New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Research Paper Writing Coach

by XiaomiMiMo in XiaomiMiMo/MiMo-Code

Drafts, rewrites and reviews academic papers in ML, CV and NLP style, section by section, and compiles LaTeX sources to PDF.

MITAuto-check passedResearch & Science

Install Research Paper Writing Coach

skills CLI
$ npx skills add XiaomiMiMo/MiMo-Code --skill research-paper-writing -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install XiaomiMiMo/MiMo-Code research-paper-writing --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/XiaomiMiMo/MiMo-Code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/cli/src/skill/builtin/.bundle/research-paper-writing .claude/skills/research-paper-writing && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
research-paper-writing
GitHub stars
14k
Token cost
~1.7k tokens
SKILL.md length
819 words
Files
37 (incl. references)
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Drafts, rewrites and reviews academic papers in ML, CV and NLP style, section by section, and compiles LaTeX sources to PDF.

  • Works in 2 steps: Diagnose the request, then route → Get the facts before writing
  • Writing or rewriting the abstract, introduction, method or experiments of a paper
  • SKILL.md covers Step 1: Diagnose the request,…, Step 2: Get the facts before…, Hard Rules (never violate) and Core Writing Principles, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The agent plays an experienced co-author aiming for a draft that survives skeptical reviewers, with a clear story, one message per paragraph and evidence behind every claim. It first routes the request using a table that maps each situation to one reference guide, loading only that guide: paragraph polish, abstract, introduction, related work, method, experiments, conclusion and limitations, a pre-submission review in five adversarial dimensions, and PDF export. Bullet points or Chinese notes are treated as section drafting.

Before writing, the agent collects the facts: the exact technical problem and why prior methods fail, the contribution, why the method works, and the strongest numbers. It asks at most three focused questions and never fills gaps by inventing. When the draft is in `.tex` or Markdown files, it edits in place and keeps every citation, reference, label, comment and math environment untouched unless the edit concerns them. The folder includes example templates for abstracts and introductions.

When your agent uses it

  • Writing or rewriting the abstract, introduction, method or experiments of a paper
  • Polishing a paragraph so it flows and carries one message
  • Turning bullet points or a Chinese draft into publication-quality English
  • Running a reviewer-style check before submission
  • Fixing LaTeX build errors or exporting the paper to PDF

Example prompts

  • “Polish the introduction in paper/intro.tex so each paragraph carries one message.”
  • “Turn these bullet points about our ablation study into an Experiments paragraph.”
  • “Review my draft the way a skeptical reviewer would before the deadline.”
  • “Compile main.tex to PDF and fix the build errors.”

Requirements

  • A LaTeX installation for compiling `.tex` sources to PDF

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Diagnose the request, then route
  2. Get the facts before writing

What it can do on your machine

Read from SKILL.md and the folder at commit 38f4c45. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Research Paper Writing Coach loads about 1.7k tokens when it runs, and up to ~24k if it reads all its reference files. Until then it costs about 164 tokens; SKILL.md has 819 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~164
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~24k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from XiaomiMiMo/MiMo-Code at commit 38f4c45, republished under its MIT licence (© XiaomiMiMo). 819 words, ~1,743 tokens.

Download SKILL.mdSave it as .claude/skills/research-paper-writing/SKILL.md (or your agent's skills folder). This skill also uses 36 other files; get the full folder from GitHub.
name
research-paper-writing
description
Write, rewrite, and polish academic papers (ML/CV/NLP style). Use when the user drafts or revises Abstract, Introduction, Related Work, Method, Experiments, or Conclusion; asks "does this flow / 这段通顺吗 / polish this paragraph"; turns bullet points or a Chinese draft into publication-quality English; runs a pre-submission self-review or reviewer-style critique; fixes paper figures/tables/LaTeX formatting; or compiles/converts the paper to PDF (LaTeX build, 编译PDF, 转成PDF). Trigger on mentions of paper, draft, camera-ready, rebuttal-facing revision, CVPR/ICCV/NeurIPS/ICLR/ACL-style venues, or .tex files being edited for a paper.

Research Paper Writing

Act as an experienced co-author who has published at top ML/CV/NLP venues. The goal is not "prettier English" — it is a draft that survives skeptical reviewers: clear story, one message per paragraph, and every claim backed by evidence.

