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-translate-advisor-feedbackgit 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-translate-advisor-feedback)<a href="https://agentmods.dev/skills/lambenthan/paper-discipline-skills/paper-translate-advisor-feedback"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-translate-advisor-feedback/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-translate-advisor-feedback"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-translate-advisor-feedback.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 | $0.00130 | $0.01379 |
| Opus 5 | $0.00065 | $0.00690 |
| Sonnet 5 | $0.00026 | $0.00276 |
| Haiku 4.5 | $0.00013 | $0.00138 |
Grade A, and why
paper-translate-advisor-feedback 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.
What it actually says
paper-translate-advisor-feedback：导师反馈先翻译再执行
核心理念
导师说的话是人对人的语言：充满省略、隐含、上下文依赖。 AI 听这种语言会抓错重点——它会按字面改"逻辑不顺"，但导师其实指的是"§3.2 那一段的论证跳跃"。
你的工作不是把导师的话喂给 AI，是把导师的意思翻译成 AI 能执行的清单。
触发条件
用户的输入包含以下任一形式 → 触发：
- "导师说..."、"老师让..."、"我导师反馈..."、"师姐说..."
- 录音转写文本
- Word / PDF 批注截图
- 微信聊天截图
- 邮件意见
- 手写便条照片
- 口述："开会的时候老师说，要我..."
强制流程
收到导师反馈
│
▼
逐条解析每个意见，提取五要素：
1. 位置（哪一章 / 节 / 段 / 句）
2. 改什么（具体动词：删 / 增 / 重写 / 调整顺序）
3. 改成什么（目标状态）
4. 标准（按什么判断改对了：篇幅 / 风格 / 引用 / 数据）
5. 不动哪里（显式列出本条不会触及的内容）
│
▼
位置不明 → 列出"可能位置"问用户哪个
意图不明 → 列出"可能意图"问用户哪个
│
▼
输出清单，等用户确认 / 调整
│
▼
按确认后的清单执行
（每条改完标记 done）
翻译模板（每条反馈都按这个填）
| 字段 | 内容 |
|---|---|
| 原话 | "[导师原话]" |
| 位置 | 第 X 章 §X.X 第 X 段 / 还需用户确认 |
| 改什么 | 删除 / 新增 / 重写 / 调整 / 补数据 / 换图 |
| 改成什么 | [目标状态，具体到文字 / 结构] |
| 标准 | [字数 / 风格 / 数据要求 / 引用要求] |
| 不动 | [显式列出本条不会触及的内容] |
❌ 反例（书 §5.4）
导师批注：「这块逻辑不顺，第二段和第三段有点跳。」
错误做法：直接把这句话扔给 AI："帮我改一下，导师说第二三段逻辑不顺。"
- AI 会改字句通顺度，不会动论证结构
- 改完导师还是说"逻辑不顺"
- 你被迫再问一遍导师
正确做法：
我把导师这条反馈翻译成下面这条 todo，你看对不对：
- 位置：§3.2 第二段、第三段
- 改什么：补一个过渡句，把第二段的"已有研究的局限"和第三段的"我们的方法"逻辑接起来
- 改成什么：在第二段末尾加一句明确指向"因此，本研究试图解决 X"
- 标准：过渡句不超过 30 字，不引入新概念
- 不动：第二、三段的核心论点和已有引文
这个理解对吗？对就开改。
"我也不确定导师指什么" 的处理
如果你（或 AI）真的看不懂某条反馈：
这条意见我有两种理解：
A. 你想让我... B. 还是说你想让我...
哪个对？或者你能再描述一下你想要的样子吗？
禁止：硬猜一个意思就改。导师的下一句就是"你怎么改成这样"。
Rationalization Table
| 念头 | 现实 |
|---|---|
| "导师的意思很清楚，直接改就行" | 清楚的话导师会写成 todo。说"逻辑不顺"就是模糊 |
| "我先按 A 理解改，他不满意再调" | 调一次 = 多见一次导师，多一次时间成本 |
| "录音转写文字很全，AI 能读懂" | 转写丢失语气、停顿、强调——这些才是真正的指令 |
| "我把整段录音喂给 AI 让它判断" | AI 不是你导师，没听过你的论文进展 |
| "翻译成 todo 显得我没听懂导师" | 翻译成 todo 是对导师意见的尊重，不是质疑 |
Red Flags
- 你打算把导师原话直接复制进 prompt → 停，先翻译
- 你看到"逻辑不顺"、"再深入点"、"风格不对"等模糊词 → 必须翻译为可执行
- 你不知道导师指的具体位置 → 不准猜，问用户
- 你打算"边改边问" → 不行，先全部翻译完，统一确认
来源
《Claude Code 科研手记》§5.4「导师反馈的处理流程」
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 · 139 lines · 130 tokens per session scan A ea77bba76cb0
paper-translate-advisor-feedback is a skill published in the GitHub repository Lambenthan/paper-discipline-skills (19 stars, last pushed 4mo ago), licensed MIT. It adds 130 tokens to every session and 1,379 once invoked, about $0.0006 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
enhancing-latex-lectures
Enhances LaTeX lecture notes by analyzing pedagogical reference materials (like Todorov's PDFs) and systematically adding stunning visualizations, concrete examples, and intuitive explanations. Use when the user requests improving lectures, adding visualizations from papers, or adopting another author's teaching style.
beamer
Use when creating LaTeX Beamer presentation slides from documents, especially for academic presentations. Use when source document contains structured content with sections, subsections, or clear hierarchical organization that should be preserved in slides.
lecture-notes-enhancement
Use when enhancing existing lecture notes with multiple course source materials (recordings, PPT slides, existing notes).
model-paper-deconstruct
A paper-analysis workflow that studies how a reference research paper is structured and written. It uses a framework for separating visible details, underlying ideas, actions, and abstract concepts.
skill-forge
A workflow for turning source material, such as a textbook or research method, into a usable skill for an AI coding assistant. It filters and structures the material, drafts the skill, checks its rules and output format, and reviews it before saving.
topic-review-semisystematic
A three-stage coaching workflow for choosing a topic for a semi-systematic or narrative literature review, which explains and connects research across a broad area instead of using a fully exhaustive search.