Norman-bury/research-writing-skill is an agent skill that turns academic paper writing into a tracked, reusable workflow with planning, drafting, reviews, figures, literature work, and LaTeX outputs. It is intended for undergraduate students, graduate students, and early-career researchers working on theses, coursework papers, or initial submissions. Its catalogue entries are the skills, instructions, plugin, and hook that implement the workflow across coding-agent platforms.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Norman-bury/research-writing-skillnpx agentmods add skills/norman-bury/research-writing-skill/literature-reviewWrote 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/norman-bury/research-writing-skill/literature-review)<a href="https://agentmods.dev/skills/norman-bury/research-writing-skill/literature-review"><img src="https://agentmods.dev/badge/skills/norman-bury/research-writing-skill/literature-review/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/norman-bury/research-writing-skill/literature-review"><img src="https://agentmods.dev/badge/skills/norman-bury/research-writing-skill/literature-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 437 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00021 | $0.03915 |
| Opus 5 | $0.00010 | $0.01958 |
| Sonnet 5 | $0.00004 | $0.00783 |
| Haiku 4.5 | $0.00002 | $0.00392 |
Grade A, and why
literature-review scanned grade A with 1 finding 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://api.crossref.org/works/10.1000/doi123" How it starts
The opening of the file, as written. The whole thing — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文献综述
本技能指导文献搜索、整理和综述写作。
这是最重要的原则，必须严格遵守：
- 英文文献：可通过网络搜索获取，但必须验证真实性
- 中文文献：明确告知用户去知网（CNKI）搜索，AI提供搜索建议
- 所有引用必须可追溯、可验证
- 不确定的文献信息，宁可不写也不编造
本技能内置了多个文献处理脚本：
1. 文献搜索 (scholar_search.py)
脚本位置：scripts/scholar_search.py
支持的数据库：PubMed, CrossRef, Semantic Scholar, arXiv
支持的输出格式：
json- JSON 格式（默认）bibtex- BibTeX 格式，可直接用于 LaTeXris- RIS 格式，用于 EndNote/Zoteroapa- APA 引用格式mla- MLA 引用格式chicago- Chicago 引用格式vancouver- Vancouver 引用格式
使用方法
# 基本搜索
python scripts/scholar_search.py "deep learning transformer"
# 指定数据库
python scripts/scholar_search.py "neural network" --sources pubmed,crossref
# 年份过滤（当前是2026年，建议使用近年范围）
python scripts/scholar_search.py "machine learning" --year 2023-2026
# 输出 BibTeX 格式（用于 LaTeX 论文）
python scripts/scholar_search.py "landslide detection" --format bibtex -o refs.bib
# 输出 APA 引用格式
python scripts/scholar_search.py "attention mechanism" --format apa --limit 5
# JSON 输出（用于程序处理）
python scripts/scholar_search.py "quantum computing" --format json -o results.json
输出格式示例
BibTeX 格式（用于 LaTeX）：
@article{xu2024,
title = {CAS Landslide Dataset: A Large-Scale and Multisensor Dataset},
author = {Yulin Xu and Chaojun Ouyang and Qingsong Xu},
journal = {Scientific Data},
year = {2024},
doi = {10.1038/s41597-023-02847-z},
}
APA 格式（用于正文引用）：
Yulin Xu and Chaojun Ouyang (2024). CAS Landslide Dataset...
各数据库特点
| 数据库 | 速率限制 | 摘要 | 引用数 | 适用领域 |
|---|---|---|---|---|
| CrossRef | 高 | 部分 | 是 | 全学科 |
| PubMed | 中 | 需额外请求 | 否 | 生物医学 |
| Semantic Scholar | 低* | 是 | 是 | 全学科 |
| arXiv | 低 | 是 | 否 | CS/物理/数学 |
* Semantic Scholar 建议配置 API Key 以获得更高限额。
Checklist
- 确认综述主题和范围
- 生成搜索关键词（中英文）
- 英文文献：执行搜索并整理结果
- 中文文献：提供搜索策略，等待用户提供
- 按主题分类整理文献
- 生成证据-论点映射（evidence-claim map）
- 标注每条文献的引用位置（citation slot）
- 撰写综述初稿
- 检查所有引用的真实性
- 更新 plan/progress.md
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.
- 13d ago First seen · 472 lines · 21 tokens per session scan A 596673b7a648
literature-review is a skill published in the GitHub repository Norman-bury/research-writing-skill (3,195 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 3,915 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…