Step 1: Diagnose the request, then route

Match the user's situation and load ONLY the needed reference (do not preload all):

User situationWhat to doLoad
"Polish this paragraph / does this flow?"Quick polish pass (see below)references/paragraph-flow.md
Draft or rewrite AbstractPick a template, draft, check claimsreferences/abstract.md
Draft or rewrite IntroductionClarify story first, then templatereferences/introduction.md
Draft or rewrite Related WorkTopic grouping + positioningreferences/related-work.md
Draft or rewrite MethodModule triad workflowreferences/method.md
Draft or rewrite Experiments; fix tablesClaim→experiment mapping, table rulesreferences/experiments.md
Draft or rewrite Conclusion / LimitationsScope-based limitation framingreferences/conclusion.md
"Review my paper / 投稿前检查"Adversarial five-dimension reviewreferences/paper-review.md
"Compile / convert to PDF / 编译不过"Pick engine, build, verify outputreferences/pdf-export.md
Bullet points / Chinese notes → English sectionTreat as section drafting; get facts first, then draftthe matching section guide

If the user's draft lives in files (.tex, .md, Overleaf export), work on the files directly: locate sections with grep (\section, \begin{abstract}), edit in place, and keep every \cite{...}, \ref{...}, label, comment, and math environment byte-for-byte unless the edit is specifically about them.

Step 2: Get the facts before writing

Good paper writing is mostly correct facts arranged well. Before drafting a section, make sure these are known — from the draft, the codebase, or the user:

  1. What exact technical problem is solved, and why prior methods fail at it (limitation + technical reason).
  2. What the contribution is (new task / pipeline / module / finding / insight).
  3. Why the method works in essence, and its concrete advantages.
  4. What the strongest experimental numbers are.

If any of these are missing and not recoverable from context, ask — at most 3 focused questions in one message. Never fill gaps by inventing.

Hard Rules (never violate)

  1. Never fabricate. Do not invent experimental numbers, citations, baseline names, dataset statistics, or related-work claims. Use explicit placeholders ([XX.X], [CITE: sparse-view NeRF methods]) and tell the user what to fill in.
  2. Preserve technical meaning. Rewrites must keep every claim's strength and scope. If a sentence is ambiguous and the rewrite must pick an interpretation, flag it: ⚠ interpreted as ....
  3. Weaken or cut unsupported claims. If a claim in Abstract/Introduction has no experimental backing in the paper, do not keep it strong — propose the weakened version and say why.
  4. Respect double-blind. Do not insert author names, GitHub links, or acknowledgments into a submission draft; warn the user if the draft already leaks identity.
  5. Scale the output to the request. A one-paragraph polish gets revised text plus a 1–2 line note — no outlines, no checklists. Full contracts are for section rewrites and reviews only.
Show full SKILL.md (346 more words)Show less

Core Writing Principles

  1. One paragraph, one message; the first sentence states it.
  2. Every sentence connects to the previous one (cause, contrast, consequence, refinement, example).
  3. Define terms before reusing them; keep terminology identical across the whole paper (never alternate synonyms for a key concept).
  4. Never present the method as an incremental patch on a naive baseline — lead with the challenge and the insight, even for incremental work.
  5. Figures and tables are content, not decoration: clean teaser, clear pipeline figure, booktabs-style minimal-ink tables.

Workflows by request size

A. Quick polish (sentence / paragraph)
  1. Run the flow test from references/paragraph-flow.md: one message? first sentence states it? nouns self-contained? sentence-to-sentence relations explicit?
  2. Return the revised paragraph, then 1–2 lines on what changed and why.
  3. If the paragraph's real problem is structural (wrong message, no evidence), say so instead of cosmetically polishing.
B. Section draft / rewrite
  1. Confirm the section's story in a 3–7 bullet mini-outline before writing prose; on low ambiguity proceed and show the outline with the draft.
  2. Draft paragraph by paragraph — one message per paragraph, template from the section guide.
  3. Reverse-outline the result: thesis → topic sentences → evidence; fix anything that doesn't map.
  4. For Abstract/Introduction, append a claim-evidence map: Claim: ... | Evidence: ... | Status: supported / needs evidence / weakened.
C. Pre-submission review
  1. Load references/paper-review.md and read the paper as a hostile reviewer.
  2. Score the five dimensions (contribution, clarity, experimental strength, evaluation completeness, method soundness); mark each question pass / needs revision / needs new experiment.
  3. Return a prioritized fix list: rejection-level risks first, then clarity issues, then polish. Include concrete edit suggestions, not just complaints.

