Bear Propose logo

Bear Propose

Community
fei0810
bear-propose

给一个研究 idea,依次执行撞车检测、安静区支撑检索、潜在挑战检索,在一份综合报告里呈现这个 idea 的立项前证据格局——撞车风险在哪、安静区里有没有文献支撑、最需要提前想清楚的挑战是什么。底层走真实检索(scimaster-cli),绝不编造引用。 **以下情况请主动触发本技能**:用户想"开题前评估一下"、"这个 idea 值不值得做"、"立项前做个全面的文献调研"、"帮我评估这个研究方向"——即使没有说"bear-propose",只要意图是**在正式投入一个研究方向之前做综合评估**,就使用本技能。 不适用于:只查撞车(用 bear-scoop)、只找支持(用 bear-support)、只找反对(用 bear-counter)、概念地图(用 bear-map)、溯源演化史(用 bear-trace)。

Overview

Publisherfei0810
Repositorybear-research-skills
Skill namebear-propose
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 Propose 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-propose
  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-propose .claude/skills/bear-propose
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bear Propose 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 Propose 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 Propose 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-propose · 研究立项前评估

一个工作流:在你正式投入之前,把撞车风险、安静区的证据基础、潜在挑战这三件事同时查清楚。这三步不是简单串联——撞车检测的结果会影响后两步的检索方向:支持和挑战的检索聚焦在安静区,而不是整个 idea 的全貌。这让 bear-propose 比分别跑三个 skill 更有价值。

先读 references/sci-cli.md——CLI 检测步骤、用法和铁律。 再读 references/output-system.md——HTML 外壳规范和设计 token。

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 — 压缩 idea,执行撞车检测 把 idea 提炼成一句话。从 5–6 个正交角度检索(字面表述 / 方法中心 / 问题中心 / 结论中心 / 相邻领域 / 抢发者标题),宽泛角度用 ultra_low,有收获的角度用 low 复跑,合并去重,按四层分类(直接撞车 / 方法孪生 / 问题孪生 / 邻居)。

告知用户本次将执行约 15–20 次检索,然后直接开始,不等待确认。

Step 2 — 识别安静区 根据撞车结果,明确哪些角度拥挤、哪些角度安静。安静区是后续检索的重点——在安静区里找支撑,才是真正有意义的文献基础。

Step 3 — 安静区支撑检索 针对安静区的 1–2 个核心角度,执行 sci search(--mode low,--limit 15),找出能支撑这个 idea 在安静区里有意义的文献。按四级口径筛选。如果安静区里支撑信号很弱,如实说——这意味着这个方向确实少有人做,但也可能是因为做了没有价值。

Step 4 — 潜在挑战检索 针对安静区的核心主张,执行反对文献检索(聚焦直接矛盾和方法批评两类,各用一次 low 检索),找出需要提前想清楚的挑战。不需要覆盖所有五类,只检索与立项最相关的两类。

Step 5 — 综合判断 基于三个 phase 的检索结果写 3–5 句立项前的证据格局描述:撞车风险级别、安静区的支撑信号强度、最需要在研究设计中提前应对的挑战类型。不做"这个 idea 值不值得做"的最终判断。

输出物

检索结束后,在当前目录创建 {topic-slug}/ 子文件夹,输出四个东西:

  1. 终端 — 直接 print 综合摘要:撞车风险级别 + 安静区主要角度 + 最需提前想清楚的挑战
  2. report.md — 稳定 YAML front matter + 综合判断 + 撞车分层 + 安静区支撑 + 潜在挑战 + 检索透明度
  3. report.html — 综合报告,见下方 HTML 规范
  4. references.bib — 合并所有 query 的 .bib,去重后只保留报告引用的文献

HTML 报告规范

强调色 #d97706(琥珀,体现"决策前"的审慎感,区别于 bear-scoop 的蓝和 bear-counter 的红)。

首屏:综合判断面板

.verdict 区块横向三段:

  • 左:撞车风险摘要(级别 + 最近撞车候选,蓝色 accent)
  • 中:证据格局描述 3–5 句(琥珀 accent,核心位置)
  • 右:最关键挑战(类型 + 一句核心挑战内容,红色 accent)

.metric-strip:直接撞车数 / 安静区有效支撑文献数 / 高威胁挑战数 / 需要提前应对的关键点数

三阶段详细内容(tabs,三个 tab)

tab「撞车检测」:SVG 四层同心圆雷达(同 bear-scoop 规范),下方四层文献列表。雷达悬停 tooltip 用 JS mousemove 实现。

tab「安静区支撑」:证据阶梯(直接支撑 / 部分支撑 / 间接相关),含安静区说明——为什么这些文献对立项有价值(它们支撑的是别人还没做的角度)。文献卡片含 DOI 链接和中文学术摘要折叠。

tab「潜在挑战」:按两类挑战方向展示(直接矛盾 / 方法批评),每张卡片含威胁等级 + 回应思路:... + DOI 链接 + 中文学术摘要折叠。

三个 tab 中最重要的卡片(最近撞车、安静区最强支撑、最高威胁挑战)加 .card-primary class,摘要默认展开。

检索透明度(底部):列出所有查询词和各 phase 的检索分布,说明安静区如何确定、后两步如何聚焦。

诚实边界

安静区是基于本次撞车检测的相对判断,不代表没有人在做——付费墙后、近期预印本、中文文献均可能遗漏。安静区支撑信号弱可能意味着方向新颖,也可能意味着前人试过但没有发表价值。报告呈现的是检索到的内容,不做"值不值得做"的判断。

Gotchas

  • Step 3 和 Step 4 必须聚焦在安静区,不要对整个 idea 做宽泛的支持和反对检索——那样就和分别跑三个 skill 没有区别
  • 安静区支撑信号弱不是坏事,要在报告里如实呈现,不要为了"看起来有支撑"而降低筛选口径
  • 三个 tab 的配色用各自原 skill 的强调色(蓝/绿/红)作为 accent,整体报告用琥珀色作为框架色,不要混淆
  • 如果撞车检测发现直接撞车超过 5 篇,在 Step 3 开始前先提示用户:安静区很窄,后续检索会聚焦在更细分的角度,本次报告的参考价值取决于用户是否愿意在细分方向上继续调整 idea

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 Propose AI skill do?

给一个研究 idea,依次执行撞车检测、安静区支撑检索、潜在挑战检索,在一份综合报告里呈现这个 idea 的立项前证据格局——撞车风险在哪、安静区里有没有文献支撑、最需要提前想清楚的挑战是什么。底层走真实检索(scimaster-cli),绝不编造引用。 **以下情况请主动触发本技能**:用户想"开题前评估一下"、"这个 idea 值不值得做"、"立项前做个全面的文献调研"、"帮我评估这个研究方向"——即使没有说"bear-propose",只要意图是**在正式投入一个研究方向之前做综合评估**,就使用本技能。 不适用于:只查撞车(用 bear-scoop)、只找支持(用 bear-support)、只找反对(用 bear-counter)、概念地图(用 bear-map)、溯源演化史(用 bear-trace)。

Why use Bear Propose on TypingMind?

Because you install it once and use it with any model. Bear Propose 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 Propose in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/fei0810/bear-research-skills/tree/main/skills/bear-propose. 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 Propose?

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 Propose?

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

Is the Bear Propose 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 👇