⚖️
AI EngineeringHTML

Bear Review

by xuzhougeng

Bear Review 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 Review
Copy Bear Review 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-review ~/.claude/skills/bear-review

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-review/SKILL.md in xuzhougeng/wisp-science
Installs to
~/.claude/skills/bear-review
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering2451 skills

What Bear Review does

Bear Review compares evidence supporting and opposing a claim, then summarizes the strongest support, the most serious counterarguments, and gaps where one side is missing. It is used for balanced, full-scope assessment of a viewpoint with real literature search.

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

Documentation

README

bear-review · 论点攻防评估

一个工作流:把一个观点的正反两侧证据同时摆出来,让你看清这个观点在哪里站得住、在哪里最脆弱。这不是替你做判断,是让局面变得清楚。

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 — 锁定主张 把观点压缩成一个精确、可证伪的句子,挖出隐含的范围(人群、条件、测量方式)。给主张编号 C1;多主张时拆成 C1C2C3,默认优先处理最核心的一条。

告知用户本次将执行约 10–13 次检索,然后直接开始,不等待确认。

Step 2 — 支持侧检索 对主张执行 sci search--mode low--limit 15,偏向直接支持的角度。按四级口径筛选(直接支撑 / 部分支撑 / 间接相关 / 排除),标出最强的那篇。

Step 3 — 反对侧检索 构建五类对立查询并逐一检索(宽泛角度用 ultra_low,有收获的方向用 low 复跑):

  1. 直接矛盾
  2. 边界 / 复杂化
  3. 替代解释
  4. 方法批评
  5. 复制失败 / 零结果

每篇反对文献评定威胁等级(高 / 中 / 低),附一行回应方向。

Step 4 — 交叉分析 检索结束后,做两项交叉:

  • 有支持无反对的角度:列出(不等于安全,可能只是研究不足)
  • 有反对无支持的角度:列出(这是最脆弱的地方)

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

Frequently asked about Bear Review

  • What else does xuzhougeng publish alongside Bear Review?

    Bear Review 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 Review 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 Review compare to other AI Engineering skills?

    Bear Review ranks #1354 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 Review against them. Open each page to compare what they document and how they install.

More from xuzhougeng/wisp-science

Bear Review is one of 25 skills cataloged on DirSkills from xuzhougeng/wisp-science.

See all 25 skills
🧠
1w ago

Agent Infini

Agent Infini uses the InfiniSynapse CLI for multi-turn data analysis with database and RAG context. Use it to start, continue, and inspect analysis tasks and workspace files.
AI Engineering
1K106
🐻
1w ago

Bear Counter

Bear Counter finds real academic papers that challenge a claim with opposing results, boundary conditions, alternative explanations, method critiques, or replication failures. Use it when you want to stress-test a conclusion or prepare for reviewer objections.
AI Engineering
1K106
🗺️
1w ago

Bear Map

Bear Map builds a concept map around a term using real paper abstracts, so each node is anchored to retrieved literature. It also outputs Mermaid and standalone HTML for screenshots, plus 3–6 starter papers.
AI Engineering
1K106
🐻
1w ago

Bear Onboard

Bear Onboard 生成一份综合报告,把陌生领域的概念版图和演化脉络一起梳理出来,帮助快速建立认知框架。它适合想快速入门一个方向、理解核心概念和发展历史时使用。
AI Engineering
1K106
🐻
1w ago

Bear Propose

Bear Propose evaluates a research idea before you commit to it by checking collision risk, support in the quiet zone, and likely challenges. It runs real literature searches and summarizes the evidence without inventing citations.
AI Engineering
1K106
🔎
1w ago

Bear Scoop

Bear Scoop checks whether an idea is already being pursued by searching from several angles and ranking nearby papers by collision risk. Use it before submitting or writing to see the closest competing work, especially with the -r flag for recent preprints.
AI Engineering
1K106