paper-write
Skill9 starsChanged 3 months agoMITView on GitHub
Prompt-only by default in the lightweight pack; Claude/Gemini reviewer transport is explicit opt-in. Draft LaTeX paper section by section from an outline. Use when user says \"写论文\", \"write paper\", \"draft LaTeX\", \"开始写\", or wants to generate LaTeX content from a paper plan.
12 other projects use a version of this, 6 of them edited.
Adopted by
Most recently taken up by
- cabbage2000-lab/paper-tutor-skillstheir own version, first seen Nov 8, 2026
- wangyi0403/dl-research-workflowtheir own version, first seen Oct 13, 2026
- PUNCKe/manuscript-context-integritytheir own version, first seen Sep 19, 2026
- talhaMah56/claude_skillsedited, first seen Sep 12, 2026
- wanshuiyin/Auto-claude-code-research-in-sleepedited, first seen Jul 15, 2026
- catalsqlb-cmd/Prism-Hedited, first seen May 29, 2026
Used with
Projects with it also use paper-illustration, deepxiv and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
raja21068Skillpaper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says \"生成图表\", \"画架构图\", \"AI绘图\", \"paper illustration\", \"generate diagram\", or needs visual figures for papers.
Also in 6 projects that use this
raja21068Skilldeepxiv
Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.
Also in 4 projects that use this
Yusong-EnceladusSkilldse-loop
Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says \"DSE\", \"design space exploration\", \"sweep parameters\", \"optimize\", \"find best config\", or wants iterative parameter tuning.
Also in 4 projects that use this
- +3 more from raja21068
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 6
- wanshuiyin/Auto-claude-code-research-in-sleep★ 19k32% same
- Chanw-research/claude-code-paper-writing★ 4238% same
- catalsqlb-cmd/Prism-H★ 1639% same
- Yusong-Enceladus/claude-skills★ 895% same
- raja21068/AutoResearch★ 238% same
- talhaMah56/claude_skills★ 039% same
Wrote their own version · 6
- xstongxue/best-skills★ 2.9ksame name
- cabbage2000-lab/paper-tutor-skills★ 48same name
- b1mango/Agent-Skills★ 4same name
- wangyi0403/dl-research-workflow★ 4same name
- PUNCKe/manuscript-context-integrity★ 2same name
- LaoK2017/Agent-Skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- autodl-hpcSkill
- experiment-bridgeSkill
- experiment-planSkill
- human-toneSkill
- idea-discoverySkill
- paper-visualizationSkill
- paper-writingSkill
- rebuttalSkill
- research-blueprintSkill
- research-pipelineSkill
- research-repo-architectSkill
- research-reviewSkill
- resubmit-pipelineSkill
- autodl-hpcSkill
- auto-paper-improvement-loopSkill
- auto-review-loopSkill
- novelty-checkSkill
- paper-figureSkill
- paper-planSkill
- paper-writeSkill
- research-refineSkill
- research-reviewSkill
- experiment-bridgeSkill
- experiment-planSkill
- auto-paper-improvement-loopSkill
- auto-review-loopSkill
- grant-proposalSkill
- idea-creatorSkill
- idea-discoverySkill
- novelty-checkSkill
- paper-figureSkill
- paper-planSkill
- paper-posterSkill
- paper-slidesSkill
- paper-writingSkill
- research-refineSkill
- research-reviewSkill
- human-toneSkill
- idea-discoverySkill
- paper-visualizationSkill
- paper-writingSkill
- rebuttalSkill
- research-blueprintSkill
- research-pipelineSkill
- research-repo-architectSkill
- research-reviewSkill
- resubmit-pipelineSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
34 rules. 7 are common, 11 are distinctive, and 16 are very specific to this project.
7
Common
Most of the 9 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
16
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Write the review prompt under review-prompts/ and ask the user to run it in a separate conversation with the relevant skills enabled.
- Distinctive: line 16
Do not call Claude/Gemini reviewer MCP bridges, APIs, or follow-up status tools by default.
- Very specific: line 18
Use pasted review text as the external verdict, then write compact summaries such as REVIEW_SUMMARY.md, NEXT_ACTIONS.md, or the …
- Distinctive: line 20
Keep heavy experiments AutoDL/HPC-gated and user-approved.
- Very specific: line 43
If no PAPER_PLAN.md exists, ask the user to run /paper-plan first or provide a brief outline.
