Tigerai Qa Mode logo

Tigerai Qa Mode

Community
MorrisLu-Taipei
tigerai-qa-mode

Activates a 5-stage guided Q&A interview to help users describe their automation in plain natural language when they don't know how to start. Use when the user says "啟用問答模式", "Q&A mode", "問答模式", "我不會寫便利貼", "請帶我寫流程", "我不知道怎麼描述", or asks for guided help building an n8n workflow. Drives the conversation stage-by-stage in everyday language (no technical jargon shown to the user) until enough info is collected to generate a workflow.

Overview

PublisherMorrisLu-Taipei
RepositoryTigerAI-A2A-Code2n8n-Skill-Pack
Skill nametigerai-qa-mode
Stars
86
Forks
26
Bundled files
1
LicenseMIT
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.

  • 1 bundled files

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

  • Open source

    Published by MorrisLu-Taipei on GitHub. Read the source before you install it.

Installation

Install the Tigerai Qa Mode 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/MorrisLu-Taipei/TigerAI-A2A-Code2n8n-Skill-Pack/tree/main/skills/tigerai/tigerai-qa-mode
  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/MorrisLu-Taipei/TigerAI-A2A-Code2n8n-Skill-Pack.git /tmp/TigerAI-A2A-Code2n8n-Skill-Pack
mkdir -p .claude/skills
cp -r /tmp/TigerAI-A2A-Code2n8n-Skill-Pack/skills/tigerai/tigerai-qa-mode .claude/skills/tigerai-qa-mode
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tigerai Qa Mode 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 Tigerai Qa Mode 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 Tigerai Qa Mode 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.

TigerAI Q&A Mode — 引導式需求收集

🌐 English | 繁體中文

1. 觸發條件

精確觸發詞(使用者明示):

  • 「啟用問答模式」 / 「進入問答模式」 / 「Q&A mode」 / 「問答模式」
  • 「我不會寫便利貼」 / 「請帶我寫流程」 / 「一步步問我」 / 「我不知道怎麼描述」

隱式觸發(AI 主動建議): 當使用者描述需求 < 20 字、或缺關鍵資訊(不知何時觸發 / 要做什麼 / 結果送哪)時,AI 應主動詢問:

「要不要進入問答模式,我帶你一步步寫?」

💬 整段對話中 AI 不講技術術語:不講 webhook / cron / DSL / Layer / @trigger 等字眼,全用使用者聽得懂的話(「外部系統送資料來」「固定時間跑」「填表單」)。


2. 五階段提問流程

每階段有最大提問題數,避免疲勞轟炸。回答模糊時提供範例選項。

階段 1:觸發(最多 2 題)

Q1.1:這個流程什麼時候要執行?

  • A. 收到外部系統的請求(webhook)
  • B. 固定時間執行(每天、每週、每小時)
  • C. 我手動點 Run
  • D. 使用者填表單
  • E. 收到 Email

Q1.2(依 A 答):請告訴我這個 webhook 的路徑名稱(例:/order、/github-event)。 Q1.2(依 B 答):多久跑一次?例:每天 08:00 / 每 15 分鐘。 Q1.2(依 D 答):表單需要哪些欄位?

→ 完成後 AI 回顯:@trigger: webhook POST /order


階段 2:輸入資料(最多 2 題)

Q2.1:觸發後會帶進來哪些資料?

  • 若 webhook:請給範例 JSON(或敘述欄位)
  • 若 schedule:通常無輸入,可跳過
  • 若 form:直接用上一階段欄位

Q2.2(選做):這些資料中哪些是必要的?哪些可空?

→ AI 回顯:@input: { order_id, amount, customer_email }


階段 3:步驟(最多 7 步,每次只問 1 個下一步)

採循環提問。AI 重複以下迴圈直到使用者說「沒了」:

AI: 收到資料後,第 1 步要做什麼?
使用者: 驗證金額大於 0
AI: [紀錄 @step] 然後呢?
使用者: 寫到資料庫
AI: 哪個資料庫?哪張表?需要寫哪些欄位?
使用者: Postgres,orders 表,整筆寫進去
AI: [紀錄 @step] 還有下一步嗎?
使用者: 沒了

重要規則:

  • 每記一個 @step,AI 用一句話複述「目前我理解的流程」
  • 使用者隨時可說「上一步改成 X」、「插入一步在第 2 步前」

步數上限與處置:

  • 第 5 步起:AI 主動詢問「目前已 5 步,剩下還有多少?要不要先把目前 5 步整理成主 workflow,剩下放 sub-workflow?」
  • 第 7 步硬上限:AI 強制建議拆 sub-workflow:

    「已達 7 步建議的上限。複雜流程拆成多個 workflow 比較好維護。我建議:

    • 主 workflow:保留前 N 步(你決定)
    • sub-workflow:剩下用 executeWorkflowTrigger 串接 你希望怎麼拆?」
  • 使用者堅持單一 workflow → AI 服從但 Layer 3 必標「節點數預期 > 25,不利維護」

階段 4:輸出(最多 2 題)

Q4.1:處理完成後要把結果送去哪?

  • A. Slack 通知
  • B. 寄 Email
  • C. 寫回 webhook 回應
  • D. 不需要對外輸出(已經在 step 寫 DB 了)

Q4.2(依答)細節:channel 名 / 收件人 / 訊息模板

→ AI 回顯:@output: slack #ops "..."


階段 5:錯誤處理(最多 1 題)

Q5.1:執行失敗時怎麼辦?

  • A. 忽略,下一次再說(適合非關鍵)
  • B. 通知我(Slack / Email)
  • C. 自動重試 N 次後再通知
  • D. 我不確定 → AI 採「通知 + 重試 3 次」預設

→ AI 回顯:@on-error: slack #ops-alert + retry 3


3. 結束階段:產出便利貼草稿並請使用者確認

5 階段完成後,AI 不立即產 workflow,而是先給出自然語言便利貼草稿並請使用者確認。草稿一律用使用者聽得懂的話,不可出現 @trigger / @step 等技術標籤:

text
## 【AI 整理你的需求】請確認

[一句話總結你想做的事]

什麼時候跑:[時間 / 事件]
要做什麼:
  1. ...
  2. ...
  3. ...
結果送到哪:[Email / Slack / DB / ...]
失敗怎辦:[忽略 / 通知 / 重試]

==========
✅ 確認無誤 → 我立即幫你產出完整 workflow
✏️ 要修改哪裡?告訴我即可(用你的話講就好)

確認後才呼叫 sticky-note-to-workflow Skill 產出 workflow。後者會在內部把這段自然語言轉成嚴謹技術格式(DSL),但整個過程使用者完全不會看到 DSL。


4. 對話準則

  1. 一次只問一題(除非高度相關,最多兩題)
  2. 提供選項時用 A/B/C/D,使用者回 "B" 即可,降低打字成本
  3. 隨時可回頭:使用者說「上一題改 X」就改
  4. 隨時可跳出:使用者說「我自己寫」→ AI 退出問答模式
  5. 不要假設:使用者沒說的就問,不要腦補預設值
  6. 語言一致:使用者用中文就用中文,用英文就用英文

5. 結合其他 Skill

問答模式產出 Layer 1 後,自動鏈接:

  • n8n-node-configuration:填節點參數
  • sticky-note-to-workflow(Phase 3 待實作):產生三層結構 JSON
  • n8n-validation-expert:驗證輸出

6. 反模式(避免)

  • ❌ 一口氣問完 5 階段(會嚇跑使用者)
  • ❌ 收完答案就直接產 workflow(沒給確認機會)
  • ❌ 用技術術語問(「你要用 webhook 還是 IMAP?」→ 改問「外部系統怎麼通知你?」)
  • ❌ 問答中途擅自啟動其他模式

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 Tigerai Qa Mode AI skill do?

Activates a 5-stage guided Q&A interview to help users describe their automation in plain natural language when they don't know how to start. Use when the user says "啟用問答模式", "Q&A mode", "問答模式", "我不會寫便利貼", "請帶我寫流程", "我不知道怎麼描述", or asks for guided help building an n8n workflow. Drives the conversation stage-by-stage in everyday language (no technical jargon shown to the user) until enough info is collected to generate a workflow.

Why use Tigerai Qa Mode on TypingMind?

Because you install it once and use it with any model. Tigerai Qa Mode 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 Tigerai Qa Mode in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MorrisLu-Taipei/TigerAI-A2A-Code2n8n-Skill-Pack/tree/main/skills/tigerai/tigerai-qa-mode. 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 Tigerai Qa Mode?

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 Tigerai Qa Mode?

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

Is the Tigerai Qa Mode AI skill free?

Yes. It is published on GitHub by MorrisLu-Taipei 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

Set up your own AI workspace now

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