Paper Insight Local logo

Paper Insight Local

Community
Keming-Shen
paper-insight-local

面向 MotionSurf 已生成单篇 note 的论文 insight 提炼入口。当用户希望把某篇已完成的 ReadNote/ResearchPaper/<Paper>/note.md 进一步提炼成可积累的知识库条目、Obsidian 友好的 insight markdown、或为后续 overview / taxonomy / graph 做中间语义层时,优先使用这个 skill。它只消费已有 note.md 与 meta.json,不直接重做论文解读。

Overview

PublisherKeming-Shen
RepositoryMotionSurf
Skill namepaper-insight-local
Stars
104
Forks
0
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

    Published by Keming-Shen on GitHub. Read the source before you install it.

Installation

Install the Paper Insight Local 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/Keming-Shen/MotionSurf/tree/main/.claude/skills/paper-insight-local
  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/Keming-Shen/MotionSurf.git /tmp/MotionSurf
mkdir -p .claude/skills
cp -r /tmp/MotionSurf/.claude/skills/paper-insight-local .claude/skills/paper-insight-local
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paper Insight Local 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 Paper Insight Local 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 Paper Insight Local 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.

Paper Insight Local

你负责把 MotionSurf 中已经完成单篇解读的一篇论文,进一步提炼为可复用的 insight 层产物。

输出目标:

  • ReadNote/ResearchPaper/<Paper>/insight.json
  • ReadNote/ResearchPaper/<Paper>/insight.md
  • ReadNote/Wiki/KnowledgeUnits/... 下的 Layer 2 critique-oriented knowledge units
  • ReadNote/Wiki/KnowledgeUnits/index.json
  • ReadNote/Wiki/KnowledgeUnits/state.json
  • ReadNote/Wiki/motion_generation_insight_map.md
  • ReadNote/Wiki/motion_generation_insight_state.json
  • ReadNote/Wiki/Graph/... 下的少量 Obsidian 节点页
  • ReadNote/Wiki/Taxonomy/... 下的 taxonomy 导航层
  • ReadNote/Wiki/ReviewPacks/... 下的子领域综述包
  • 必要时同步轻量状态到 registry / insight index

适用场景

当用户有以下意图时使用本 skill:

  • 想把单篇论文 note 提炼成更短、更结构化的知识条目
  • 想为 MotionSurf 的领域总览准备中间语义层
  • 想为 Obsidian / graph / wikilink 组织生成更适合浏览的 markdown
  • 想批量补齐已有论文 note 的 insight 层

以下情况不要把它当主工具:

  • 用户还没有生成单篇论文 note:先交给 paper-read-local
  • 用户要直接刷新领域总览:交给 motion-overview
  • 用户要直接联网找论文:交给 hunter 类 skill

输入约束

默认只消费以下本地产物:

  • ReadNote/ResearchPaper/<Paper>/note.md
  • ReadNote/ResearchPaper/<Paper>/meta.json
  • ReadNote/Wiki/paper_registry.json(仅用于选择与身份信息,不作为主语义证据)