- Very specific: line 92
Section files are FLEXIBLE: If the paper plan has 6-8 sections, create corresponding files (e.g., 4_theory.tex, 5_experiments.tex, …
- Very specific: line 98
If paper/ already exists, back up to paper-backup-{timestamp}/ before overwriting.
- Very specific: line 100
CRITICAL: Clean stale files: When changing section structure (e.g., 5 sections → 7 sections), delete section files that are no longer …
- Common: line 106
All standard packages (amsmath, hyperref, cleveref, booktabs, etc.)
- Very specific: line 110
Create section files matching PAPER_PLAN structure
- Common: line 119
Create shared math macros based on the paper's notation:
- Common: line 143
Must be self-contained (understandable without reading the paper)
- Common: line 147
No citations, no undefined acronyms
- Distinctive: line 159
Keep Related Work compact by default.
- Common: line 162
Do NOT just list papers — synthesize and compare
- Very specific: line 167
Use \begin{definition}, \begin{theorem} environments for formal statements
- Common: line 174
Start with experimental setup (datasets, baselines, metrics, implementation details)
- Common: line 177
Every claim from the introduction must have supporting evidence here
- Very specific: line 200
Check existing .bib files in the project/narrative docs
- Very specific: line 201
If not found and DBLP_BIBTEX = true, use the verified fetch chain below
- Very specific: line 202
If not found and DBLP_BIBTEX = false, search arXiv/Scholar for correct BibTeX
- Very specific: line 204
Write references.bib containing ONLY cited entries (no bloat)
- Very specific: line 226
If both DBLP and CrossRef return nothing, mark the entry with % [VERIFY] comment.
- Distinctive: line 243
Every BibTeX entry must have: author, title, year, venue/journal
- Distinctive: line 244
Prefer published venue versions over arXiv preprints (if published)
- Very specific: line 245
Use consistent key format: {firstauthor}{year}{keyword} (e.g., ho2020denoising)
- Distinctive: line 247
Remove duplicate entries (same paper with different keys)
- Distinctive: line 251
After drafting all sections, scan for common AI writing patterns and fix them:
- Distinctive: line 260
Remove filler: "It is worth noting that", "Importantly,", "Notably,"
- Distinctive: line 261
Avoid rule-of-three lists ("X, Y, and Z" appearing repeatedly)
- Distinctive: line 262
Don't start consecutive sentences with "This" or "We"
- Very specific: line 287
After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until …
- Distinctive: line 293
After drafting all sections:
- Very specific: line 328
Large file handling: If the Write tool fails due to file size, immediately retry using Bash (cat << 'EOF' > file) to write in chunks.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Override for Codex users who want Gemini, not a second Codex agent, to act as the reviewer. Install this package after
skills/skills-codex/*.
Customized Pack Defaults
This reviewer overlay is opt-in transport only. In the customized lightweight pack, default to prompt-only review unless the user explicitly asks to use this overlay reviewer backend:
- Write the review prompt under
review-prompts/and ask the user to run it in a separate conversation with the relevant skills enabled. - Do not call Claude/Gemini reviewer MCP bridges, APIs, or follow-up status tools by default.
- Use pasted review text as the external verdict, then write compact summaries
such as
REVIEW_SUMMARY.md,NEXT_ACTIONS.md, or the skill-specific log. - Keep heavy experiments AutoDL/HPC-gated and user-approved; local work stays at edits, tests, lint, dry-runs, and tiny smoke checks.
Paper Write: Section-by-Section LaTeX Generation
Draft a LaTeX paper based on: $ARGUMENTS
Constants
- REVIEWER_MODEL =
gemini-review— Gemini reviewer invoked through the localgemini-reviewMCP bridge. SetGEMINI_REVIEW_MODELif you need a specific Gemini model override. - TARGET_VENUE =
ICLR— Default venue. Supported:ICLR,NeurIPS,ICML. Determines style file and formatting. - ANONYMOUS = true — If true, use anonymous author block. Set
falsefor camera-ready. - MAX_PAGES = 9 — Main body page limit. Counts from first page to end of Conclusion section. References and appendix are NOT counted.
- DBLP_BIBTEX = true — Fetch real BibTeX from DBLP/CrossRef instead of LLM-generated entries. Eliminates hallucinated citations. Zero install required. Set
falseto use legacy behavior (LLM search +[VERIFY]markers).