References

  • references/abstract.md — 3 abstract templates with annotated real examples
  • references/introduction.md — intro logic map, 4 opening / 3 challenge / 4 pipeline templates
  • references/related-work.md — topic grouping and positioning
  • references/method.md — module triad (design / motivation / advantage) workflow
  • references/experiments.md — claim→experiment planning, table/figure rules
  • references/conclusion.md — limitation framing that doesn't invite rejection
  • references/paper-review.md — adversarial five-dimension review checklist
  • references/paragraph-flow.md — paragraph clarity test, reverse outlining, transitions
  • references/pdf-export.md — compiling LaTeX/Markdown to PDF, engine choice, failure fixes, output verification
  • references/examples/ — annotated LaTeX examples cited from the section guides

© XiaomiMiMo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 36 other files (references) in packages/cli/src/skill/builtin/.bundle/research-paper-writing of XiaomiMiMo/MiMo-Code.

  • SKILL.md
  • agents/openai.yaml
  • references/abstract.md
  • references/conclusion.md
  • references/examples/abstract/template-a.md
  • references/examples/abstract/template-b.md
  • references/examples/abstract/template-c.md
  • references/examples/introduction/novel-task-challenge-decomposition.md
  • references/examples/introduction/pipeline-not-recommended-abstract-only.md
  • references/examples/introduction/pipeline-version-1-one-contribution-multi-advantages.md
  • references/examples/introduction/pipeline-version-2-two-contributions.md
  • references/examples/introduction/pipeline-version-3-new-module-on-existing-pipeline.md
  • references/examples/introduction/pipeline-version-4-observation-driven.md
  • references/examples/introduction/technical-challenge-version-1-existing-task.md
  • references/examples/introduction/technical-challenge-version-2-existing-task-insight-backed-by-traditional.md
  • references/examples/introduction/technical-challenge-version-3-novel-task.md
  • … and 21 more

Open the folder on GitHubat commit 38f4c45

Compare with similar skills

Research Paper Writing Coach next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Research Paper Writing Coach compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Research Paper Writing Coach this skillXiaomiMiMo/MiMo-Code14k—~1.7kAutomated safety check: PassMIT
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence
Nature Polishingaiskillstore/marketplace4301 repos~1.3kAutomated safety check: PassNone
LLM Reviewer Bias DefenseMichael-Jiahao-Zhang/game-the-llm-reviewer205—~1.5kAutomated safety check: PassMIT
Nature-Style Academic PolishingYuan1z0825/nature-skills47k—~1.5kAutomated safety check: PassApache-2.0
Paper Writingvoidful/academic-skills134—~1.9kAutomated safety check: PassMIT

Similar skills

  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated yesterday
    Research & ScienceAuto-check passed

  • Nature Polishing

    aiskillstore/marketplace

    Polish, restructure, or translate academic prose into Nature-leaning English using writing-strategy principles, curated Nature/Nature Communications article patterns, and phrase-level support from…

    430 GitHub starsUsed in 1 repo~1.3k tokens
    Research & ScienceAuto-check passed

  • LLM Reviewer Bias Defense

    Michael-Jiahao-Zhang/game-the-llm-reviewer

    Applies small, meaning-preserving rhetorical edits to a finished manuscript so wording does not trigger known LLM reviewer penalties, and delivers a change note.

    205 GitHub stars~1.5k tokensUpdated 17 days ago
    Research & ScienceAuto-check passed

  • Nature-Style Academic Polishing

    Yuan1z0825/nature-skills

    Polishes, translates or tightens existing academic prose and fixes manuscript LaTeX layout while keeping facts, terminology and evidence boundaries intact.

    47k GitHub stars~1.5k tokensUpdated yesterday
    Writing & ContentAuto-check passed

  • Paper Writing

    voidful/academic-skills

    頂級會議論文寫作技能——以嚴格 reviewer 視角指導從草稿到終稿的完整寫作流程。當使用者要寫論文、改善論文草稿、修改特定章節（introduction、method、experiments、conclusion）、潤色學術英文、回應 reviewer 意見，或問「這段怎麼寫」時，一定要使用此技能。觸發詞包括：寫論文、paper writing、improve my…

    134 GitHub stars~1.9k tokensUpdated 6 mo ago
    Research & ScienceAuto-check passed

  • Paperjury

    Spark-To-Paper-Skills/paperjury

    Three modes for CS-conference papers (CVPR/ICCV/ECCV vision, ACL/EMNLP/NAACL NLP, ICLR/NeurIPS/ICML/AAAI ML).

