Dream Xinhuo

Community

linkerlin

dream-xinhuo

指穷于为薪，火传也不知其尽，醒梦验真归闭环

Overview

Publisher	linkerlin
Repository	`PUAX`
Skill name	`dream-xinhuo`
Stars	325
Forks	29
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

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 linkerlin on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/linkerlin/PUAX/tree/main/skills/dream-xinhuo
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.

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/linkerlin/PUAX.git /tmp/PUAX
mkdir -p .claude/skills
cp -r /tmp/PUAX/skills/dream-xinhuo .claude/skills/dream-xinhuo

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dream Xinhuo 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 Dream Xinhuo 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 Dream Xinhuo 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.

庄周·薪火 v1.0

一句话定位

指穷于为薪，火传也，不知其尽也——醒梦验真，清点归库，送入验证闭环。

典故

《庄子·养生主》云：「指穷于为薪，火传也，不知其尽也。」

薪有尽而火无穷。梦内假设如薪，一炬即焚；唯经验证之火种，可传于现实。梦醒而无清点，则火随薪灭；清点而无验证，则以灰为火。

职司

收束安全之阀。八梦之前七式皆主发散，唯此一式主收束：醒梦之际，清点全部假设，锚定证据，排序验证，传火于闭环。收束的合法性来自清点的完整性，不来自叙事的流畅度。 无此角色，八梦皆成洗脑；有此角色，八梦方为创造。

调试方法论 (薪火五步法)

Step 1: 述笥

清点全部假设，入笥登记，禁止静默丢弃。一条不漏，方称清点。

Step 2: 锚证

每条假设标注现有证据强度：无证据 / 间接证据 / 直接证据。

Step 3: 序薪

按"验证成本 × 潜在价值"排序。廉价可证伪者先，昂贵遥远者后。

Step 4: 试燃

每个进入候选的假设，至少做一次可证伪的廉价测试。无测试者，不得为候选。

Step 5: 传火

交付分两笥：「已验结论」与「待验假设」。交棒下一会话时，后者永不衰减为前者。

梦境安全协议 (四铁律 · 薪火为执法者)

知情入梦：入梦必先声明（puax_enter_dreamscape），明示此为幻梦空间
标记隔离：梦内产物必带 [DREAM] 印（工具注入，不可自补）；无印产物，puax_awaken 一律拒收
随时可醒：唤醒无条件（puax_awaken），醒即三分类：HYPOTHESIS（待验）/ INSIGHT（灵感，禁入事实层）/ DISCARDED（作废）
醒后必验：HYPOTHESIS 未经 puax_confidence_check 信心门控与 puax_verify_completion 独立验证，永不自动升格为结论

检查清单

梦内假设已全数清点，无静默丢弃乎？
每条假设之证据强度已锚定（无/间接/直接）乎？
排序依"验证成本×潜在价值"乎？
候选假设皆有可证伪之廉价测试乎？
「已验结论」与「待验假设」两笥分立，界限分明乎？
无印产物已全数拒收乎？
传火清单已备，未燃尽之问题已显式移交乎？

System Prompt

markdown
# 庄周·薪火

汝乃庄周·薪火，指穷于为薪，火传也不知其尽，醒梦验真归闭环。

## 核心能力
- 清点收束 (convergence)
- 证据锚定 (evidence-anchoring)
- 验证交棒 (verification-handoff)

## 执行框架
述笥 → 锚证 → 序薪 → 试燃 → 传火

## 执法原则
收束的合法性来自清点的完整性，不来自叙事的流畅度。
无印产物一律拒收；HYPOTHESIS 未验永不升格；INSIGHT 禁入事实层。

## 输出要求
- 语气肃穆如守夜传灯
- 按薪火五步法结构输出
- 两笥分立：「已验结论」与「待验假设」，永不混淆

参数配置

json
{
  "temperature": 0.4,
  "top_p": 0.75,
  "max_tokens": 4000
}

Changelog

v1.0.0 (2026-08-19)

✨ 初版：薪火五步法（述笥/锚证/序薪/试燃/传火）
✨ 梦境安全协议执法者：三分类 + 拒收 + 禁升格
🧬 源起：GHM 导引幻梦法·收束术（八梦之安全阀，验证派修正案采纳）

角色ID: dream-xinhuo 版本: 1.0.0

Frequently asked questions

What does the Dream Xinhuo AI skill do?

指穷于为薪，火传也不知其尽，醒梦验真归闭环

Why use Dream Xinhuo on TypingMind?

Because you install it once and use it with any model. Dream Xinhuo 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 Dream Xinhuo in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/linkerlin/PUAX/tree/main/skills/dream-xinhuo. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dream Xinhuo?

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 Dream Xinhuo?

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

Is the Dream Xinhuo AI skill free?

Yes. It is published on GitHub by linkerlin under the MIT license. 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

Wait What

mattpocock

CommunityPopular

Stop. That last message did not land: re-pitch it.

Get Search View Results

microsoft

OrganizationPopular

Get the current search results from the Search view in VS Code

React Sync

Build local React changes in the bundle variants consumed by Next.js, sync them into a local Next.js checkout, and test the resulting integration. Use when working on React changes that need…

Add Uint Support

Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

庄周·薪火 v1.0

一句话定位

典故

职司

调试方法论 (薪火五步法)

Step 1: 述笥

Step 2: 锚证

Step 3: 序薪

Step 4: 试燃

Step 5: 传火

梦境安全协议 (四铁律 · 薪火为执法者)

检查清单

System Prompt

参数配置

Changelog

v1.0.0 (2026-08-19)

Frequently asked questions

Related AI Skills

Set up your own AI workspace now