Inputs
- PAPER_PLAN.md — outline with claims-evidence matrix, section plan, figure plan (from
/paper-plan) - NARRATIVE_REPORT.md — the research narrative (primary source of content)
- Generated figures — PDF/PNG files in
figures/(from/paper-figure) - LaTeX includes —
figures/latex_includes.tex(from/paper-figure) - Bibliography — existing
.bibfile, or will create one
If no PAPER_PLAN.md exists, ask the user to run /paper-plan first or provide a brief outline.
Templates
Venue-Specific Setup
The skill includes conference templates in templates/. Select based on TARGET_VENUE:
ICLR:
\documentclass{article}
\usepackage{iclr2026_conference,times}
% \iclrfinalcopy % Uncomment for camera-readyNeurIPS:
\documentclass{article}
\usepackage[preprint]{neurips_2025}
% \usepackage[final]{neurips_2025} % Camera-readyICML:
\documentclass[accepted]{icml2025}
% Use [accepted] for camera-readyProject Structure
Generate this file structure:
paper/
├── main.tex # master file (includes sections)
├── iclr2026_conference.sty # or neurips_2025.sty / icml2025.sty
├── math_commands.tex # shared math macros
├── references.bib # bibliography (filtered — only cited entries)
├── sections/
│ ├── 0_abstract.tex
│ ├── 1_introduction.tex
│ ├── 2_related_work.tex
│ ├── 3_method.tex # or preliminaries, setup, etc.
│ ├── 4_experiments.tex
│ ├── 5_conclusion.tex
│ └── A_appendix.tex # proof details, extra experiments
└── figures/ # symlink or copy from project figures/Section files are FLEXIBLE: If the paper plan has 6-8 sections, create corresponding files (e.g., 4_theory.tex, 5_experiments.tex, 6_analysis.tex, 7_conclusion.tex).
Workflow
Step 0: Backup and Clean
If paper/ already exists, back up to paper-backup-{timestamp}/ before overwriting. Never silently destroy existing work.
CRITICAL: Clean stale files. When changing section structure (e.g., 5 sections → 7 sections), delete section files that are no longer referenced by main.tex. Stale files (e.g., old 5_conclusion.tex left behind when conclusion moved to 7_conclusion.tex) cause confusion and waste space.
Step 1: Initialize Project
- Create
paper/directory - Copy venue template from
templates/— the template already includes:- All standard packages (amsmath, hyperref, cleveref, booktabs, etc.)
- Theorem environments with
\crefname{assumption}fix - Anonymous author block
- Generate
math_commands.texwith paper-specific notation - Create section files matching PAPER_PLAN structure
Author block (anonymous mode):
\author{Anonymous Authors}Step 2: Generate math_commands.tex
Create shared math macros based on the paper's notation:
% math_commands.tex — shared notation
\newcommand{\R}{\mathbb{R}}
\newcommand{\E}{\mathbb{E}}
\DeclareMathOperator*{\argmin}{arg\,min}
\DeclareMathOperator*{\argmax}{arg\,max}
% Add paper-specific notation hereStep 3: Write Each Section
Process sections in order. For each section:
- Read the plan — what claims, evidence, citations belong here
- Read NARRATIVE_REPORT.md — extract relevant content, findings, and quantitative results
- Draft content — write complete LaTeX (not placeholders)
- Insert figures/tables — use snippets from
figures/latex_includes.tex - Add citations — use
\citep{}/\citet{}(all three venues usenatbib)
Section-Specific Guidelines
§0 Abstract:
- Must be self-contained (understandable without reading the paper)
- Structure: problem → approach → key result → implication
- Include one concrete quantitative result
- 150-250 words (check venue limit)
- No citations, no undefined acronyms
- No
\begin{abstract}— that's in main.tex
§1 Introduction:
- Open with a compelling hook (1-2 sentences, problem motivation)
- State the gap clearly ("However, ...")
- List contributions as a numbered or bulleted list
- End with a brief roadmap ("The rest of this paper is organized as...")
- Include the main result figure if space allows
- Target: 1.5 pages
§2 Related Work:
- Keep Related Work compact by default; for IEEE/Overleaf-style two-column papers, plan Related Work plus Conclusion to fit within about 0.8 page total unless the target venue explicitly requires more.
