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
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 Norman-bury/research-writing-skill --skill writing-chaptersgit clone --depth 1 https://github.com/Norman-bury/research-writing-skillWrote 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/writing-chapters)<a href="https://agentmods.dev/skills/norman-bury/research-writing-skill/writing-chapters"><img src="https://agentmods.dev/badge/skills/norman-bury/research-writing-skill/writing-chapters/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/writing-chapters"><img src="https://agentmods.dev/badge/skills/norman-bury/research-writing-skill/writing-chapters.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.03245 |
| Opus 5 | $0.00012 | $0.01622 |
| Sonnet 5 | $0.00005 | $0.00649 |
| Haiku 4.5 | $0.00002 | $0.00325 |
Grade A, and why
writing-chapters 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 12d 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
章节写作
负责论文各章节的实际写作。必须在头脑风暴完成、项目结构创建后调用。
如果任何条件不满足，必须先调用 brainstorming-research 技能。
- Introduction、Related Work、研究背景、文献综述：必须先调用
evidence-driven-writing，并读取refs/evidence-map.md或plan/evidence-map.md。 - Methodology、Methods、研究方法：必须按“输入到输出”的技术流写作，不能只罗列模块。
- Results、Discussion、实验结果：必须先调用
experiment-results-planning，确认真实数据或明确标记的 mock/synthetic planning data。
任何用户要求都不得直接进入正文。诸如“写得自然”“不要泛泛而谈”“注意衔接”只能转化为句子、段落、结构和证据处理。
Checklist（每章必须完成）
- 读取 plan/outline.md 确认本章目标和要点
- 如果存在 plan/chapter-architecture.md，确认本章文件名、最小正文长度和 agent owner
- 检查前置章节是否完成（按逻辑顺序）
- 与用户确认本章关键论点和内容方向
- 根据学科领域调用对应写作模块
- 对引言/相关工作读取 evidence-driven-writing 产物
- 对方法章节检查输入到输出 flow
- 执行正文污染 contamination firewall 检查
- 写作输出到 chapters/XX-name.md
- 阶段1：规范合规检查
- 阶段2：质量检查（去AI化、语言流畅度）
- 更新 plan/progress.md
- 展示写作成果，询问用户确认或修改
- 用户确认后，询问是否继续下一章
Chapter Agent Contract
Full-paper drafts and redrafts must use a separate fresh agent for each major chapter. The controller prepares the task packet and review criteria; the chapter agent writes only its assigned file.
Each chapter agent must receive:
- the exact chapter file it owns;
- the chapter's role in the whole manuscript;
- required source files and evidence IDs;
- paragraph-level argument chain, not a list of section labels;
- minimum prose length from
plan/chapter-architecture.md; - prohibited wording and prohibited structure;
- instructions to report unresolved gaps instead of inventing evidence or results.
Each chapter agent must return:
- status: DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, or BLOCKED;
- changed file path;
- short summary of argument chain;
- unresolved evidence/data gaps;
- self-review against the rejection checks.
The controller must record this in plan/chapter-agent-provenance.md. A chapter without provenance is not accepted for a full-paper redraft.
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.
- 12d ago First seen · 343 lines · 23 tokens per session scan A 566363076c60
writing-chapters is a skill published in the GitHub repository Norman-bury/research-writing-skill (3,187 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 3,245 once invoked, about $0.0001 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 2026-08-30.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…