brand-discovery

affaan-m ｜ 寫作與文件 ｜ 原文 ｜ MIT

跨多場次做結構化品牌訪談，最後產出主品牌手冊

---
name: brand-discovery
description: 跨 8 個模組（目的、定位、受眾、個性、語調、敘事、創辦人張力）進行結構化、可中斷續跑的多場次品牌識別訪談，運用階梯式追問、5 Whys 和投射技巧，把答案存到磁碟，最後產出主品牌手冊（90_SYNTHESIS.md）。適用於建立或重新定位品牌、向設計師或寫手交辦需求，或把創辦人腦中的隱性知識講清楚。
---

# Brand Discovery

用這個 skill 進行一場結構化、會隨答案調整的品牌識別訪談。
最終目標是一份完整的 `90_SYNTHESIS.md`，也就是一本主品牌手冊，
組織可以拿它去向設計師、寫手和外部合作夥伴交辦工作。

訪談會跨好幾個場次進行。邊問邊把答案存到磁碟，
這樣對話結束時問出來的東西不會流失，
之後的場次也能從上次停下來的地方接著做。

## When to Activate

- 正在建立品牌、重新定位品牌，或需要一份書面的品牌識別參考文件來向合作夥伴交辦。
- 預期會有多個場次，對話會橫跨好幾天或好幾週。
- 有多位創辦人或利害關係人，需要先各自訪談，再做整合。
- 使用者想要的是結構化、可重複的方法，而不是隨興聊天。
- 現有的品牌文件零散、隱性，或要靠創辦人本人才講得清楚，需要把它們明確寫下來。

## Session start protocol

每次啟動時，在問任何訪談問題**之前**，先做這幾步：

1. **檢查先前的進度。** 在專案的 brand-identity 目錄裡找現有的模組檔案
   和 `state.json` checkpoint。
   如果都沒有，就是全新開始：先確認品牌名稱、
   參與者，以及 brand-identity 檔案要存在哪裡，然後從第一個模組開始。
2. **讀目前進行中的模組檔**（如果有的話），掃過它的 Raw
   區塊，看之前記下哪些答案。
3. **向使用者回報**，用兩三句話講：目前在哪個模組、
   狀態如何、還剩什麼。然後問：「要從這裡繼續，還是換模組？」

## Interview discipline

每個模組都要遵守這些規則：

1. **一次只問一個問題。** 絕對不要丟出一整串問題。
2. **每次回答之後：** 簡短複述 → 再做一個深入追問，或者
   如果這個主題已經飽和就收掉這條線。不准默默跳到下一題。
3. **階梯式追問（Laddering）：** 對每個「是什麼」的回答，接著問
   「這對你為什麼重要？」，一直問到核心價值浮現（通常兩到四輪）。
4. **5 Whys：** 針對信念或定位主張，一路追到根本原因，
   不要停在表面的宣告。
5. **察覺薄弱的回答：** 如果答案很籠統、滿是行話或很模糊，就請對方舉
   一個具體例子、一個客戶故事，或一個數字。
6. **投射技巧**（每個模組用一次，用來突破停滯期）：
   - 「如果這個品牌是一個人，他會怎麼走進一個房間？」
   - 品牌訃聞：「如果這個組織五年後關門了，客戶會懷念什麼？
     你會後悔沒說出口的又是什麼？」
   - 競爭對照：「說一個你欣賞、但絕對不想變成的同業。
     他具體哪裡是錯誤的範本？」
7. **飽和訊號：** 連續兩次追問都沒有帶出新資訊時，就做摘要
   並結束這個模組。
8. **模組結尾：** 寫一份結構化的模組檔，分成兩個區塊：
   - `## Raw`：逐字引述和例子。
   - `## Synthesis`：你的詮釋、三個候選表述、
     未解的問題、參與者之間的矛盾。
   然後更新 `state.json` checkpoint（見下面的 State protocol）。

## Module sequence

| File | Label | Frameworks used |
|------|-------|-----------------|
| `10_purpose-why.md` | Purpose / Why | Sinek Golden Circle, Lencioni |
| `20_positioning.md` | Positioning | Dunford "Obviously Awesome", Moore template |
| `30_audience-niche.md` | Audience & Niche | Baker "Business of Expertise", ICP |
| `40_personality-archetype.md` | Personality & Archetype | Mark & Pearson 12 archetypes, J. Aaker 5 dims |
| `50_voice-tone.md` | Voice & Tone | Brand voice guidelines |
| `60_narrative-story.md` | Narrative / Story | Neumeier trueline, brand story arc |
| `70_founder-tension.md` | Founder Brands vs Studio Brand | Enns "Win Without Pitching" |
| `90_SYNTHESIS.md` | Master Brandbook | Kapferer prism, Aaker brand system |

