paper-writing
Skill1 starsChanged 3 months agoMITView on GitHub
Academic paper / preprint / position paper の draft skill。Title + outline + section drafting + abstract + references の手順正本。Primary source への直接 access を強制し、claim と cite の 1:1 mapping を author に握らせる。SSRN / arXiv / Zenodo / journal venue 向けに使う。Voice 規約・Source Fidelity 規約・Citation 規約は orchestrator skill `paper-ecosystem` を参照する。
36 other projects use a version of this.
Adopted by
Most recently taken up by
- kinhluan/skillstheir own version, first seen Nov 8, 2026
- 70asunflower/70asunflower-skillstheir own version, first seen Nov 8, 2026
- SNL-UCSB/paper-writing-skilltheir own version, first seen Nov 4, 2026
- VeryMath/AI4Math-Writingtheir own version, first seen Nov 3, 2026
- Deadpoolmine/systematic-research-skillstheir own version, first seen Nov 1, 2026
- takayoshitoyoda05/claude-ml-templatetheir own version, first seen Oct 20, 2026
Used with
Projects with it also use ml-training-recipe, replication and 10 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.
getcompanion-aiSkillml-training-recipe
Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, train, reproduce, or choose a practical ML method, dataset, hyperparameter setup, or benchmark recipe.
Also in 3 projects that use this
getcompanion-aiSkillreplication
Plan a replication of a paper, claim, or benchmark, and execute only after an explicit environment choice. Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package.
Also in 3 projects that use this
brainbytes-devSkillalpha-research
Also in 3 projects that use this
JaimeParkerSkillpaper-code-audit
Perform three-way cross-validation of a research paper by comparing the original paper text (via Zotero), official code implementation (via Git), and personal Obsidian notes. Use this skill whenever the user wants to "audit a paper", "verify paper claims against code", "cross-check notes with implementation", "triangulate paper + code + notes", "find discrepancies between paper and code", or mentions wanting a deep, structured comparison of a paper's claims against its implementation and their own notes. Also trigger when the user asks to "analyze this paper thoroughly" with code available, or when they want to systematically reconcile what the paper says, what the code does, and what their notes claim.
Also in 3 projects that use this
JimLiuSkillpdf-explore
Use this skill when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, or find/list/extract every instance of something across the whole document (datasets, benchmarks, citations, figures, table rows, accession numbers — including appendices). Skip it only for a single lookup of 1–4 pages quoted in your very next response — `read_file(pages=[...])` attaches pages as images that are dropped from context after one turn, so multi-section answers end up re-reading the same ranges repeatedly. Parses the PDF once in the Python kernel: `pdf_pages` (pages as persistent text), `pdf_outline` (TOC), `pdf_scan` (rank pages by relevance), `pdf_map`/`pdf_extract` (per-page summary / structured fields via parallel haiku calls). For PDF creation/manipulation, use reportlab/pypdf directly.
Also in 4 projects that use this
Yusong-EnceladusSkillresearch-review
Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
Also in 6 projects that use this
- +1 more from getcompanion-ai
Other versions36 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 36
- wanshuiyin/Auto-claude-code-research-in-sleep★ 19ksame name
- advaitpaliwal/feynman★ 10ksame name
- companion-inc/feynman★ 10ksame name
- getcompanion-ai/feynman★ 10ksame name
- MLNLP-World/Paper-Writing-Tips★ 4.7ksame name
- ZimoLiao/scholaraio★ 585same name
- EvoScientist/EvoSkills★ 481same name
- SNL-UCSB/paper-writing-skill★ 249same name
- voidful/academic-skills★ 126same name
- TenureAI/PhD-Zero★ 52same name
26 more not listed
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 repository3 other files it gives its agents.
- llms-full.txtllms.txt
- llms.txtllms.txt
- paper-ecosystemSkill
The file
Files
paper-writing — Academic paper draft の手順
Position paper / preprint / journal-style article の draft 手順を、paper-ecosystem orchestrator の正本ルールに従って organize する skill。
When to Activate
- SSRN / arXiv / Zenodo / journal venue 向け paper を draft する
- 既存の essay 連作 / ADR 群 / 実装 history から paper を抽出する
- Position paper の outline 確定後、各 section の drafting に入る
- Preprint v1 → v2 の改訂 (significant rewriting を伴う場合)
Activation 外
- Blog post / essay (人間 primary、informal) →
writing-ecosystemを使う - llms.txt / FAQ (AI primary) →
llms-txt-writerを使う - README (project doc) →
readme-writerを使う / CHANGELOG → skill を介さず直接書く
Pre-draft Checklist
Paper draft に入る前に、author は次を完了させる:
1. Primary source list の確立
Paper が cite する primary source をリスト化する:
- 引用元 essays / blog posts (URL + 日付 + 1 行 summary)
- 引用元 ADRs / spec docs (repo path + version + 1 行 summary)
- 引用元 external papers (Author YEAR + arXiv ID / DOI + 1 行 summary)
- 引用元 standards / framework docs (Org YEAR + standard ID)
各 primary source は paper draft 時に 直接読む ことができる状態にする (URL アクセス可、repo clone 済み、PDF 取得済み)。
2. Glossary / summary への依拠を 避ける
Primary source の代わりに repo の glossary / summary / secondary doc を citation 元として参照しない。Secondary 側の drift が paper に伝播するため (詳細: paper-ecosystem skill の Source Fidelity Rules)。
Secondary を参照するのは次の 2 つのみ:
- Term の definition 整合性 check (paper の definition と glossary の definition が一致するか確認)
- Reference list の format 参考 (どの fields を含めるかの style 例)
3. Claim ↔ cite source の 1:1 mapping
Outline 段階で、各 section の core claim を 1 文で書き出し、各 claim に対応する cite source を 1:1 で対応させる。Mapping が曖昧な claim は draft に入れる前に解消する。
Format 例:
§3 core claim: "Redirect failure has two architecturally distinct modes — principled (intrinsic to autonomous loops) and artificial (workflow work routed through autonomous loops)."
