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 5.5 | $0.00052 | $0.00552 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (20 stars, last pushed 5mo ago), licensed MIT. It adds 130 tokens to every session and 1,379 once invoked, about $0.0005 per session on Opus 5.5. 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.
paper-translate-advisor-feedback compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paper-translate-advisor-feedbackLambenthan/paper-discipline-skills | Skill | 20 | 5mo ago | MIT | A | 130 | Claude Code, Codex |
| enhancing-latex-lecturesshubham0704/claude-skills | Skill | 2 | 29d ago | MIT | A | 64 | Claude Code |
| explain-systems-visuallyshubham0704/claude-skills | Skill | 2 | 29d ago | MIT | A | 59 | Claude Code, Codex |
| reader-comprehension-passshubham0704/claude-skills | Skill | 2 | 29d ago | MIT | A | 74 | Claude Code |
| model-paper-deconstructqiaomiaojoe/ai-academic-workflow | Skill | 10 | 3d ago | none | A | 232 | Claude Code, Codex |
| skill-forgeqiaomiaojoe/ai-academic-workflow | Skill | 10 | 3d ago | none | A | 227 | Claude Code, Codex |
| topic-review-semisystematicqiaomiaojoe/ai-academic-workflow | Skill | 10 | 3d ago | none | A | 246 | Claude Code, Codex |