模組照順序做。使用者要求跳模組就照辦，
並在 `state.json` 裡記下跳過了哪個。

## State write protocol

每個模組達到飽和或完成狀態後，寫兩個檔案：

**模組檔**放在 `modules/{moduleFile}`，內容是完整的 Raw 和 Synthesis。

**`state.json`** 是輕量的 checkpoint，讓之後的場次可以接著做。
更新 `completedModules`、`inProgressModule`、`nextModule`、`lastUpdated`。
Schema：

```json
{
  "session": "{brand_name}-brand-{YYYY-MM}",
  "outputPath": "{path_to_brand_identity_directory}",
  "completedModules": [],
  "inProgressModule": "10_purpose-why.md",
  "nextModule": "20_positioning.md",
  "participants": ["founder-A"],
  "lastUpdated": "{ISO-8601}"
}
```

寫完之後確認：「Module X saved. State updated. Next: Y.」

**最後一個模組（90_SYNTHESIS.md）：** 寫最終整合時，
在 `state.json` 把 `inProgressModule` 設成 `"90_SYNTHESIS.md"`，
`nextModule` 設成 `null`。寫完後，把 `"90_SYNTHESIS.md"` 加進 `completedModules`，
再把 `inProgressModule` 設成 `null`。如果留著不清掉，
之後續跑時會把已完成的品牌手冊當成還在進行中。
然後確認：「Brandbook complete. All modules saved.」

## Multi-founder mode

不只一位創辦人參與時，把每位創辦人的答案寫到
`founders/{participant}.md`，不要寫進主模組檔。寫入前先驗證
`participant` 名稱：只接受英數字和連字號
（例如 `founder-a`、`anna`）；拒絕含路徑分隔符號
（`/`、`\`、`..`）或特殊字元的名稱。`moduleFile` 要對照
列舉出來的模組順序驗證（只能是 10 到 90）。`outputPath` 要驗證
它是專案目錄內的絕對路徑，相對路徑和用 `..` 跳出去的路徑一律拒絕。
所有創辦人都完成某個模組後，跑一次整合：在模組檔裡摘要
共識與分歧，並標出「有建設性的張力」，留給團體對齊工作坊討論。

## Anti-Patterns

- **沒先讀 state 就開始。** 每個場次一開始都必須先檢查現有的模組檔和 `state.json`。跳過這步，前面場次累積的脈絡就全丟了。
- **一次問好幾個問題。** 一次一個問題沒有商量餘地，列清單只會得到打勾式的答案，問不出真正的洞見。
- **還沒飽和就進 Synthesis。** 如果最後兩次追問都沒帶出新資訊，這個模組就做完了；如果有，就還沒完。
- **跳過多創辦人整合。** 有多位利害關係人時，必須先完成各自的訪談再整合。一開始就集體討論品牌，會引入錨定偏誤。
- **把這當成一次就結束的場次。** 這個 skill 設計給多場次使用。在一場對話裡硬衝到 `90_SYNTHESIS.md`，產出會很淺。

## Related Skills

- `competitive-platform-analysis`：brand-discovery 把定位簡報確立之後，用這個 skill 來界定並分類競爭對手集合。
- `brand-voice`（ECC）：如果 brand-discovery 的語調模組需要另外一份從來源推導出來的寫作風格檔案。

---
name: brand-discovery
description: Run a structured, resumable multi-session brand identity interview across 8 modules (purpose, positioning, audience, personality, voice, narrative, founder tension) using laddering, 5 Whys, and projective techniques, persisting answers to disk and producing a master brandbook (90_SYNTHESIS.md). Use when creating or repositioning a brand, briefing designers or writers, or making implicit founder knowledge explicit.
---

# Brand Discovery

Use this skill to conduct a structured, adaptive brand identity interview.
The goal is a complete `90_SYNTHESIS.md` — a master brandbook the
organization can use to brief designers, writers, and external
collaborators.

The interview runs across multiple sessions. Capture answers to disk as you
go so that no elicited knowledge is lost when a conversation ends, and so a
later session can resume from where the last one stopped.

## When to Activate

- A brand is being created, repositioned, or needs a written identity reference to brief collaborators.
- Multiple sessions are expected — the conversation will span days or weeks.
- Multiple founders or stakeholders need individual interviews before a reconciliation pass.
- The user wants a structured, repeatable method rather than an ad-hoc chat.
- Existing brand documentation is scattered, implicit, or founder-dependent and needs to be made explicit.

## Session start protocol

On every activation, perform these steps **before** asking any interview
question:

1. **Check for prior progress.** Look for an existing set of module files
   and a `state.json` checkpoint in the project's brand-identity directory.
   If none exists, this is a fresh start — confirm the brand name,
   participants, and where to save the brand-identity files, then begin at
   the first module.
2. **Read the current module file** if one is in progress, and scan its Raw
   section for previously captured answers.
3. **Report to the user** in two or three sentences: which module we are
   in, its status, and what remains. Then ask: "Continue here, or switch
   module?"

