annota: Skill for Claude Code

.claude/skills/annota-read/SKILL.md

annota-read is a skill for Claude Code from dengls24/annota. It costs 95 tokens per session (2,098 once invoked), scanned A, original, MIT.

A Chinese-language skill for deeply reading a research paper, including finding the paper, extracting its full text, highlighting important passages, and creating structured notes. It can also produce peer-review feedback.

In plain words
What is it for?
Use it to read a paper from a file or Zotero, identify contributions, methods, results, and limitations, save notes, or request a review-style assessment.
Why use it?
It turns an unfamiliar paper into an overview, categorized annotations, and organized notes. It supports different reading depths depending on what the reader needs.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is dengls24/annota's own configuration. It tells Claude Code how to work on annota itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything annota configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dengls24/annota. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dengls24/annota/master/.claude/skills/annota-read/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dengls24/annota

Made for: Claude Code.

Wrote 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.

agentmods badge for annota-read

README.md
[![agentmods](https://agentmods.dev/badge/skills/dengls24/annota/annota-read/github.svg)](https://agentmods.dev/skills/dengls24/annota/annota-read)
Your own site
<a href="https://agentmods.dev/skills/dengls24/annota/annota-read"><img src="https://agentmods.dev/badge/skills/dengls24/annota/annota-read/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.

agentmods 80×15 button for annota-read

Your own site · 80×15
<a href="https://agentmods.dev/skills/dengls24/annota/annota-read"><img src="https://agentmods.dev/badge/skills/dengls24/annota/annota-read.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,098 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00095 $0.02098
Opus 5 $0.00048 $0.01049
Sonnet 5 $0.00019 $0.00420
Haiku 4.5 $0.00010 $0.00210

Measured 10d ago against content hash 4b6632cb6584, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

annota-read 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 10d 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.

.claude/skills/annota-read/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

论文全套深度阅读

用户给了一篇论文,但没有具体指令。你的目标是给出开箱惊艳的阅读体验。

输入解析

用户输入:$ARGUMENTS


Step 1:快速扫描,生成论文概览

1.1 定位论文

如果是文件路径直接使用;否则调用 search_zotero_items(query) 搜索。 同时调用 get_item_metadata(item_id) 获取元数据。

1.2 提取全文

调用 get_pdf_text_bulk(item_id, skip_refs=True)

1.3 输出论文快照(在对话中展示,不保存)

阅读全文后,用以下格式输出一段论文快照,让用户知道你已经读懂了:

📄 **{标题}**
👥 {作者} · {会议/期刊} {年份}

🎯 **一句话核心**:{用一句话说清楚这篇论文做了什么,解决了什么问题}

💡 **3个关键贡献**:
  1. {贡献1}
  2. {贡献2}
  3. {贡献3}

📊 **最亮眼的数据**:{最重要的一两个实验结果数字}

⚠️ **主要局限**:{最关键的一个局限}

Step 2:交互式确认阅读方案

展示快照后,立即询问用户想要什么深度:

我已经读完了这篇论文。接下来你想要:

A) 🚀 **全套深度阅读**(推荐)
   四色标注全文重点 + 结构化阅读笔记保存到 Zotero
   预计创建 15-25 条标注 + 1 份完整笔记

B) 🎨 **只做标注**
   四色高亮:贡献(紫)、方法(蓝)、结果(绿)、不足(红)
   预计 15-25 条标注

C) 📝 **只写笔记**
   生成结构化阅读笔记保存到 Zotero

D) 🔍 **审稿模式**
   以顶会审稿人视角给出评审意见 + 评分

E) 🎯 **自定义**
   告诉我你最关心什么(某个具体方法、某类实验、某个问题)

直接回复 A/B/C/D/E,或者告诉我你想要什么。

Step 3A:全套深度阅读(选 A)

标注阶段

分析全文,识别以下四类内容,每类至少找 3-5 处

类型 颜色 代码 标准
核心贡献/创新点 紫色 #a28ae5 论文声称的 novelty、contribution
方法/架构/算法 蓝色 #2EA8E5 关键技术设计、核心机制
实验结果/数据 绿色 #28CA42 具体数字、性能对比、improvement
局限/不足/future work 红色 #ff6666 limitation、weakness、future work