不要默认重新读取原论文 markdown 或代码目录,除非 note 缺失、损坏,或用户明确要求 fallback。

生成原则

  1. insight 不是第二份长 note,而是更短、更结构化、可跨论文对齐的中间知识层。
  2. 语义提炼交给 LLM,脚本只负责读取 note/meta、调用模型、写文件、同步索引。
  3. 优先保留:生态位、核心贡献、技术 takeaways、优点、局限性、MotionSurf 影响、与 task/dataset/method family 的关系。
  4. 所有高层判断都必须能回溯到当前 note.md,不要超出单篇 note 已经支持的边界。
  5. insight.md 可以引入 Obsidian 友好的 frontmatter / tags / [[wikilinks]],但不要批量改写既有 note.md。
  6. 如需输出 [[wikilinks]],优先复用已有 canonical 命名:论文标题优先跟随 registry,稳定任务/方法/数据集节点优先跟随现有 ReadNote/Wiki/Graph/... 的约定,不要在同一链路里混用大小写或同义别名。
  7. Layer 2 的 KnowledgeUnits 是正式中间层:它存储可复用、可追溯、面向 critique 的领域判断,而不是普通摘要。新论文若支持、修正或反驳已有 unit,应更新对应 unit;若提出新的跨论文可复用判断,才创建 candidate unit。
  8. Knowledge unit 不应从单篇论文直接升级成领域共识。默认新 unit 从 candidate 开始;只有多篇论文或 survey 证据支撑时才升为 emerging / stable。
  9. 如果要把论文进一步注入 wiki 累计知识页,必须让 LLM 先读取当前 ReadNote/Wiki/motion_generation_insight_map.md 的现状,再结合这篇论文的 insight.json / insight.md / note.md / KnowledgeUnits 做整页更新,而不是简单尾部追加。
  10. wiki 累计页与 motion_generation_overview.md 分工不同:前者高频、跨论文、渐进累积;后者低频、稳定、教科书式,不应在每次新论文注入时直接重写。

推荐执行方式

优先运行仓库内的 insight runner:

bash
python ".claude/skills/paper-insight-local/scripts/generate_paper_insight.py" --paper "<paper title or dir>"

如需批量补齐已有 note 的 insight,可运行:

bash
python ".claude/skills/paper-insight-local/scripts/batch_generate_paper_insights.py" --all --only-missing-insight --dry-run
python ".claude/skills/paper-insight-local/scripts/batch_generate_paper_insights.py" --limit 5
python ".claude/skills/paper-insight-local/scripts/batch_generate_paper_insights.py" --match diffusion --limit 5
python ".claude/skills/paper-insight-local/scripts/batch_generate_paper_insights.py" --paper "HUMAN MOTION DIFFUSION MODEL" --paper "Generating Diverse and Natural 3D Human Motions from Text" --sync-wiki final

默认的一键自动化入口是:

bash
python ".claude/skills/paper-insight-local/scripts/generate_paper_insight.py" --paper "<paper title or dir>"

这个主脚本现在会自动:

  • 定位目标论文 note/meta
  • 选择少量高价值语义字段作为输入
  • 调用 Claude 生成结构化 insight
  • 写入 insight.json / insight.md
  • 更新 registry 轻量 insight 状态与全局 insight index
  • 调用 Layer 2 updater,维护 ReadNote/Wiki/KnowledgeUnits/...、KnowledgeUnits/index.json 与 KnowledgeUnits/state.json
  • 继续调用 wiki 注入脚本,把该论文同步进累计 wiki insight 页面与 graph 节点页
  • 最后重建 taxonomy 与 review pack 层,使相关子领域综述自动更新

Layer 2 updater 的默认行为是:

  • 读取 ReadNote/Wiki/KnowledgeUnits/index.json 与 shortlist 相关 unit
  • 判断新论文支持、修正、反驳哪些已有 unit
  • 仅在有跨论文复用价值时创建新的 candidate unit
  • 保守重建 KnowledgeUnits/index.json / KnowledgeUnits/state.json

如需单独重跑 wiki 累计页与 graph 节点,而不重做单篇 insight,可运行:

bash
python ".claude/skills/paper-insight-local/scripts/update_wiki_insight.py" --paper "<paper title or dir>"

这个第二个脚本负责:

  • 读取当前 ReadNote/Wiki/motion_generation_insight_map.md(若存在)
  • 读取目标论文的 insight.json / insight.md / note.md / meta.json
  • 调用 Claude 更新累计 wiki insight 页面
  • 写入 motion_generation_insight_map.md / motion_generation_insight_state.json
  • 写入少量 ReadNote/Wiki/Graph/... 节点页

