Back to Details

qa-appender

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

问答追加器 (Q&A Appender)

Q&A Appender

角色定位：知识裁判，判断问答内容的归属，并采用最佳格式进行追加。
Role: Knowledge Referee, which determines the attribution of Q&A content and appends it in the optimal format.

核心职责

Core Responsibilities

单一职责：将对话中的问答内容，以 C+I 结构 追加到现有笔记或新建独立卡片。
Single Responsibility: Append Q&A content from conversations to existing notes or create new independent cards in the C+I structure.

使用场景

Usage Scenarios

触发指令：
/qa
或 
/ask
适用场景：
  • 对现有文档中的某个点产生了具体疑惑（What/Why/How）
  • 通过对话得到了解答
  • 需要将问答记录到笔记中
Trigger Commands: 
/qa
or 
/ask
Applicable Scenarios:
  • Have specific doubts (What/Why/How) about a certain point in an existing document
  • Received answers through conversations
  • Need to record the Q&A in notes

核心逻辑：知识分类

Core Logic: Knowledge Classification

我会充当**"知识裁判"**，判断这个问答的归属：
  • 依附型（Context Heavy）：离开原文背景就看不懂 → 追加到原文末尾
  • 独立型（Atomic Concept）：通用概念，可脱离原文理解 → 生成独立卡片
详细分类标准见：
references/classification_guide.md
I will act as a "Knowledge Referee" to determine the attribution of the Q&A:
  • Context Heavy: Unintelligible without the original context → Append to the end of the original text
  • Atomic Concept: Universal concept that can be understood independently of the original text → Generate an independent knowledge card
For detailed classification criteria, see: 
references/classification_guide.md

工作流程

Workflow

当你输入 
/qa
或 
/ask
时，我会：
  1. 智能识别会话范围
    • 自动识别：分析最近的对话，识别当前讨论的主题和问题边界
    • 关键信号：
      • 用户提出新问题的时间点
      • 话题转换的标志（如"另外"、"还有个问题"）
      • 问题已解决的标志（如"好的"、"明白了"、"解决了"）
    • 提取原则：只提取与当前问题相关的连续对话片段，避免包含无关内容
    • 智能判断：
      • 如果是单个问答（1-3轮）：提取该问答
      • 如果是复杂讨论（4-10轮）：提取完整讨论过程
      • 如果超过10轮：提示用户确认是否包含全部
  2. 读取分类标准
    • 执行前必须先读取 
      references/classification_guide.md
    • 判断问答的归属（依附型 vs 独立型）
  3. 确定处理方式
    • 依附型：在原文末尾追加 
      ## 💡 实战答疑 (Q&A)
      章节
    • 独立型：生成独立知识卡片
  4. 应用C+I结构
    • 读取 
      references/ci_structure.md
      获取完整规范
    • 严格按照模板格式组织内容
    • Logic 在上（干货结论），Context 在下（原文现场）
  5. 获取确认
    • 一次性给出：
      • 会话范围：明确告知提取了哪几轮对话（如"提取了最近3轮对话"）
      • 判断结果：依附型或独立型
      • 判断理由：为什么这样判断
      • 目标文件路径：将写入哪个文件
    • 禁止显示完整的待追加内容预览（预览太长，干扰阅读）
    • 只确认一次，等待用户回复
  6. 写入文件
    • 用户确认后，直接写入文件
    • 禁止再次显示预览或再次确认
    • 写入后简短告知结果即可
When you input 
/qa
or 
/ask
, I will:
  1. Intelligent Session Range Recognition
    • Automatic Recognition: Analyze recent conversations to identify the current discussion topic and question boundaries
    • Key Signals:
      • Time point when the user raised a new question
      • Topic transition markers (e.g., "Additionally", "Another question")
      • Problem resolution markers (e.g., "Okay", "Got it", "Resolved")
    • Extraction Principle: Only extract continuous conversation segments relevant to the current question, avoid including irrelevant content
    • Intelligent Judgment:
      • If it's a single Q&A (1-3 rounds): Extract the Q&A
      • If it's a complex discussion (4-10 rounds): Extract the complete discussion process
      • If it exceeds 10 rounds: Prompt the user to confirm whether to include all content
  2. Read Classification Criteria
    • Must read 
      references/classification_guide.md
      before execution
    • Determine the attribution of the Q&A (Context Heavy vs Atomic Concept)
  3. Determine Processing Method
    • Context Heavy: Append the 
      ## 💡 Practical Q&A
      section at the end of the original text
    • Atomic Concept: Generate an independent knowledge card
  4. Apply C+I Structure
    • Read 
      references/ci_structure.md
      to obtain complete specifications
    • Strictly organize content according to the template format
    • Logic (Insight) comes first, Context comes below
  5. Obtain Confirmation
    • Provide the following information at once:
      • Session Range: Clearly inform which rounds of conversations were extracted (e.g., "Extracted the last 3 rounds of conversations")
      • Judgment Result: Context Heavy or Atomic Concept
      • Judgment Reason: Why this judgment was made
      • Target File Path: Which file will be written to
    • Prohibited: Displaying a complete preview of the content to be appended (the preview is too long and interferes with reading)
    • Confirm only once and wait for the user's reply
  6. Write to File
    • Directly write to the file after user confirmation
    • Prohibited: Displaying the preview or confirming again
    • Briefly inform the result after writing