    1.2k GitHub stars~5.3k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed

More from XiaomiMiMo/MiMo-Code

All 22 skills in this repo

  • Agent Skill Creator

    XiaomiMiMo/MiMo-Code

    Interactive guide for creating, reviewing and fixing agent skills (SKILL.md folders), covering structure, frontmatter rules, trigger phrases and validation before sharing.

    14k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

  • Paper Research on arXiv

    XiaomiMiMo/MiMo-Code

    Searches arXiv, fetches metadata, generates BibTeX, downloads PDFs and finds citations and related papers using a bundled Python script.

    14k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • DOCX Toolkit

    XiaomiMiMo/MiMo-Code

    Produces, edits and reads Microsoft Word files through python-docx and lxml, with a decision table for picking the lightest workflow for a given task.

    14k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

  • Drive MiMo Code

    XiaomiMiMo/MiMo-Code

    Lets one MiMoCode process drive another, headless with JSON events or interactively through tmux, to test behavior and visual regressions with parseable evidence.

    14k GitHub stars~3.9k tokensUpdated yesterday
    Auto-check passed

  • PDF Toolkit

    XiaomiMiMo/MiMo-Code

    Reads, transforms, composes and fills PDFs with Python scripts for extraction, merging, watermarking, encryption, OCR and form filling.

    14k GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

  • XLSX Spreadsheet Toolkit

    XiaomiMiMo/MiMo-Code

    Builds, edits, cleans, recalculates and reads Excel workbooks and CSV files with openpyxl and pandas, plus LibreOffice for recalculation and PDF export.

    14k GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Research Paper Writing Coach

What does Research Paper Writing Coach do?

Drafts, rewrites and reviews academic papers in ML, CV and NLP style, section by section, and compiles LaTeX sources to PDF. The agent plays an experienced co-author aiming for a draft that survives skeptical reviewers, with a clear story, one message per paragraph and evidence behind every claim. It first routes the request using a table that maps each situation to one reference guide, loading only that guide: paragraph polish, abstract, introduction, related work, method, experiments, conclusion and limitations, a pre-submission review in five adversarial dimensions, and PDF export.

When should I use Research Paper Writing Coach?

Research Paper Writing Coach fits situations like: writing or rewriting the abstract, introduction, method or experiments of a paper; polishing a paragraph so it flows and carries one message; turning bullet points or a Chinese draft into publication-quality English; running a reviewer-style check before submission.

How do I install Research Paper Writing Coach in Claude Code?

Run `npx skills add XiaomiMiMo/MiMo-Code --skill research-paper-writing -a claude-code`. Or copy the skill folder (packages/cli/src/skill/builtin/.bundle/research-paper-writing in XiaomiMiMo/MiMo-Code) into .claude/skills/research-paper-writing in your project. Claude Code loads it when a task matches its description.

How do I install Research Paper Writing Coach in Codex?

Run `npx skills add XiaomiMiMo/MiMo-Code --skill research-paper-writing -a codex`. Or copy the skill folder (packages/cli/src/skill/builtin/.bundle/research-paper-writing in XiaomiMiMo/MiMo-Code) into .agents/skills/research-paper-writing in your project. Codex loads it when a task matches its description.

Can I use Research Paper Writing Coach in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add XiaomiMiMo/MiMo-Code --skill research-paper-writing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-paper-writing, .gemini/skills/research-paper-writing, .github/skills/research-paper-writing and .opencode/skills/research-paper-writing in your project.

What does Research Paper Writing Coach need to run?

SKILL.md names no scripts, command-line tools or credentials: Research Paper Writing Coach is instructions for the agent only. Our summary lists: A LaTeX installation for compiling `.tex` sources to PDF.

Does Research Paper Writing Coach access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Research Paper Writing Coach safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Research Paper Writing Coach use?

Research Paper Writing Coach is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Research Paper Writing Coach use?

About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 23k tokens, read only when the agent opens those files.

What are the alternatives to Research Paper Writing Coach?

Skills that share tags, products or a category with Research Paper Writing Coach: Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars), Nature Polishing (aiskillstore/marketplace, 430 stars), LLM Reviewer Bias Defense (Michael-Jiahao-Zhang/game-the-llm-reviewer, 205 stars) and Nature-Style Academic Polishing (Yuan1z0825/nature-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Research Paper Writing Coach?

XiaomiMiMo (a GitHub organization) maintains it in XiaomiMiMo/MiMo-Code, which has 13,616 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 9, 2026.

Source: XiaomiMiMo/MiMo-Code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.