Tech Batch logo

Tech Batch

Community
ricky-theseus
tech-batch

批量生产内容。外层循环按计划调度条目,内层循环走产→审→改→再审直到零问题。产和审由不同 agent 完成。

Overview

Publisherricky-theseus
RepositoryDaisyWriter
Skill nametech-batch
Stars
77
Forks
5
Bundled files
Instructions only
LicenseGPL-3.0
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 ricky-theseus on GitHub. Read the source before you install it.

Installation

Install the Tech Batch 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/ricky-theseus/DaisyWriter/tree/master/skills/tech/batch
  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/ricky-theseus/DaisyWriter.git /tmp/DaisyWriter
mkdir -p .claude/skills
cp -r /tmp/DaisyWriter/skills/tech/batch .claude/skills/tech-batch
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tech Batch 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 Tech Batch 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 Tech Batch 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.

批量生产流水线

核心原则

产 agent 和审 agent 不能是同一个。 产 agent 负责产出内容,审 agent 负责质量把关。

审 agent 每次调用都是新的子 agent 调用,不带历史上下文——真正做到双重验证,不依赖前一次的判断。

二层架构

外层循环(调度器)
┌────────────────────────────────────────────────────┐
│  read 计划文件 → 解析条目标清单                     │
│  for each item in plan:                            │
│    if item.completed → skip                        │
│    dispatch 内层循环(item)                         │
│    collect result                                  │
│    update progress                                 │
└────────────────────────────────────────────────────┘

内层循环(产审循环)
┌────────────────────────────────────────────────┐
│  产 agent(产出初稿)                           │
│    → 按 item 配置加载素材/参考/规范             │
│    → 产出 → 保存到 {output_dir}                │
└──────────┬─────────────────────────────────────┘
           ▼
┌────────────────────────────────────────────────┐
│  审 agent(盲审,无上下文记忆)                 │
│    → 只读产出物                                 │
│    → 按审查标准逐项检查                         │
│    → 返回 {passed, blocking}                   │
└──────────┬─────────────────────────────────────┘
      ┌────┴────┐
      ▼         ▼
   passed    not passed
      │         │
      │         └──→ 产 agent 修改
      │                → 逐条处理 blocking
      │                → 保存修改
      │                → 回到审 agent
      │
 ┌────┴────┐
 ▼
标记 completed

计划文件格式

计划文件定义一批生产条目。路径由外层循环指定。

yaml
# plan.yaml 示例
project: "AI Agent 框架生态篇"
output_root: "博文/AI/Agent/草稿"
reference_root: "博文/参考文章/Agent"

items:
  - id: "langchain-lcel"
    title: "LangChain LCEL 核心模式与组合"
    produce_prompt: >
      写一篇 LangChain LCEL 的技术文章。
      风格:概念速查 → 底层原理 → 架构设计原则。
      包含 Mermaid 图 + 可运行代码。
    review_questions:
      - "字数 ≥ 800?"
      - "结构是否三段齐全?"
      - "Mermaid 图独立代码块、无嵌套 subgraph?"
      - "代码可复制、版本号/API 明确?"
      - "无面试八股、无博文关联、无下一篇引导?"
    references:
      - "LangChain/LangChain_WanZheng_JiaoCheng"
      - "LangChain/LangChain_Agent_ReAct"

  - id: "crewai-core"
    title: "CrewAI 核心概念"
    ...

计划文件与内层循环的审查标准解耦。每个条目可以定义不同的 review_questions,外层循环不需要知道具体审查什么,只负责调度流转。

内层循环:产审循环

产 agent

  • 接收 item 配置(title, produce_prompt, references, format_guidelines)
  • 加载参考素材
  • 产出内容并保存到 {output_root}/{id}.md
  • 返回 {id, status: "produced", word_count}

审 agent(盲审)

  • 只读产出物,不带历史上下文
  • 按 item 的 review_questions 逐条回答 yes/no
  • no 必须指出具体位置
  • 全部 yes → passed。任意 no → blocking

循环

审不过 → 产 agent 按 blocking 逐条修改 → 保存 → 调审 agent(新调用) → 再审,直到零 blocking 才退出。

不设重试上限。审不过是流程的一部分,不是异常。

进度文件

每完成一条实时写入 batch_progress.json:

json
{
  "project": "AI Agent 框架生态篇",
  "plan": "series_plan.md",
  "items": [
    {"id": "langchain-lcel", "status": "completed", "review_rounds": 2},
    {"id": "crewai-core", "status": "pending", "review_rounds": 0}
  ],
  "current": 0,
  "completed": 1,
  "failed": [],
  "status": "running"
}

中断后重新运行时读进度文件,跳过已 completed 的条目。

硬规则

  • 产 agent 和审 agent 永远是两次独立的 Task 调用
  • 审 agent 每次调用不带历史上下文(盲审)
  • 审不通过不进下一个条目,不设重试上限
  • 审 agent 不提替代方案,只按问题逐条回答
  • blocking 不可修复时暂停提示用户
  • 进度文件每完成一条实时更新

Frequently asked questions

What does the Tech Batch AI skill do?

批量生产内容。外层循环按计划调度条目,内层循环走产→审→改→再审直到零问题。产和审由不同 agent 完成。

Why use Tech Batch on TypingMind?

Because you install it once and use it with any model. Tech Batch 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 Tech Batch in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ricky-theseus/DaisyWriter/tree/master/skills/tech/batch. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Tech Batch?

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 Tech Batch?

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

Is the Tech Batch AI skill free?

Yes. It is published on GitHub by ricky-theseus under the GPL-3.0 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