- Organize by category using
\paragraph{Category Name.} - Each category: 1 paragraph summarizing the line of work + 1-2 sentences positioning this paper
- Do NOT just list papers — synthesize and compare
- End each paragraph with how this paper relates/differs
§3 Method / Preliminaries / Setup:
- Define notation early (reference math_commands.tex)
- Use
\begin{definition},\begin{theorem}environments for formal statements - For theory papers: include proof sketches of key results in main body, full proofs in appendix
- For theory papers: include a comparison table of prior bounds vs. this paper
- Include algorithm pseudocode if applicable (
algorithm2eoralgorithmic) - Target: 1.5-2 pages
§4 Experiments:
- Start with experimental setup (datasets, baselines, metrics, implementation details)
- Main results table/figure first
- Then ablations and analysis
- Every claim from the introduction must have supporting evidence here
- Target: 2.5-3 pages
§5 Conclusion:
- Summarize contributions (NOT copy-paste from intro — rephrase)
- Limitations (be honest — reviewers appreciate this)
- Future work (1-2 concrete directions)
- Ethics statement and reproducibility statement (if venue requires)
- Target: 0.5 pages
Appendix:
- Proof details (full proofs of main-body theorems)
- Additional experiments, ablations
- Implementation details, hyperparameter tables
- Additional visualizations
Step 4: Build Bibliography
CRITICAL: Only include entries that are actually cited in the paper.
- Scan all
\citep{}and\citet{}references in the drafted sections - Build a citation key list
- For each citation key:
- Check existing
.bibfiles in the project/narrative docs - If not found and DBLP_BIBTEX = true, use the verified fetch chain below
- If not found and DBLP_BIBTEX = false, search arXiv/Scholar for correct BibTeX
- NEVER fabricate BibTeX entries — mark unknown ones with
[VERIFY]comment
- Check existing
- Write
references.bibcontaining ONLY cited entries (no bloat)
Verified BibTeX Fetch (when DBLP_BIBTEX = true)
Three-step fallback chain — zero install, zero auth, all real BibTeX:
Step A: DBLP (best quality — full venue, pages, editors)
# 1. Search by title + first author
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3"
# 2. Extract DBLP key from result (e.g., conf/nips/VaswaniSPUJGKP17)
# 3. Fetch real BibTeX
curl -s "https://dblp.org/rec/{key}.bib"Step B: CrossRef DOI (fallback — works for arXiv preprints)
# If paper has a DOI or arXiv ID (arXiv DOI = 10.48550/arXiv.{id})
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}"Step C: Mark [VERIFY] (last resort)
If both DBLP and CrossRef return nothing, mark the entry with % [VERIFY] comment. Do NOT fabricate.
Why this matters: LLM-generated BibTeX frequently hallucinates venue names, page numbers, or even co-authors. DBLP and CrossRef return publisher-verified metadata. Upstream skills (/research-lit, /novelty-check) may mention papers from LLM memory — this fetch chain is the gate that prevents hallucinated citations from entering the final .bib.
Automated bib cleaning — use this Python pattern to extract only cited entries:
import re
# 1. Grep all \citep{...} and \citet{...} from all .tex files
# 2. Extract unique keys (handle multi-cite like \citep{a,b,c})
# 3. Parse the full .bib file, keep only entries whose key is in the cited set
# 4. Write the filtered bibThis prevents bib bloat (e.g., 948 lines → 215 lines in testing).
Citation verification rules (from claude-scholar + Imbad0202):
- Every BibTeX entry must have: author, title, year, venue/journal
- Prefer published venue versions over arXiv preprints (if published)
- Use consistent key format:
{firstauthor}{year}{keyword}(e.g.,ho2020denoising) - Double-check year and venue for every entry
- Remove duplicate entries (same paper with different keys)
Step 5: De-AI Polish (from kgraph57/paper-writer-skill)
After drafting all sections, scan for common AI writing patterns and fix them:
Content patterns to fix:
- Significance inflation ("groundbreaking", "revolutionary" → use measured language)
- Formulaic transitions ("In this section, we..." → remove or vary)
- Generic conclusions ("This work opens exciting new avenues" → be specific)
Language patterns to fix (watch words):
- Replace: delve, pivotal, landscape, tapestry, underscore, noteworthy, intriguingly
- Remove filler: "It is worth noting that", "Importantly,", "Notably,"
- Avoid rule-of-three lists ("X, Y, and Z" appearing repeatedly)
- Don't start consecutive sentences with "This" or "We"
Step 6: Cross-Review with REVIEWER_MODEL
Send the complete draft to Gemini review:
mcp__gemini-review__review_start:
prompt: |
Review this [VENUE] paper draft (main body, excluding appendix).