输出标注清单(在对话中展示):

将创建以下标注:
[紫] Page 1: "We propose DCC, a novel..."
[蓝] Page 3: "The key insight is..."
[绿] Page 6: "achieves 2.3× speedup over..."
...(共 N 条)

⚠️ 写入需要关闭 Zotero。请确认已关闭后回复"确认"。

用户确认后,调用 batch_annotate 一次性写入所有标注。

笔记阶段

生成完整结构化笔记(HTML 格式),内容比 /annota-summarize 更深入:

<h2>📄 论文信息</h2>
<p><b>标题:</b>{title}</p>
<p><b>作者:</b>{authors}</p>
<p><b>发表:</b>{venue} {year}</p>
<p><b>DOI:</b>{doi}</p>

<h2>🎯 核心问题与动机</h2>
<p><b>问题:</b>{这篇论文要解决什么问题?}</p>
<p><b>为什么重要:</b>{这个问题的重要性和现有方案的不足}</p>

<h2>💡 核心贡献(对应紫色标注)</h2>
<ol>
<li><b>{贡献1标题}:</b>{具体说明}</li>
<li><b>{贡献2标题}:</b>{具体说明}</li>
<li><b>{贡献3标题}:</b>{具体说明}</li>
</ol>

<h2>🔧 方法详解(对应蓝色标注)</h2>
<p><b>整体架构:</b>{一段话描述整体方案}</p>
<p><b>关键设计1:</b>{设计决策及其原因}</p>
<p><b>关键设计2:</b>{设计决策及其原因}</p>

<h2>📊 实验结果(对应绿色标注)</h2>
<ul>
<li><b>主要结论:</b>{最重要的实验结论}</li>
<li><b>关键数据:</b>{具体数字,如"比 baseline 快 2.3×"}</li>
<li><b>Baseline 对比:</b>{与哪些方法对比,结果如何}</li>
</ul>

<h2>⚠️ 局限与不足(对应红色标注)</h2>
<ul>
<li><b>论文自述:</b>{作者承认的 limitation}</li>
<li><b>潜在问题:</b>{你认为的其他不足}</li>
</ul>

<h2>💭 批判性思考</h2>
<p><b>最强的地方:</b>{这篇论文最有说服力的点}</p>
<p><b>最弱的地方:</b>{最值得质疑的地方}</p>
<p><b>可复现性:</b>{实验设置是否清晰,能否复现}</p>

<h2>🔗 对我的启发</h2>
<p>{这篇论文对读者自己研究的启发,如果知道用户研究方向则定制}</p>

<h2>📚 值得追读</h2>
<ul>
<li>{引用中最值得读的 2-3 篇相关工作}</li>
</ul>

Read the full file on GitHub · 226 lines

Changes

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.

  1. 10d ago First seen · 226 lines · 95 tokens per session scan A 4b6632cb6584

Subscribe to this mod's changes

annota-read is a skill published in the GitHub repository dengls24/annota (19 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 2,098 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

fs-notebook-tabs

A computer-science capstone: an on-device ML keyboard that predicts next words privately — problem, method, evaluation, and defense answers. Built as a decision-grade coursework defense deck for professor, defense committee.

nexu-io/open-design · 47 tokens

html-ppt-zhangzara-cartesian

An economics senior thesis on the employment effects of local minimum-wage increases — identification strategy, evidence, and limitations. Built as a decision-grade coursework defense deck for thesis committee.

nexu-io/open-design · 46 tokens

html-ppt-zhangzara-pin-and-paper

A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.

nexu-io/open-design · 51 tokens

html-ppt-zhangzara-scatterbrain

A design-school graduation project: a civic wayfinding system for a transit hub — the brief, the process, and the outcome. Built as a decision-grade coursework defense deck for crit panel, faculty.

nexu-io/open-design · 52 tokens

Academic CV Builder

Format CVs for academic positions with publications, grants, and teaching.

PramodDutta/qaskills · 17 tokens

paper-slide-deck

Generate professional slide deck images from academic papers and content. Creates comprehensive outlines with style instructions, auto-detects figures from PDFs, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", or "slide deck" for papers.

LeonChaoX/qinyan-academic-skills · 63 tokens