Home / imad7777 / paper-citation-tracer · GitHub

paper-citation-tracer SKILL.md skillA

paper-citation-tracer from imad7777/paper-citation-tracer is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add imad7777/paper-citation-tracer/paper-citation-tracer@git:20260923.673ac1b

Pins git:20260923.673ac1b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
imad7777/paper-citation-tracer
Path
SKILL.md
Versions recorded
5
Latest version
git:20260923.673ac1b, committed Sep 23, 2026
First version recorded
Sep 21, 2026
Size
8,176 bytes
Repository stars
16
License
MIT

为学术写作与文献综述任务，定位 PDF 全文中与用户引文（中文或英文段落）对应的原文段落， 用 PyMuPDF 添加高亮注释（黄色），输出标注后的 PDF 文件——用于核验引文出处是否属实。 适用于：用户在论文/综述写作中提供"引文原文"和"参考文献 PDF 路径"，要求把 PDF 中 对应的定义段、关键术语、引用位置都标黄，方便直接对照原文核验引用。 触发词：核验引用、引文溯源、高亮文献、高亮 PDF、文献段落标注、标黄引文、PDF 标注、 verify citation、trace quote to source、highlight citations in PDF、mark up PDF with quotes。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Paper Citation Tracer

为用户的引文（中文或英文段落）在指定的 PDF 全文中定位原文出处，并添加高亮注释——
把引文的原始证据翻出来，核验判断由人来做。

> 本仓库同时提供独立 CLI `highlight_citations.py`：没有 agent 环境时，
> 也可以直接在命令行完成同样的标注（见 README）。

## 适用场景

- **核验 AI 插入的引用**：AI 辅助写作给出的引用「看着像真的」，把带引用的正文段落 + 被引文献 PDF 交给 agent，标出原文出处，人工判断引用是否合理、有无过度转述
- **原文定位 / 引文溯源**：写综述时想确认某句话出自哪篇文献的哪一段——给它文字和 PDF，它把原文位置标出来
- 输出：保留原 PDF 所有内容，仅在原文位置加 highlight 注释（不修改文字、不删页）

## 使用粒度（重要：避免「整页变黄」）

- **一次核验一条引用**。正文里一段含 5 条引用，就提取 5 个要害短语一次跑完，
  但**不要把整句甚至整段原文都当短语喂进来**——短语越长、越泛，命中面积越大，
  视觉上就是「整页被涂满」。每条引用只取 1–2 个 8–25 字符的独特短语
  （动词 + 宾语 + 限定词，不含标点年份）。
- 想让版面清爽可加 `--opacity 0.5`（CLI 现已默认 0.5；半透明高亮，正文透出，
  且避免部分阅读器把不透明高亮盖在文字上）。
- 如果输出 PDF 出现大面积高亮，先检查：是不是把整句话当短语了？换更短的
  独特短语重跑——这是输入问题，不是工具失控。

## 工作流

### 1. 通读 PDF，定位关键页

```python
import fitz  # PyMuPDF, pip install pymupdf
doc = fitz.open(pdf_path)
for pno in range(len(doc)):
    text = doc[pno].get_text()
    # 用引文的核心术语作为搜索关键词
    # 例如"holistic in nature"、"multidimensional construct"
    if "holistic in nature" in text.lower():
        print(f"Page {pno+1} matched")
        print(text[:1500])
```

**关键**：
- 优先看 abstract（第 1 页）和 introduction（前 3-4 页）
- 用 `len(doc)` 确认总页数，只在前 30% 找定义段，避免误中高频词
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add imad7777/paper-citation-tracer/paper-citation-tracer@sha256:94fec640a7cbcc5b

The line at the top of this page pins the label git:20260923.673ac1b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7chkvhehspnomvuu.svg)](https://markdownregistry.com/a/art_7chkvhehspnomvuu)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 21, 2026 and Sep 23, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20260923.673ac1b latest2026-09-23 673ac1b 8,176 BA view · diff
git:20260923.446f67e2026-09-23 446f67e 7,673 BA view · diff
git:20260922.808ea2e2026-09-22 808ea2e 6,955 BA view · diff
git:20260922.faafc272026-09-22 faafc27 6,749 BA view · diff
git:20260921.8009bf02026-09-21 8009bf0 6,601 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8176 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

imad7777/paper-citation-tracer · 16 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7chkvhehspnomvuu
GET https://markdownregistry.com/api/v1/resolve?ref=imad7777/paper-citation-tracer/paper-citation-tracer
GET https://markdownregistry.com/api/v1/blob/94fec640a7cbcc5b31e0774e34e2b57cfcf490864449d2e215af452941f3b7a7

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

Browse by kind, by grade A, or by owner.