Bear Trace

Bear Trace is an AI Engineering skill for Claude Code, published by xuzhougeng in wisp-science.

1K stars106 forkson xuzhougeng/wisp-scienceAdded 2026/08/21+1% in starsRepository updated 2026/08/21

agent-skillsai-agentai-assistantai-for-scienceai4sciencebioinformaticscomputational-biologydesktop-appllmlocal-firstmcpmodel-context-protocolpythonreproducible-researchresearch-assistantrstatsrustscientific-computingscientific-workflowtauri

Install in seconds

Install Bear Trace

Copy Bear Trace 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/xuzhougeng/wisp-science/tree/main/skills/bear-trace ~/.claude/skills/bear-trace

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/xuzhougeng/wisp-science.git

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

In this catalog

Source file: skills/bear-trace/SKILL.md in xuzhougeng/wisp-science
Installs to: ~/.claude/skills/bear-trace
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Bear Trace does

Bear Trace traces a research topic or seed paper backward through its predecessors, then adds recent developments to show how the idea evolved. Use it when you want the origin, development path, or intellectual lineage of a field or paper.

Bear Trace is cataloged under AI Engineering on DirSkills. Bear Trace comes from a repository tagged agent-skills, ai-agent, ai-assistant, ai-for-science and ai4science.

Documentation

README

Excerpt

bear-trace · 文献溯源

一个任务：讲清楚一个问题是怎么走到今天的，通过向前挖掘来完成。大多数综述是向前平铺的；这个技能顺着传承线向后追，让你看见每一步为什么发生。

先读 references/sci-cli.md——CLI 检测步骤、用法和铁律。再读 references/output-system.md——三层输出体系和 HTML 外壳规范。

Flags

默认：向前追溯 3 层
-d N：追溯 N 层（1 到 5）；默认 3 层约 4–5 次检索，5 层约 7–8 次

步骤（固定顺序）

Step 0 — 确认 CLI 可用 运行 sci --version。未安装就给安装命令并停止；认证错误就提示 sci init 并停止。

Step 1 — 锚定当前里程碑 如果输入是主题，先 sci search 找到当前的标志性工作作为起点。如果输入是一篇具体论文，直接用它作为锚点。

如果用户输入具体论文，先用标题、DOI 或作者年份做精确检索确认锚点。确认不到时，不要凭记忆补论文信息；改为把输入当作主题处理，并在检索缺口里说明未确认到种子论文。

Step 2 — 逐层向前追溯 从锚点出发，每层单独做一次 sci search：它依赖的方法是什么、解决的前驱问题是什么、建立在哪些奠基性结论上。每层是独立的检索，不是记忆推断。层数由 -d 决定，默认 3 层。

深度溯源意味着多次检索，告知用户"本次将执行约 N 次检索"后直接开始，不等待确认。

每条传承边必须标注关系类型：

方法来源：后文使用或改造了前文方法
问题来源：后文延续了前文提出的问题
证据来源：后文建立在前文结论或数据上
领域转折：后文改变了研究对象、尺度或解释框架

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

Frequently asked about Bear Trace

What else does xuzhougeng publish alongside Bear Trace?
Bear Trace is one of 25 skills that DirSkills catalogs from xuzhougeng/wisp-science, the repository it ships in. Its siblings there include Agent Infini, Bear Counter and Bear Map. Each one is a separate skill with its own page in this directory, installs the same way Bear Trace does, and is maintained by xuzhougeng in that same repository. The rest of the collection is listed on the xuzhougeng/wisp-science page.
How does Bear Trace compare to other AI Engineering skills?
Bear Trace ranks #1357 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. 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 Bear Trace against them. Open each page to compare what they document and how they install.