科研 Skill

学术论文写作打磨

research-paper-writing

Improves ML, CV, or NLP paper sections for structure, flow, and reviewer clarity, checking claim-evidence alignment. Use when drafting or revising a paper before submission.

发布者 Codar安全审核通过v0.1.0更新于 2026-11-18

SKILL.md

Research Paper Writing

Overview

Use this skill to rewrite a research paper into a reviewer-friendly, high-clarity draft. Prioritize first-impression quality (figures/tables/layout), logical flow, and evidence-backed claims.

Core Workflow

  1. Clarify the paper story before sentence-level edits.
  2. Use section-specific guidance in references/.
  3. Rewrite paragraph-by-paragraph with one message per paragraph.
  4. Run reverse outlining after writing each section.
  5. Check every major claim in Abstract/Introduction against experimental evidence.
  6. Run final-paper adversarial review with references/paper-review.md.

Global Principles

  1. Keep one paragraph for one message only.
  2. State the paragraph message in the first sentence.
  3. Make nouns self-contained; define new terms before reusing them.
  4. Maintain sentence-to-sentence flow (cause, contrast, consequence, or refinement).
  5. Iterate with adversarial self-review: read as a skeptical reviewer.
  6. Treat visual quality as core content, not decoration.
  7. Use a clean teaser and pipeline figure.
  8. Use readable, minimal-ink tables.
  9. Keep formatting consistent and tidy.

Paragraph Clarity Check (Important)

Use this quick test whenever the user asks whether a paragraph "flows" or is clear.

  1. Read as an external reader:
    • Does this paragraph have one explicit message?
    • Does the first sentence state what this paragraph will do?
    • Are all key nouns/terms readable without hidden context?
    • Does each sentence connect to the previous one with a clear relation (cause, contrast, consequence, refinement, example)?
  2. Run reverse outlining for the current section:
    • Write down thesis/main claim.
    • Write down each paragraph topic sentence.
    • Write down the evidence/explanation points under each paragraph.
    • Check mapping: topic sentence -> thesis, and evidence -> topic sentence.
    • Revise or remove any paragraph that cannot be mapped cleanly.
  3. If flow is still weak, add temporary section headers and explicit transition phrases during revision, then remove unnecessary headers before finalizing.

Source reference for this check:

  • references/does-my-writing-flow-source.md

Section Guides

Load only the needed section file:

  • Introduction: references/introduction.md
  • Abstract: references/abstract.md
  • Related Work: references/related-work.md
  • Method: references/method.md
  • Experiments: references/experiments.md
  • Conclusion: references/conclusion.md
  • Paper review (Paper Review): references/paper-review.md
  • Paragraph clarity source: references/does-my-writing-flow-source.md
  • Example bank index: references/examples/index.md

Paper Review Core Points

Use references/paper-review.md for the full checklist and workflow.

  1. Add an end-of-draft self-review question list in five dimensions:
    • contribution,
    • writing clarity,
    • experimental strength,
    • evaluation completeness,
    • method design soundness.
  2. Treat claim-evidence alignment as a hard constraint, especially for Abstract and Introduction.
  3. Perform adversarial writing: review as a skeptical reviewer and resolve every high-risk question.
  4. Revise until major rejection risks are explicitly addressed.

Execution Rules

  1. Build a mini-outline before drafting prose.
  2. For each subsection, explicitly include motivation, design, and technical advantage when applicable.
  3. Avoid writing style that looks like incremental patching of a naive baseline.
  4. Keep terminology stable across the full paper.
  5. If a claim cannot be supported by results, weaken or remove the claim.
  6. Before finalizing, append and answer a five-dimension self-review question list, then revise the paper based on unresolved items.
  7. Do not load all section references (Introduction/Abstract/Related Work/Method/Experiments/Conclusion) at once; load only the specific section guide needed for the current edit target.

Output Contract

When asked to rewrite or draft sections, return:

  1. A compact section outline (3-7 bullets).
  2. Revised paragraphs with explicit paragraph roles (opening/challenge/method/advantage/evidence/limitation).
  3. A short self-review checklist covering clarity, flow, terminology consistency, unsupported claims, and missing evidence.
  4. A claim-evidence map for each major claim in the revised text using Claim: ... | Evidence: ... | Status: supported/needs evidence.

