Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Azzygoatcoder/agent-useful-skills --skill paper-writinggit clone --depth 1 https://github.com/Azzygoatcoder/agent-useful-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/azzygoatcoder/agent-useful-skills/paper-writing)<a href="https://agentmods.dev/skills/azzygoatcoder/agent-useful-skills/paper-writing"><img src="https://agentmods.dev/badge/skills/azzygoatcoder/agent-useful-skills/paper-writing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/azzygoatcoder/agent-useful-skills/paper-writing"><img src="https://agentmods.dev/badge/skills/azzygoatcoder/agent-useful-skills/paper-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.01286 |
| Opus 5 | $0.00040 | $0.00643 |
| Sonnet 5 | $0.00016 | $0.00257 |
| Haiku 4.5 | $0.00008 | $0.00129 |
Grade A, and why
paper-writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Writing — 论文写作一条龙
科研骨架的写作编排层（PDF 侧）。把 LaTeX 模板库 + 编译脚本 + 制图 + 评审串成一条龙。Office 侧（Word/PPT）走 office-tools，本 skill 管 PDF。
场景判定（先定文档类型，再选路线）
| 场景 | 触发 | 模板 | 引擎 | 页数规则 |
|---|---|---|---|---|
| A. 会议投稿 | 写论文/投稿（DAC/ICCAD/ICML/NeurIPS） | ieee-conf / icml / neurips |
pdflatex | ML 正文≤8（References 前）/ IEEE 全算≤6 |
| B. 学位论文 | 毕设/硕博 | sjtuthesis（--src 指向 clone） |
xelatex | 整本 |
| C. 报告 | 实习/PRP 中期/课程报告 | sjtureport |
xelatex | 短 |
| D. Office 快速 | Word/PPT 课程作业 | pandoc（office-tools） | — | — |
场景 A 主流程（ARIS 模式，模块化写作）
- 定 venue → 模板：
latex-build list。ICML/NeurIPS 先下载当年官方.sty放模板目录（每年更新，不 vendoring） - 初始化项目：
latex-build new --template ieee-conf --dir 项目名 - 模块化写作（长文关键，防 context 爆）：
main.tex= venue 模板 + title/abstract +\input{sections/...}sections/每节一个文件，数字前缀排序：00-intro.tex10-method.tex20-experiments.tex30-conclusion.tex- 一节一子任务：写完
\input组合进 main，Agent 逐节推进不整篇塞一个 context
- 图：对外结构化图 → diagram-design skill（SVG 直进 LaTeX，矢量无损）；需要 draw.io 可编辑 → figure-drawing → 导出 PDF 进
figures/ - 编译：
latex-build build --dir 项目名 --engine pdflatex（latexmk 多遍，自动跑 biber） - 页数检查：
latex-build build --dir 项目名 --pages --main-body（ML：References 前≤8） - 评审：
review ...（ARIS 对抗评审，语义正确性）→ 修订 → 重编译
其他场景
- B 学位论文：
latex-build new --template sjtuthesis --dir 论文 --src <SJTUThesis-path>；盲审版\documentclass[review=true]；章节在contents/分文件 - C 报告：
new --template sjtureport；中文正文 + biblatex biber gb7714-2015 参考文献（UTF-8 中文无痛） - D Office：
office-tools md2docx/md2pptx（公式→OMML 原生方程）；模板bin/templates/reference.docx
关键约定
- 交付物 =
main.pdf；源文件进 git，编译产物不进（main.pdf + aux/log 忽略） - 参考文献：
refs.bib统一管理；中文gb7714-2015/ IEEEIEEEtran.bst/ ML 官方.bst - 公式：LaTeX 原生；md 迁移走 pandoc 转 Word OMML（Office 侧），两路独立
- 图：矢量优先（SVG/PDF 进 LaTeX），PNG 仅栅格图（实验截图等）
- 长文模块化：一节一文件 +
\input组合；短文（报告）单文件即可 - 盲审：投稿前
review=true编译一版，确认作者/致谢已去
工具
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 62 lines · 80 tokens per session scan A 981c67e16410
paper-writing is a skill published in the GitHub repository Azzygoatcoder/agent-useful-skills (7 stars, last pushed 12d ago), licensed MIT. It adds 80 tokens to every session and 1,286 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
paper-planning
Guides pre-writing planning for academic papers with 4 structured steps: story design (task-challenge-insight-contribution-advantage), experiment planning (comparisons + ablations), figure design (pipeline + teaser), and 4-week timeline management. Includes counterintuitive planning tactics (write a mock rejection…
arxiv-package
Package a TeX/LaTeX project into a clean tarball or zip for arXiv upload: file selection, build-artifact exclusion, 00README.XXX generation, ancillary file organization, archive validation. Triggers on: "package for arXiv", "create arXiv tarball", "bundle submission", "zip for arXiv", "prepare arXiv upload", "arXiv…
paper-review
Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: 5-aspect checklist (contribution sufficiency, writing clarity, results quality, testing completeness, method design), counterintuitive protocol (reject-first simulation, delete unsupported claims, score trust…
research-critique
Critical analysis of research papers evaluating methodology, claims-evidence alignment, and contribution significance. Triggers on: "critique this paper", "review this research", "analyze this study", "evaluate the methodology", "is this paper sound". NOT for formatting or submission readiness, use manuscript-review.
paper2poster
Convert academic papers (PDF) into conference posters (HTML/PNG). You are the conductor: you decide what each section needs — an original paper figure or text — write the outline, hand-author the poster HTML, and iterate on the render using your own visual read and a blind-reader content quiz. Use when the user wants…
evaluate-ml-pipeline
Methodology for evaluating a single sklearn-compatible learner (in particular, the SkrubLearner produced by build-ml-pipeline). Owns: which entry point to call (skore.evaluate first, the explicit report classes when needed), which cross-validator to pick from scikit-learn's catalogue, how to consume the structural…