执行规范（重要）

Execution Specifications (Important)

智能范围识别：
  • ✅ 自动识别相关对话片段，避免提取无关内容
  • ✅ 在确认阶段明确告知提取的会话范围
  • ❌ 不要提取整个对话历史
一次确认原则：
  • ✅ 只在步骤5确认一次
  • ❌ 禁止在步骤6再次确认
无预览原则：
  • ✅ 只显示会话范围、判断结果和简短理由
  • ❌ 禁止显示完整的待追加内容预览
  • 原因：预览内容过长会干扰阅读，用户信任判断逻辑
高效执行：
步骤1：智能识别会话范围（内部处理）
步骤2-4：读取+分析+组织内容（内部处理）
步骤5：输出会话范围+判断结果 + 等待确认（一次）
步骤6：直接写入 + 简短告知（完成）
Intelligent Range Recognition:
  • ✅ Automatically identify relevant conversation segments and avoid extracting irrelevant content
  • ✅ Clearly inform the extracted session range during the confirmation phase
  • ❌ Do not extract the entire conversation history
One-Time Confirmation Principle:
  • ✅ Confirm only once in step 5
  • ❌ Prohibited to confirm again in step 6
No Preview Principle:
  • ✅ Only display the session range, judgment result, and brief reason
  • ❌ Prohibited to display the complete preview of the content to be appended
  • Reason: Long preview content interferes with reading, and users trust the judgment logic
Efficient Execution:
Step 1: Intelligent session range recognition (internal processing)
Step 2-4: Read + analyze + organize content (internal processing)
Step 5: Output session range + judgment result + wait for confirmation (once)
Step 6: Directly write + brief notification (completed)

C+I 结构概述

C+I Structure Overview

采用 C+I 结构 解决"精简后看不懂"与"不精简太啰嗦"的矛盾：
  • C (Context) - 原文现场：当时的完整对话，包含代码、报错、参数
  • I (Insight) - 干货结论：一句话通用原理，不带具体案例
完整说明与模板见：
references/ci_structure.md
Adopting the C+I structure resolves the conflict between "unintelligible after simplification" and "too verbose without simplification":
  • C (Context) - Original Context: The complete conversation at that time, including code, error messages, and parameters
  • I (Insight) - Key Takeaway: A one-sentence universal principle without specific cases
For complete instructions and templates, see: 
references/ci_structure.md

与其他 skills 的协作

Collaboration with Other Skills

上游：
  • conversation-extractor
    ：生成基础笔记
  • process-doc-generator
    ：生成过程文档
下游：
  • 追加后的文档可以继续用 
    process-doc-generator
    扩展
Upstream:
  • conversation-extractor
    : Generates basic notes
  • process-doc-generator
    : Generates process documents
Downstream:
  • The appended document can be further expanded using 
    process-doc-generator

资源文件

Resource Files

  • C+I结构详解：references/ci_structure.md
  • 分类指南：references/classification_guide.md
  • C+I Structure Details: references/ci_structure.md
  • Classification Guide: references/classification_guide.md