Adjacent human-facing documents

This skill governs the published paper draft itself (Abstract, Introduction, Related Work, Method, Experiments, Conclusion). When the work also requires producing or revising meta-documents that support the paper -- for example:

  • updates to the project's PLAN.md,
  • per-section research notes (notes/section_<N>.md),
  • per-component implementation plans (notes/impl_<component>.md),
  • the project's README.md,
  • a reviewer-response draft,

those documents have a different audience (the user, co-authors, reviewers) and a different style budget than the paper itself. Load the human-facing-doc-authoring skill (if installed in this agent's skill set) for the conventions and per-doc-type structural skeletons. Use BOTH skills together: paper-writing for the paper draft, human-facing for any meta-doc.

Resource discipline for paper-writing sessions

A paper-writing session typically iterates across multiple sections, re-reads many survey notes, may re-grep the paper draft repeatedly, and often spans multiple sessions before a section is finalised. Whenever the session is going to be heavy (more than ~5 file reads, multiple section drafts, or a span across multiple sittings), load the agent-resource-discipline skill (if installed) at session start. In particular:

  • agent-resource-discipline/references/persistent-memory.md -- the first-/last-action protocol that updates notes/section_<N>.md and PLAN.md status fields so the next session resumes cheaply.
  • agent-resource-discipline/references/context-window-budget.md -- the rule that this skill's Execution Rule #7 ("do not load all section references at once") generalises to: do not load all survey notes at once, do not load the full .txt extraction of every cited paper -- target-grep instead.

Both skills compose: paper-writing for what to write; agent-resource- discipline for what to load while writing.


Note on this skill's references/ files

The references files under references/ (abstract.md, conclusion.md, experiments.md, introduction.md, method.md, paper-review.md, related-work.md, examples/) are vendored from the upstream Master-cai/Research-Paper-Writing-Skills repository at commit 9ee5edd (see ATTRIBUTION.md). They are deliberately preserved without per-file date-stamp footers -- our universal "every plan-of-record-style document ends with a date-stamp footer" convention (root AGENTS.md Section 6) does not apply to upstream-imported reference content; modifying the upstream files to add footers would create false revision history.

When upstream evolves the references files, we may selectively cherry-pick changes (per ATTRIBUTION.md "Pulling updates from upstream"). When we substantially modify a reference file, we will add a *Revised YYYY-MM-DD by A. Attia: <note>.* footer to that specific file at that point. Until then the upstream provenance is authoritative.


Revised 2026-05-13: added "Adjacent human-facing documents" section pointing at the human-facing-doc-authoring skill for meta-docs (PLAN.md, section/impl notes, README, rebuttal) that this skill does not directly govern. Revised 2026-05-13: added "Resource discipline for paper-writing sessions" section pointing at the agent-resource-discipline skill for the cross-cutting context-window / persistent-memory protocol that complements this skill's Execution Rule #7. Revised 2026-05-14 (post-fresh-audit): documented the deliberate exception from the universal date-stamp-footer convention for upstream-vendored references files (the eight files under references/ that were imported from Master-cai upstream and have not been substantially modified).

Limitations

  • This skill names sibling skills (human-facing-doc-authoring, agent-resource-discipline) by name rather than by a fixed filesystem path; they help only if your agent also has those skills installed from this same marketplace.
  • Section guidance is tuned for ML/CV/NLP-style empirical papers; humanities, qualitative, or pure-theory papers may need a different structure than Abstract/Intro/Related Work/Method/ Experiments/Conclusion.

示例提示词

帮我润色这篇机器学习论文的Method和Experiments章节表述。

所属插件

跨学科科研方法跨学科通用科研方法:系统综述与元分析、预注册、实验与问卷设计、文献矛盾与研究空白、科学计量与专利分析、可复现研究、答辩与审稿回复。

安装该插件会一并获得同领域的 54 个 Skill / MCP。

同插件的其他科研 Skill

常见问题

学术论文写作打磨能做什么?

Improves ML, CV, or NLP paper sections for structure, flow, and reviewer clarity, checking claim-evidence alignment. Use when drafting or revising a paper before submission。

如何安装学术论文写作打磨?

在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「学术论文写作打磨」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。

学术论文写作打磨需要哪些权限?

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。

学术论文写作打磨经过官方审核吗?

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。