如需在不改动现有 flat graph 的前提下,额外生成一套更适合分类导航的 taxonomy 层,可运行:

bash
python ".claude/skills/paper-insight-local/scripts/build_motion_taxonomy.py" --dry-run
python ".claude/skills/paper-insight-local/scripts/build_motion_taxonomy.py" --deterministic-only
python ".claude/skills/paper-insight-local/scripts/build_motion_taxonomy.py" --category method:diffusion --category task:text-to-motion --category dataset:humanml3d

这个 taxonomy 脚本负责:

  • 读取 paper_insight_index.json、paper_registry.json 与各论文的 meta.json / insight.json
  • 先构建 deterministic taxonomy inventory
  • 再生成领域根页 ReadNote/Wiki/Taxonomy/index.md
  • 生成 axis hub:ReadNote/Wiki/Taxonomy/Axes/{methods,tasks,datasets}.md
  • 生成 ReadNote/Wiki/Taxonomy/Categories/Methods/*.md
  • 生成 ReadNote/Wiki/Taxonomy/Categories/Tasks/*.md
  • 生成 ReadNote/Wiki/Taxonomy/Categories/Datasets/*.md
  • 在 task 类页面中额外生成 chronology section(task -> year -> paper)
  • 生成关系侧页:ReadNote/Wiki/Taxonomy/Relations/{authors,institutions}.md
  • 生成 ReadNote/Wiki/ReviewPacks/*.md 子领域综述包
  • 写入 ReadNote/Wiki/Taxonomy/taxonomy_state.json

它与旧层分工如下:

  • 旧层:motion_generation_insight_map.md + Graph/...,承担累计型 cross-link layer
  • 新层:Taxonomy/...,承担分层导航型 layer
  • 关系侧层:Taxonomy/Relations/...,承担 researcher / institution lineage overlay

输出要求

insight.json 至少包含

  • paper_id
  • paper_title
  • source_note
  • source_meta
  • insight_version
  • generated_at
  • positioning
  • technical_takeaways
  • strengths
  • limitations
  • evidence_anchors
  • motionsurf_impact
  • relations
  • obsidian

insight.md 的目标风格

  • 更短、更适合浏览
  • 明确体现生态位 / 贡献 / 优缺点 / MotionSurf 影响
  • 允许使用 YAML frontmatter
  • 允许使用 [[wikilinks]]
  • 不要求像 note.md 一样逐节完整展开

Layer 2 KnowledgeUnits 的目标风格

  • 每个 unit 只表达一个可复用的领域判断、评测警告、方法分化轴、伪创新模式或 critique hook
  • v1 schema 保持精简:id、type、title、statement、scope、status、confidence、evidence、why_it_matters、questions_to_ask、source_paths、last_updated
  • 优先类型:stable_judgment、evaluation_warning、method_split、false_novelty_pattern、critique_hook
  • 默认状态:证据不足时写 candidate;跨论文或 survey 支撑后才升为 emerging / stable
  • 判断标准:只有能帮助未来评估新论文、新 idea 或新代码仓库的内容才进入 Layer 2

汇报要求

回复时简短说明:

  • 为哪篇论文生成了 insight
  • 写入了哪些文件
  • registry / insight index 是否已同步
  • 哪些关系或 graph link 目前仍只是候选、还不应视为强事实

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 Paper Insight Local AI skill do?

面向 MotionSurf 已生成单篇 note 的论文 insight 提炼入口。当用户希望把某篇已完成的 ReadNote/ResearchPaper/<Paper>/note.md 进一步提炼成可积累的知识库条目、Obsidian 友好的 insight markdown、或为后续 overview / taxonomy / graph 做中间语义层时,优先使用这个 skill。它只消费已有 note.md 与 meta.json,不直接重做论文解读。

Why use Paper Insight Local on TypingMind?

Because you install it once and use it with any model. Paper Insight Local 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 Paper Insight Local in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Keming-Shen/MotionSurf/tree/main/.claude/skills/paper-insight-local. 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 Paper Insight Local?

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 Paper Insight Local?

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

Is the Paper Insight Local AI skill free?

It is published on GitHub by Keming-Shen. 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 👇