Bear Trace logo

Bear Trace

Community
fei0810
bear-trace

给一个主题或一篇种子论文,向前挖掘它建立在哪些前驱工作上(逐层回溯),再向后补充最新进展,讲清楚这个问题从源头到现在是怎么演化的。底层走真实检索(scimaster-cli),每个节点都锚定真实检索到的论文。 **以下情况请主动触发本技能**:用户问"这个问题是怎么来的"、"帮我溯源这个方向"、"这个领域怎么发展的"、"这篇论文是建立在谁的基础上的"、"从头讲一下这个方向的历史"、"入门一个新领域想先了解演化脉络"——即使用户没有说"bear-trace",只要意图是**理解一个研究问题或领域的来龙去脉**,就使用本技能。加 `-d N` 控制向前溯源的层数(默认 3 层)。 不适用于:为观点找支持文献(用 bear-support)、找反对文献(用 bear-counter)、选题查重(用 bear-scoop)、概念地图(用 bear-map)。

Overview

Publisherfei0810
Repositorybear-research-skills
Skill namebear-trace
Stars
73
Forks
16
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by fei0810 on GitHub. Read the source before you install it.

Installation

Install the Bear Trace AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/fei0810/bear-research-skills/tree/main/skills/bear-trace
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/fei0810/bear-research-skills.git /tmp/bear-research-skills
mkdir -p .claude/skills
cp -r /tmp/bear-research-skills/skills/bear-trace .claude/skills/bear-trace
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bear Trace in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bear Trace on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bear Trace is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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:

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

除非检索结果明确显示引用、方法继承或问题延续,不要写成直接师承。证据不足时写"候选前驱"或"可能相关前驱",并放入检索缺口。

Step 3 — 补充前沿 向另一个方向搜索:过去 1–2 年的最新进展,让溯源线延伸到现在而不是只停在过去。

Step 4 — 组装传承线 把检索结果串成一条从最早根源到当前前沿的故事线,每个节点:

  • 一篇真实检索到的论文(标题、作者、年份)
  • 一行"它在这条线上改变了什么"

传承线不追求填满年份。宁可留下缺口,也不要插入无法锚定的过渡节点。

输出格式

── 传承线 ──────────────────────────────────

2010  ●  Smith et al. — "论文标题"
      │  改变了什么(一句话)
      ↓
2016  ●  Jones et al. — "论文标题"
      │  改变了什么(一句话)
      ↓
2023  ●  Lee et al. — "论文标题"   ← 当前前沿
         改变了什么(一句话)

────────────────────────────────────────────
贯穿问题:一直被重新问的那件事(一句话)
开放边缘:这条线下一步可能走向哪里(一句话)
检索缺口:有则列出并说明原因;无则写"无已知缺口"

检索缺口这一行不可省略——它让用户知道哪些节点有实证支撑、哪里存在盲点。

输出物

检索结束后创建 {topic-slug}/ 子文件夹,输出四个东西:

  1. 终端 — 直接 print TUI 格式(竖向时间线)
  2. report.md — 按 output-system.md 的结构化 Markdown 规范生成:稳定 YAML front matter + 一眼结论 + 传承链 + 阅读顺序 + 证据表 + 详细证据 + 检索透明度 + 可复用 JSON
  3. report.html — 自包含 HTML,按 output-system.md 规范生成
  4. references.bib — 合并所有 query 生成的 .bib 文件,去重后只保留报告中实际引用的文献条目

HTML 签名体验:竖向传承时间线,强调色 #d97706(琥珀)。末尾三张 summary cards:贯穿问题 / 开放边缘 / 检索缺口。HTML 组件规范见 output-system.md 的 bear-trace 节。

简单查询只给 1–2 条轻量下一步。入门领域或写综述时给具体建议:阅读顺序、哪条边证据最弱、综述分段逻辑。

诚实边界

数据库覆盖有限,传承链可能存在缺口。发现缺口就标出来,不用伪造一个过渡节点来填补。完整的文献综述或空白地图是产品级任务,交给 SciMaster。

Gotchas

  • 不要用记忆填节点:某一层检索不到合适论文时,宁可在"检索缺口"里说明,也不要凭训练数据补一篇"应该存在"的论文。
  • 时间线不要强求连续:两个节点之间有年份空缺是正常的,不要插入没有检索依据的过渡论文来填满时间轴。
  • 传承边关系要明确:每条边必须写关系类型(方法来源/问题来源/证据来源/领域转折),"相关"或"影响了"不是有效的关系描述。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Bear Trace AI skill do?

给一个主题或一篇种子论文,向前挖掘它建立在哪些前驱工作上(逐层回溯),再向后补充最新进展,讲清楚这个问题从源头到现在是怎么演化的。底层走真实检索(scimaster-cli),每个节点都锚定真实检索到的论文。 **以下情况请主动触发本技能**:用户问"这个问题是怎么来的"、"帮我溯源这个方向"、"这个领域怎么发展的"、"这篇论文是建立在谁的基础上的"、"从头讲一下这个方向的历史"、"入门一个新领域想先了解演化脉络"——即使用户没有说"bear-trace",只要意图是**理解一个研究问题或领域的来龙去脉**,就使用本技能。加 `-d N` 控制向前溯源的层数(默认 3 层)。 不适用于:为观点找支持文献(用 bear-support)、找反对文献(用 bear-counter)、选题查重(用 bear-scoop)、概念地图(用 bear-map)。

Why use Bear Trace on TypingMind?

Because you install it once and use it with any model. Bear Trace is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bear Trace in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/fei0810/bear-research-skills/tree/main/skills/bear-trace. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Bear Trace?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bear Trace?

As many as you like. As long as a model supports skills, you can use Bear Trace with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bear Trace AI skill free?

It is published on GitHub by fei0810. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