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 Lambenthan/paper-discipline-skills --skill paper-writing-disciplinegit clone --depth 1 https://github.com/Lambenthan/paper-discipline-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/lambenthan/paper-discipline-skills/paper-writing-discipline)<a href="https://agentmods.dev/skills/lambenthan/paper-discipline-skills/paper-writing-discipline"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-writing-discipline/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/lambenthan/paper-discipline-skills/paper-writing-discipline"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-writing-discipline.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 | $0.00144 | $0.01905 |
| Opus 5 | $0.00072 | $0.00953 |
| Sonnet 5 | $0.00029 | $0.00381 |
| Haiku 4.5 | $0.00014 | $0.00191 |
Grade A, and why
paper-writing-discipline 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper-writing-discipline：怎么把新坑变成新 skill
核心理念
skill 不是知识，是踩过坑后才悟出来的纪律。 每次踩新坑，都是写一个新 skill 的机会——别让同一个坑再踩第二次。
知识可以查，纪律必须前置。
触发条件
用户出现以下任一信号 → 触发：
- 「以后...我都要...」
- 「下次记得...」
- 「这种情况要先...」
- 「这个教训我得记下来」
- 「帮我把这个习惯固化下来」
- 「再加一条新规则到 skill 里」
- 你识别到用户刚踩了一个坑、且这个坑可被规则化避免
4 个判断题（不全过 ≠ 写 skill）
判断这条新规则是否值得做成 skill：
Q1：不用会翻车？
├─ 不用没事 → 不是纪律，是偏好 → 不要 skill，写进 CLAUDE.md
└─ 不用会翻车 → 进入 Q2
Q2：是反直觉的？
├─ "本来就该这么做"的常识 → 不要 skill（太弱）
└─ 必须经历过才懂 → 进入 Q3
Q3：能在动手前就触发？
├─ 只能事后补救 → 不是 skill，是 hook
└─ 能在用户提需求时就触发 → 进入 Q4
Q4：是 HOW 不是 WHAT？
├─ 是某个工具的用法 → 写文档 / 教程
└─ 是"做事的方式" → 做 skill ✅
4 个全过 → 写 skill。任何一个 No → 改用其他形式（CLAUDE.md / hook / 教程）。
SKILL.md 模板（直接复制改填）
---
name: paper-<动词>-<对象>
description: |
[一段中文，说清这个 skill 防什么灾]
Use when [中文触发条件，列具体场景]。
---
# paper-<名字>：[一句话标题]
## 核心理念
[1-2 句，说清这条纪律的根本原因]
> [一句金句，让用户读到就记住]
## 触发条件
满足任一条 → 触发：
- [...]
- [...]
## 强制流程
\`\`\`
[简单流程图]
\`\`\`
## 标准回复模板
> [让 AI 能直接套用的话术]
## ❌ 反例（书 §X.X）
[具体翻车故事]
## Rationalization Table
| 念头 | 现实 |
|---|---|
| [...] | [...] |
## Red Flags
- [...]
## 来源
《Claude Code 科研手记》§X.X
命名规范
- 前缀统一
paper-（让所有 skill 在~/.claude/skills/里聚成一组） - 动词开头：
paper-confirm-before-doing、paper-backup-before-word - 描述触发场景，不是描述功能
- 只用小写字母 + 数字 + 连字符（YAML 强制）
| ✅ 好名字 | ❌ 坏名字 |
|---|---|
| paper-backup-before-word | word-backup-system |
| paper-pilot-before-batch | batch-task-helper |
| paper-confirm-before-doing | task-confirmation |
description 写法
核心原则：description 写"什么时候触发"，不要写"做什么"。
| ✅ 好 | ❌ 坏 |
|---|---|
| Use when 用户编辑 .docx 文件之前 | 这是一个 Word 备份工具 |
| Use when 用户给出模糊润色任务 | 用来润色论文段落 |
| Use when 拿到导师录音 / 便条 | 处理导师反馈的 skill |
为什么：description 进入 Claude 的 system prompt，决定它"要不要打开这个 skill"。 描述功能 → Claude 不知道何时调用 → 永远不会被触发。
必备 6 个栏目（缺一不可）
每个 paper-* skill 必须有：
- 核心理念（1-2 句 + 一句金句）
- 触发条件（list，要具体）
- 强制流程（流程图 / 步骤）
- 标准回复模板（能直接套）
- Rationalization Table（封掉合理化借口）
- Red Flags（自检停止信号）
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 · 219 lines · 144 tokens per session scan A a50775e2b24c
paper-writing-discipline is a skill published in the GitHub repository Lambenthan/paper-discipline-skills (19 stars, last pushed 4mo ago), licensed MIT. It adds 144 tokens to every session and 1,905 once invoked, about $0.0007 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
paper-writer
Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers.…
food-research
Run a comprehensive, multi-source literature and evidence-synthesis workflow for food & nutrition science. Use when the user wants to research a food/nutrition topic in depth, do a literature review, build an evidence brief, screen and synthesize many sources, verify citations, or scope a systematic review.…
food-paper
Multi-subagent manuscript system for food & nutrition science covering the whole research process: understand the field, frame research questions, curate and analyze data, run statistics, build figures and tables, construct the discussion, draft, polish, and self-review — journal-aware throughout. Includes a…
food-pipeline
Master orchestrator for the whole food & nutrition research-to-publication workflow. Coordinates the specialist skills — each with its own subagent set — into one governed path: journal selection, research (food-research / food-deep-research), writing & analysis (food-paper), figures (food-figure), peer review…
food-deep-research
General-purpose deep research that produces a fully written, source-validated literature review on any question: scope it, design the method, discover and screen sources by journal ranking, validate every source, extract and verify evidence, synthesize, stress-test, then write and format the review (APA 7.0 by…
food-figure
Comprehensive figure system for food & nutrition manuscripts: analyzes the user's data, recommends the best figure(s) to make, then produces submission-grade graphics in Python or R at the target journal's spec. Handles all common scientific figure types (bar/box/violin, line/kinetic, scatter/regression, Bland–Altman…