Wander Synthesis logo

Wander Synthesis

CommunityPopular
Jamailar
wander-synthesis

漫步选题综合技能,用于从随机素材中选出高互动母版、拆解其内容公式,再从三条素材里挖掘细小选题,并完成基础质量自检。

Overview

PublisherJamailar
RepositoryBeav
Skill namewander-synthesis
Stars
1.7K
Forks
225
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Wander Synthesis 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.
  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/Jamailar/Beav.git /tmp/Beav
mkdir -p .claude/skills
cp -r /tmp/Beav/desktop/builtin-skills/wander-synthesis .claude/skills/wander-synthesis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wander Synthesis 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 Wander Synthesis 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 Wander Synthesis 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.

Wander Synthesis

用于漫步页的随机灵感选题。宿主负责机械地随机选择素材;本技能负责后续 AI 判断流程。

核心原则:漫步不是三篇素材合并,不是找一个能概括三篇的大主题。漫步要先找出数据最强的母版,再借另外两篇提供小细节、小场景、小反差,产出一个越细越好的选题。

输入边界

  • 只使用本轮随机素材、宿主预读素材包,以及必要时补读到的同一批素材文件。
  • 不读取、不引用、不迁就用户档案、长期记忆、账号定位或其他知识库内容。
  • 预读素材包足够时,不要调用工具;只有内容缺口会影响判断时,才补读 1-2 个具体文件。
  • 不做目录侦察,不为了显得勤奋而 List/Search。

思考流程

  1. 先判断每条素材的内容价值类型,不要一开始就想标题。
素材价值更适合贡献什么灵感
新知识解释、科普、入门认知
方法步骤、清单、行动承诺
观点洞察、反常识、判断
案例拆解、复盘、故事场景
数据趋势、判断依据、对比
资源合集、工具、书单、素材
冲突争议、对比、讨论入口
情绪共鸣、处境、身份表达
  1. 再看互动数据,默认以 likes 最高且内容价值最清楚的素材为母版;如果 likes 缺失,再参考 collects/comments 或内容完整度,但要在 thinking_process 里说明。
  2. 拆母版公式:它靠什么成立,可能是标题 hook、目标人群、情绪张力、叙事结构、场景包装、反常识判断、行动承诺、细节可信度或素材价值类型本身。
  3. 另外两条素材不是并列主题,只用于找灵感:可以借一个词、一个场景、一个比喻、一个动作、一个痛点、一个反差、一个价值类型补充,不能为了覆盖率硬串。
  4. 在三条素材里寻找最小可写细节。优先选择窄到一篇笔记能讲透的切口,而不是宏大议题、合集、方法论总论。
  5. 收敛成一个可继续创作的小选题:目标读者、核心矛盾、叙事角度、母版公式和细节切口必须清楚。
  6. 先定 direction_frame,再写标题和 content_direction
  7. 如果本轮要把漫步方向继续写成小红书图文标题,并且 xhs-title 已激活,标题阶段必须先按 xhs-title 的公式匹配逻辑内部筛选;漫步结果只输出最终标题,不输出公式编号、候选标题或推荐理由。

质量标准

  • 标题必须像真实内容选题,不能是“从某素材延展出的内容选题”“未命名选题”。
  • 面向小红书图文创作的标题必须符合 xhs-title 的 20 字以内和标题张力规则。
  • content_direction 必须说明母版是谁、借用了母版什么公式、另外素材提供了哪个细节灵感、最终小切口是什么。
  • direction_frame.target_readercore_tensionanglematerial_entry 都要是具体中文短句,其中 material_entry 要写清母版公式和细节来源。
  • connections 只能包含实际参与最终方向的素材序号,取值范围是 1-3。
  • 不要把三条素材机械拼接成摘要;不要追求覆盖三篇;质量、传播性、可写性和细节颗粒度优先。
  • 越细、越小、越具体的选题越好。避免“AI 时代如何做产品”“年轻人如何找回自己”这类大题,优先“为什么宅家越休息越迟钝”“一个穿搭词怎么包装低能量生活”等小题。

自检

  • 是否引入了本轮素材之外的知识或账号定位。如果有,删除。
  • 是否把点赞最高的素材作为母版。如果没有,必须有明确理由。
  • 是否为了覆盖率硬塞另外两条素材。如果有,删掉,只保留真正提供细节灵感的部分。
  • 选题是否还太大。如果是,继续缩小到一个具体人群、具体状态、具体动作或具体瞬间。
  • 标题是否太像 AI 占位句。如果是,重写。
  • 方向是否具体到目标读者、冲突和切口。如果不是,补齐。

最终输出标准

最终只输出一个 JSON 对象。不要输出 Markdown、不要用 ```json 代码块、不要输出字段说明、不要把中间分析对象塞进结果。

single_choice 必须严格使用这个结构:

json
{
  "content_direction": "一句话说明母版是谁、借了什么公式、哪个素材提供细节、最终小切口是什么",
  "thinking_process": [
    "母版选择:素材 X,因为互动数据和内容价值最强",
    "细节灵感:素材 Y 提供了具体场景/反差/动作",
    "收敛判断:最终选题足够小,能一篇笔记讲透"
  ],
  "topic": {
    "title": "20字以内的真实内容标题",
    "connections": [1, 2]
  },
  "direction_frame": {
    "target_reader": "具体目标读者",
    "core_tension": "具体核心矛盾",
    "angle": "具体叙事角度",
    "material_entry": "母版公式和细节来源"
  }
}

输出前按顺序检查:

  1. 顶层字段只能是 content_directionthinking_processtopicdirection_frame;多选模式才允许 optionsselected_index
  2. thinking_process 只能是 2-4 条短字符串,不能是对象,不能包含 material_analysismother_template_selection 这类嵌套分析。
  3. topic.titlecontent_directiondirection_frame.target_readerdirection_frame.core_tensiondirection_frame.angledirection_frame.material_entry 都不能为空。
  4. topic.connections 只能是 1-3 的数字数组,只放实际参与最终小选题的素材。
  5. 如果 JSON 会超过输出预算,删减 thinking_process,不能删最终结构字段。

进入创作时

  • 漫步结果只是起点,不是成稿提纲。
  • 创作阶段以最终文章质量为第一目标,不要求把三条素材都写进去。
  • 可以只继承母版公式和一个小细节,然后自由完成新的表达。
  • 如果素材关联会拖累文章,宁可断开关联,也不要强行解释三篇素材之间的关系。

Frequently asked questions

What does the Wander Synthesis AI skill do?

漫步选题综合技能,用于从随机素材中选出高互动母版、拆解其内容公式,再从三条素材里挖掘细小选题,并完成基础质量自检。

Why use Wander Synthesis on TypingMind?

Because you install it once and use it with any model. Wander Synthesis 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 Wander Synthesis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Jamailar/Beav/tree/main/desktop/builtin-skills/wander-synthesis. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Wander Synthesis?

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 Wander Synthesis?

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

Is the Wander Synthesis AI skill free?

It is published on GitHub by Jamailar. 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 👇