Focus on:
1. Does each claim from the intro have supporting evidence?
2. Is the writing clear, concise, and free of AI-isms?
3. Any logical gaps or unclear explanations?
4. Does it fit within [MAX_PAGES] pages (to end of Conclusion)?
5. Is related work sufficiently comprehensive (≥1 page)?
6. For theory papers: are proof sketches adequate?
7. Are figures/tables clearly described and properly referenced?
For each issue, specify: severity (CRITICAL/MAJOR/MINOR), location, and fix.
[paste full draft text]After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until done=true. Treat the completed status payload's response as the reviewer output, and save the completed threadId for any follow-up round.
Apply CRITICAL and MAJOR fixes. Document MINOR issues for the user.
Step 7: Reverse Outline Test (from Research-Paper-Writing-Skills)
After drafting all sections:
- Extract topic sentences — pull the first sentence of every paragraph
- Read them in sequence — they should form a coherent narrative on their own
- Check claim coverage — every claim from the Claims-Evidence Matrix must appear
- Check evidence mapping — every experiment/figure must support a stated claim
- Fix gaps — if a topic sentence doesn't advance the story, rewrite the paragraph
Step 8: Final Checks
Before declaring done:
- All
\ref{}and\label{}match (no undefined references) - All
\citep{}/\citet{}have corresponding BibTeX entries - No author information in anonymous mode
- Figure/table numbering is correct
- Page count within MAX_PAGES (main body to Conclusion end)
- No TODO/FIXME/XXX markers left in the text
- No
[VERIFY]markers left unchecked - Abstract is self-contained (understandable without reading the paper)
- Title is specific and informative (not generic)
- Related work is ≥1 full page
- references.bib contains ONLY cited entries (no bloat)
- No stale section files — every .tex in
sections/is\inputed bymain.tex - Section files match main.tex — file numbering and
\inputpaths are consistent
Output Protocols
Follow these shared protocols for all output files:
- Output Versioning Protocol — write timestamped file first, then copy to fixed name
- Output Manifest Protocol — log every output to docs/project/OUTPUT_MANIFEST.md
- Output Language Protocol — respect the project's language setting
Key Rules
- Large file handling: If the Write tool fails due to file size, immediately retry using Bash (
cat << 'EOF' > file) to write in chunks. Do NOT ask the user for permission — just do it silently. - Do NOT generate author names, emails, or affiliations — use anonymous block or placeholder
- Write complete sections, not outlines — the output should be compilable LaTeX
- One file per section — modular structure for easy editing
- Every claim must cite evidence — cross-reference the Claims-Evidence Matrix
- Compile-ready — the output should compile with
latexmkwithout errors (modulo missing figures) - No over-claiming — use hedging language ("suggests", "indicates") for weak evidence
- Venue style matters — all three venues (ICLR/NeurIPS/ICML) use
natbib(\citep/\citet) - Page limit = main body to Conclusion — references and appendix do NOT count
- Clean bib — references.bib must only contain entries that are actually
\cited - Section count is flexible — match PAPER_PLAN structure, don't force into 5 sections
- Backup before overwrite — never destroy existing
paper/directory without backing up
Writing Quality Reference
Principles from Research-Paper-Writing-Skills:
- One message per paragraph — each paragraph makes exactly one point
- Topic sentence first — the first sentence states the paragraph's message
- Explicit transitions — connect paragraphs with logical connectors
- Reverse outline test — extract topic sentences; they should form a coherent narrative
De-AI patterns from kgraph57/paper-writer-skill:
- No AI watch words — delve, pivotal, landscape, tapestry, underscore
- No significance inflation — groundbreaking, revolutionary, paradigm shift
- No formulaic structures — vary sentence openings and transitions
Acknowledgements
Writing methodology adapted from Research-Paper-Writing-Skills (CCF award-winning methodology). Citation verification from claude-scholar and Imbad0202/academic-research-skills. De-AI polish from kgraph57/paper-writer-skill. Backup mechanism from baoyu-skills.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

