记录。
所属插件
安装该插件会一并获得同领域的 62 个 Skill / MCP。
同插件的其他科研 Skill
- 学术文献获取下载Auto-downloads open-access PDFs for graded sources and writes a manual worklist for paywalled items. Use after literature-review, before ingest-source.
- 单篇文献入库管理Adds one verified PDF to a shared bibliography library, computing its citation key and keywords. Use to register a single document outside the full workflow.
- 数字人文计算方法Surveys computational DH methods: text mining, NLP, corpus linguistics, archive standards, GIS, network analysis, and OCR. Use for an overview of available DH tools.
- 考古地理信息系统分析Runs archaeological GIS analysis with GeoPandas: catchment analysis, viewshed, kernel density, spatial statistics. Use for mapping archaeological site locations.
- 论证结构提取可视化Extracts and visualizes argument structure: Toulmin reconstruction, support/attack graphs, circularity detection. Use to diagram an argument’s logical structure.
- 考古遗物类型学分析Performs artifact analysis: typological classification, ceramic attribute coding, lithic reduction analysis. Use when classifying excavated artifacts statistically.
- 引文与出处核查Checks citations, quotations, page numbers, and bibliography entries for accuracy and source fit. Use before submission to verify source-supported claims.
- 研究选题构思设计Explores research intent, field state, methodology, and ethics, then writes an approved design doc. Use before starting a new research question or chapter.
- 术语译名一致性检查Audits a manuscript for terms, translations, abbreviations, and names whose forms must stay stable. Use when terminology drift could undermine an argument.
- 计算语用学分析Runs computational pragmatics: speech act classification, implicature detection, discourse coherence, politeness analysis. Use for language-use-and-meaning studies.
- 文献综述学术对话构建Turns verified sources into a structured scholarly conversation among positions, not a chronological summary. Use when synthesizing literature into a debate narrative.
- 语料库语言学分析Performs corpus analysis with NLTK/spaCy: collocation, keyword analysis, KWIC concordance, word2vec, diachronic trends. Use for quantitative text-corpus research.
- 数字档案馆资源检索Queries digital archive REST APIs: Europeana, Chronicling America, Internet Archive, HathiTrust, DPLA, OAI-PMH. Use when searching or harvesting heritage metadata.
- 学术手稿章节撰写Drafts a chapter or article section by section from synthesized wiki content, agreeing each section’s argument first. Use to turn stable research synthesis into prose.
- 研究项目漂移状态检测Checks a shared source library and registered projects for drift: un-indexed PDFs, unmerged keywords, bibkey collisions. Use to audit a multi-project research setup.
- EMI课堂语料转写分析Segments and annotates classroom transcripts, coding language choice and discourse function with anonymised output. Use to quantify classroom talk or translanguaging.
- 人工智能伦理分析Analyzes AI ethics: algorithmic fairness metrics, bias auditing, value alignment, moral philosophy reasoning. Use to evaluate an AI system’s ethical dimensions.
- 研究计划任务执行Executes a ready research plan task by task, gating acquisition before ingest and dispatching analysis. Use after writing-research-plan to run the planned work.
- 研究项目结项清单Runs the final completion checklist: rendering, bibliography, wiki, data, reproducibility, archiving. Use when a manuscript is finalized and ready to publish.
- 形式逻辑自动推理Applies formal logic tools: Z3 SMT solver, modal logic S5, SAT encoding, Lean4 proof verification. Use to formalize or mechanically check a logical argument.
- 研究问题凝练构建Turns a broad topic or intuition into a precise, contestable, researchable question. Use at the start of a project when no defensible question yet exists.
- 历史地理信息系统分析Performs historical GIS work: georeferencing old maps, digitizing boundaries, temporal territory overlays, population interpolation. Use for historical spatial analysis.
- 历史语言学比较分析Analyzes historical linguistics in Python: sound correspondences, cognate detection, phylogenetic trees, Swadesh lists. Use when reconstructing language relationships.
- 历史社会网络分析Builds historical network analyses: correspondence networks, prosopography, temporal community detection, Gephi export. Use to map relationships among historical actors.
常见问题
评审意见回应撰写能做什么?
Interprets reviewer comments and produces a point-by-point response grounded in actual changes. Use when authors must decide how to revise after peer review。
如何安装评审意见回应撰写?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「评审意见回应撰写」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。
评审意见回应撰写需要哪些权限?
该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。
评审意见回应撰写经过官方审核吗?
是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。