Cite sources:
- Essay 5 (zenn-content/articles-en/react-agent-business-quadrant-2.md, 2026-04-30)
- ADR-0009 §Context (agent-attribution-practice/docs/adr/0009-triage-before-autonomy.md)
- Elish (2019) "Moral Crumple Zones"4. Sub-classification の preservation
Primary source が概念に sub-form / sub-cell / sub-type を与えている場合、paper の term introduction で明示する。Flat 化は drift (詳細: paper-ecosystem skill の Vocabulary Consistency Rules)。
Section Template (position paper / preprint)
標準的な 9-section 構造:
- Title page — Title + subtitle + author + ORCID + version + companion repository + license
- Abstract — 250-300 words、3 段落構造 (下記)
- Introduction — Problem statement + thesis preview + section roadmap
- [Body sections] — Paper の core contribution。3-6 sections 程度
- Relationship to existing frameworks — 短い (1 paragraph 〜 1 page)、competing frameworks との関係
- Conclusion — Thesis reprise + open questions
- References — APA-like simplified
- Acknowledgements (任意)
- Appendix (任意)
Journal-style article では venue の house style に従って section 番号 / heading 階層 / table & figure 配置を調整する。
Abstract Structure (250-300 words)
3 段落:
- Problem statement (~70-90 words) — どの phenomenon を取り上げ、現状の discourse の何が不足か
- Contributions (~120-150 words) — Paper の core contribution 2-3 個を明示。各 contribution に対し what / why / how が 1 文ずつ
- Consequence (~60-90 words) — Contribution が paper の audience に何をもたらすか、unresolved な open questions の言及
Keywords (5-8 個) を abstract 直下に置く。
References Format
正本は paper-ecosystem skill の Citation Format Rules。Source type 別の必須項目と
組版形を 1 つの表に持つ(2026-08-15 に本 skill から組版列を移設・統合)。DOI / arXiv ID の
inclusion 規約と orphan citation の禁止も同節。ここには再掲しない — 分けていた結果
Industry 行のラベルが doc / report に分岐していた。
Multi-language Convention (任意)
正本は paper-ecosystem skill の Multi-language Paper Convention。ここには再掲しない —
本 skill にあったコピーは 5 項目のうち 2 つを落としており(各ファイル冒頭の Language: ヘッダ行と、
著者校正は日本語版で行うという校正フェーズの例外)、ここで止まった読者が校正の運用を
知らないまま進む状態だった(2026-08-15 に削除)。
Writing Process (section drafting)
各 section の draft 手順:
- Section claim を 1 文で書き出す (pre-draft checklist の output を再確認)
- Section opening は具体物: 例 / 既知の現象 / cited source からの引用、抽象的 framing から始めない
- Claim を支える evidence を直後に置く (cite と 1:1)
- Section transition を section 末尾で明示: 次 section に何を渡すか、現 section の何が前提として持ち越されるか
- Subordinate paragraphs は claim を分解する direction か、counter / alternative を treat する direction、いずれかに揃える (両方混在は flow を弱める)
各 section draft 完了後、paper-reviewer agent + source-fidelity-checker agent + vocabulary-consistency-checker agent + clarity-reviewer agent を 並列 で起動して review する(正本の paper-ecosystem が定める 4 agent。2026-08-23 まで本 skill は 3 つしか列挙しておらず、この skill だけを読む書き手は 4 分の 3 しか回していなかった)。
Quality Gate (deposit 前)
Deposit 直前に次を確認:
- 全 section が
paper-reviewerを pass している - 全 claim が
source-fidelity-checkerで ALIGNED または PARTIAL 判定 (DRIFT は残っていない) - 全 term が
vocabulary-consistency-checkerを pass している (sub-classification の introduction 明示済み) clarity-reviewerの verdict が PASS(初見読者の明瞭性。造語過多・タイトル軸ずれ・編集メタ語り・内部文脈依存)citation-formatterで orphan citation 0、cite ↔ references 1:1- 脚注の 1:1 marker 検証(
paper-ecosystemの Two-Layer Density Rules) - Abstract の word count が venue 標準範囲内
- DOI / arXiv ID / URL がすべて valid
- Multi-language 版がある場合、英語版と内容で乖離していない
詳細な dimension は paper-ecosystem skill 内 4 つの canonical rules sections を参照。
Related
paper-ecosystemskill — Source Fidelity / Vocabulary Consistency / Academic Voice / Citation Format の正本。本 skill が依拠する orchestratorpaper-revieweragent — Section draft 完了後の structure reviewsource-fidelity-checkeragent — Section draft 完了後の cite-claim 整合 verifyvocabulary-consistency-checkeragent — Section draft 完了後の term 一貫性 verifyclarity-revieweragent — 初見読者の明瞭性(paper-ecosystemが定める 4 agent panel の 1 つ)citation-formatteragent — Deposit 直前の cite ↔ references final gatepaper-depositskill — citation gate 通過後の Zenodo deposit 手順writing-ecosystemskill — Blog post / essay 用、本 skill ではなくあちらllms-txt-writerskill — AI 向け doc 用、本 skill ではなくあちら
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.

