auto-cite SKILL.md skillA
auto-cite from kendrick-stein/mcislab_deepread is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kendrick-stein/mcislab_deepread/auto-cite@git:20260706.1b25cb2Pins git:20260706.1b25cb2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kendrick-stein/mcislab_deepread
- Path
skills/4-writing/auto-cite/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260706.1b25cb2, committed Jul 6, 2026
- Size
- 5,831 bytes
- Repository stars
- 12
- License
- none declared
当 Supervisor 在写 LaTeX 论文、需要用知识库（Papers/）里读过的论文给草稿加引用时， 逐条判断 claim 是否真被某篇论文支撑，给出带理由的 \cite{} 建议，确认后再插入。 触发："给这篇 tex 加引用""用我读过的论文 cite 一下".
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
## Purpose
给定一篇 LaTeX 草稿，用知识库里**已读过**的论文为它添加引用。核心原则：**evidence-driven，不按关键词盲插**——关键词重叠 ≠ 这篇论文真的支撑这句话。脚本只负责"缩小候选 + 机械校验"，**"该不该引、引哪篇"的判断由 Agent 读 summary 后做出，并经 Supervisor 确认后才写入**。
与 `latex-citation-enhancer` 的分工：后者把读过的论文导成准确的 `references.bib`（条目正确）；本 skill 决定**在哪句话引哪篇**（引用位置正确）。
## Steps
### Step 1：同步引用身份与索引
```bash
python3 skills/4-writing/latex-citation-enhancer/assign_cite_keys.py
python3 skills/4-writing/latex-citation-enhancer/build_paper_index.py
```
确保全库每篇都有稳定 `cite_key`，且 `paper_index.json` 是最新的（含 summary/key_results 供检索）。
### Step 2：解析草稿，定位"值得引用的 claim"
用 Read 读取 `.tex`。**由 Agent 判断**哪些句子需要引用支撑，典型信号：
- attributive：归因于已有工作（"prior work shows""X et al. propose""following [prior]"）。
- 实证断言：具体方法名、数据集名、benchmark 名、可被某篇论文证实的数字/结论。
- 背景陈述：领域内已被确立的事实（"GUI agents remain brittle on long-horizon tasks"）。
**不**需要引用的：作者自己的贡献陈述、纯过渡句、定义性陈述。
用 `tex_cite_ops.py existing <tex>` 列出**已有** `\cite{}` 的 key，对应句子默认跳过（除非 Supervisor 要求补充）。
### Step 3：候选生成（脚本，仅缩小范围）
对每条 claim，把该句（必要时加上下文短语）作为 query 取候选：
```bash
python3 skills/4-writing/auto-cite/retrieve_candidates.py "claim 文本……" --k 6 --json
```
返回 top-K 论文（cite_key / title / summary / matched_terms / score）。**这只是候选，不是结论。**
…Read the whole file at its exact version.
How to install
mdr add kendrick-stein/mcislab_deepread/auto-cite@sha256:35204f8e360cfe2fThe line at the top of this page pins the label git:20260706.1b25cb2, 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.
[](https://markdownregistry.com/a/art_r56cpgb3tlsemotw)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 6, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5831 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
kendrick-stein/mcislab_deepread · 12 stars · license none declared · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_r56cpgb3tlsemotw GET https://markdownregistry.com/api/v1/resolve?ref=kendrick-stein/mcislab_deepread/auto-cite GET https://markdownregistry.com/api/v1/blob/35204f8e360cfe2f4fad65c0a03e1e4643b7916625929f6605de53577bc574af
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.