Paper Anchor

by cabbage2000-lab

Paper Anchor is a Writing skill for Claude Code, published by cabbage2000-lab in paper-tutor-skills.

18 stars5 forkson cabbage2000-lab/paper-tutor-skillsAdded 2026/08/11+38% in starsRepository updated 2026/08/04

academic-integrityacademic-writingai-agentchinesecitation-verificationclaude-codeclaude-pluginclaude-skillscodexliterature-reviewresearchthesis-writing

Install in seconds

Install Paper Anchor

Copy Paper Anchor into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/cabbage2000-lab/paper-tutor-skills/tree/main/skills/paper-anchor ~/.claude/skills/paper-anchor

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/cabbage2000-lab/paper-tutor-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/paper-anchor/SKILL.md in cabbage2000-lab/paper-tutor-skills
Installs to: ~/.claude/skills/paper-anchor
Collection: One of 24 skills cataloged from this repository
Category: Writing — 1012 skills

What Paper Anchor does

Scans a manuscript for zero-citation paragraphs, extracts claims, categorizes them, retrieves candidate literature via real API, and provides a side-by-side comparison for the author to decide if each claim is supported.

Paper Anchor is cataloged under Writing on DirSkills. Paper Anchor comes from a repository tagged academic-integrity, academic-writing, ai-agent, chinese and citation-verification.

Documentation

README

Excerpt

paper-anchor：文献支撑补齐（论断—支撑对照器）

你（执行本 skill 的宿主 agent）做四件事：机械统计引用密度定位缺口 → 摘论断并分类 → 真实检索取候选 → 摆字段级比对交用户判定。引用密度一律由 scripts/anchor_scan.py 算，候选一律由 ../paper-search/scripts/search.py 真实检索，两样都不凭记忆。

产物不是「找到的文献」，而是「你这句话到底需要什么支撑、现在有没有、没有的话两条路各是什么」。 这个反转是本命令的全部要点：它离「学术不端便利器」只有一步之遥——先有结论后找文献（citation shopping）就是它的失败态。裸模型面对「帮我给这段补几篇文献」会凭记忆吐三条看起来很合适的、说「这篇支持你的观点」、并且永远只给「补上文献」一个方向；那三条文献里的 DOI 一半是编的，而导师查一次原文就穿帮，代价比「没补」更大。

三条不变（优先级最高，高于本文其余一切）

① 不替用户判断某文献能否支撑某论断——你只摆「该文献说了什么（五字段）」与「你的论断说了什么」的字段级比对，末尾以 ❓ 把判断交回用户。禁用「这篇支持你的观点」「可引此文支撑」「最能支撑的是 X」「相关度 90%」「这几篇最合适」。候选按客观键排序（默认年份降序），不排相关度、不给 Top-N。是否构成支撑，用户读完原文才知道。

② 不编文献——候选一律来自 search.py 的真实 API 响应，绝不凭模型记忆补全或编造。找不到就说找不到；断网显式声明「检索不可用」，不返回空表充数、不用记忆里的文献顶替。这是硬规则 4（核验类 skill 的降级必须明标）在本命令的落点。

This is the opening of the README. Read the full README on GitHub.

Commands Paper Anchor provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/paper-draft
/paper-verify
/paper-claim
/paper-import
/paper-search
/paper-screen
/paper-init
/paper-logic

Frequently asked about Paper Anchor

What else does cabbage2000-lab publish alongside Paper Anchor?
Paper Anchor is one of 24 skills that DirSkills catalogs from cabbage2000-lab/paper-tutor-skills, the repository it ships in. Its siblings there include Paper Abstract, Paper Daily and Paper Disclose. Each one is a separate skill with its own page in this directory, installs the same way Paper Anchor does, and is maintained by cabbage2000-lab in that same repository. The rest of the collection is listed on the cabbage2000-lab/paper-tutor-skills page.
How does Paper Anchor compare to other Writing skills?
Paper Anchor ranks #974 by stars among the 1012 Writing skills in this catalog. The most-starred ones next to it are Article Writing, Social Media Content Calendar and Knowledge Comic Creator. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Paper Anchor against them. Open each page to compare what they document and how they install.