## Interview discipline

Apply these rules throughout every module:

1. **One question at a time.** Never present a list of questions.
2. **After each answer:** short paraphrase → one deepening probe OR close
   the thread if the topic is saturated. Never move on silently.
3. **Laddering:** for every "what" answer, follow with "Why does that
   matter to you?" until a core value surfaces (typically two to four
   iterations).
4. **5 Whys:** for beliefs or positioning claims — push until the root
   reason, not the surface declaration, is on the table.
5. **Detect thin answers:** if generic, jargon-heavy, or vague, ask for
   one concrete example, a client story, or a number.
6. **Projective techniques** (use once per module to break a plateau):
   - "If the brand were a person, how would they walk into a room?"
   - Brand obituary: "If the organization closed in five years, what would
     customers miss? What would you regret not having said?"
   - Competitive contrast: "Name one peer you admire but would never want
     to become. What specifically makes them the wrong model?"
7. **Saturation signal:** when two consecutive probes produce no new
   information, summarise and close the module.
8. **End of module:** write a structured module file with two sections:
   - `## Raw` — verbatim quotes and examples.
   - `## Synthesis` — your interpretation, three candidate formulations,
     open questions, contradictions between participants.
   Then update the `state.json` checkpoint (see State protocol below).

## Module sequence

| File | Label | Frameworks used |
|------|-------|-----------------|
| `10_purpose-why.md` | Purpose / Why | Sinek Golden Circle, Lencioni |
| `20_positioning.md` | Positioning | Dunford "Obviously Awesome", Moore template |
| `30_audience-niche.md` | Audience & Niche | Baker "Business of Expertise", ICP |
| `40_personality-archetype.md` | Personality & Archetype | Mark & Pearson 12 archetypes, J. Aaker 5 dims |
| `50_voice-tone.md` | Voice & Tone | Brand voice guidelines |
| `60_narrative-story.md` | Narrative / Story | Neumeier trueline, brand story arc |
| `70_founder-tension.md` | Founder Brands vs Studio Brand | Enns "Win Without Pitching" |
| `90_SYNTHESIS.md` | Master Brandbook | Kapferer prism, Aaker brand system |

Complete modules in order. Honour a user request to jump modules and note
the skip in `state.json`.

## State write protocol

After each module reaches saturation or done status, write two files:

**Module file** at `modules/{moduleFile}` — full Raw and Synthesis content.

**`state.json`** — a lightweight checkpoint so a later session can resume.
Update `completedModules`, `inProgressModule`, `nextModule`, `lastUpdated`.
Schema:

```json
{
  "session": "{brand_name}-brand-{YYYY-MM}",
  "outputPath": "{path_to_brand_identity_directory}",
  "completedModules": [],
  "inProgressModule": "10_purpose-why.md",
  "nextModule": "20_positioning.md",
  "participants": ["founder-A"],
  "lastUpdated": "{ISO-8601}"
}
```

After writing, confirm: "Module X saved. State updated. Next: Y."

**Terminal module (90_SYNTHESIS.md):** when writing the final synthesis,
set `inProgressModule` to `"90_SYNTHESIS.md"` and `nextModule` to `null`
in `state.json`. After writing, set `completedModules` to include
`"90_SYNTHESIS.md"`, then set `inProgressModule` to `null` — leaving it
populated would cause a future resumption to treat the completed brandbook
as still in progress. Confirm: "Brandbook complete. All modules saved."

## Multi-founder mode

When more than one founder participates, write each founder's answers to
`founders/{participant}.md` instead of the main module files. Validate the
`participant` name before writing: accept only alphanumeric characters and
hyphens (e.g. `founder-a`, `anna`); reject names containing path separators
(`/`, `\`, `..`) or special characters. Validate `moduleFile` against the
enumerated module sequence (10 through 90 only). Validate `outputPath` to
ensure it is an absolute path within the project directory — reject relative
paths and paths that escape via `..` segments. After all founders complete a
module, run a reconciliation pass: summarise convergences and divergences in
the module file, flag "productive tensions" for the group alignment workshop.

## Anti-Patterns

- **Starting without reading state first.** Every session must open by checking for existing module files and `state.json`. Skipping this loses all continuity from prior sessions.
- **Asking multiple questions at once.** One question at a time is not optional — lists produce checklist answers, not real insight.
- **Moving to Synthesis before saturation.** If the last two probes produced no new information, the module is done. If they did — it isn't.
- **Skipping multi-founder reconciliation.** When multiple stakeholders are involved, individual interviews must complete before reconciliation. Discussing the brand collectively first introduces anchoring bias.
- **Treating this as a one-shot session.** This skill is designed for multiple sessions. Rushing to `90_SYNTHESIS.md` in one conversation produces shallow output.

## Related Skills

- `competitive-platform-analysis` — after brand-discovery establishes the positioning brief, use this to scope and categorise the competitor set.
- `brand-voice` (ECC) — if the brand-discovery voice-and-tone module needs a separate, source-derived writing-style profile.