team-update

jezweb ｜ 寫作與文件 ｜ 原文 ｜ MIT

把進度貼到團隊聊天室、分類回饋並規劃下一步，靠 playbook 記住設定

---
name: team-update
description: "把專案進度更新貼到團隊聊天室、收集回饋、分類處理回應，並規劃下一步。會依可用的工具（聊天、git、issue、任務）調整做法。第一次執行會探索工具並存下 playbook，之後直接照 playbook 執行。觸發詞：'team update'、'post update'、'sync with team'、'standup'、'check team chat'、'feedback loop'、'project update'、'what did the team say'。"
compatibility: claude-code-only
allowed-tools: "*"
---

# Team Update

把專案進度更新貼到團隊聊天室，讀取並分類回饋，再規劃下一步。會配合手邊有的溝通和專案工具來調整。

## Playbook 模式

這個 skill 在專案根目錄用一個 **playbook** 檔案：`.claude/team-update-playbook.md`。

- **第一次執行**：探索可用工具、詢問使用者偏好、執行、存下 playbook
- **之後的執行**：讀 playbook，跳過探索，直接執行
- **使用者編輯 playbook**：改動立刻生效（頻道、風格、分類規則）

Playbook 是使用者可以自己編輯的純 markdown。裡面記錄工具設定、頻道偏好、訊息風格、分類規則，以及上次執行的 metadata。

---

## Phase 0：檢查 Playbook

檢查專案根目錄有沒有 `.claude/team-update-playbook.md`。

**如果存在**：讀它。所有工具設定、頻道資訊、訊息風格和分類規則都在裡面。帶著已知的設定直接跳到 Phase 1。

**如果不存在**：先執行 Phase 0b（探索）。

---

## Phase 0b：探索（只在第一次執行）

檢查有哪些 MCP 工具已連線、本機有哪些工具，偵測可用的能力。

讀 [references/discovery-patterns.md](references/discovery-patterns.md) 看偵測模式。

### 能力偵測

逐一檢查每個能力類別：

| 能力 | 怎麼偵測 | 缺少時的替代方案 |
|---|---|---|
| **Chat** | 名稱符合 `chat`、`slack`、`discord`、`teams` 的 MCP 工具 | 輸出排好版的文字，讓使用者手動貼 |
| **Git** | `git rev-parse --is-inside-work-tree` | 跳過 commit 摘要 |
| **Issues** | 名稱符合 `github`、`linear`、`jira` 的 MCP 工具 | 跳過，或輸出文字清單 |
| **Tasks** | 名稱符合 `tasks`、`todos`、`asana` 的 MCP 工具 | 跳過，或輸出文字清單 |
| **Knowledge** | Basalt Cortex（`~/Documents/basalt-cortex/`） | 搜尋相關的知識筆記 |

### 使用者偏好（詢問）

探索完之後，請使用者確認：

1. **頻道**：要把更新貼到哪個聊天空間/頻道？（列出探索到的選項）
2. **身分**：用自己的身分貼，還是用 bot 身分？（例如 Anthro Morphic）
3. **Repo 範圍**：要追蹤哪些 repo？（預設：目前這個 repo）
4. **訊息風格**：簡短的 standup、詳細的 changelog，還是對話式更新？
5. **團隊背景**：有需要特別留意的成員嗎？（姓名、角色）
6. **分類規則**：處理回饋有沒有自訂規則？（或用預設的）

### 儲存 Playbook

探索加上使用者偏好都有了之後，把 playbook 存到 `.claude/team-update-playbook.md`。

讀 [references/playbook-format.md](references/playbook-format.md) 看完整模板。所有區塊都用探索到的工具和使用者偏好填好。如果某個能力沒找到，就在 playbook 裡標成 "Not available"。

確認 `.claude/` 在 `.gitignore` 裡（playbook 含有空間 ID 和偏好設定，不該被 commit）。

---

## Phase 1：收集背景資訊

從所有可用的來源蒐集資訊。用 playbook 的 "Data Sources" 區塊來知道要呼叫哪些工具。

### 1a. 決定時間範圍

查看 playbook 的 "Last Run" 區塊，找出上次更新的時間戳記。如果之前沒跑過，問使用者要回溯多久（預設：24 小時）。

### 1b. 收集資料

從每個可用的來源蒐集：

| 來源 | 要收集什麼 | 工具 |
|---|---|---|
| **Git commits** | `git log --oneline --since=<last-update>` | Bash |
| **聊天訊息** | 自上次更新以來，設定的頻道裡的訊息 | playbook 裡的 Chat MCP 工具 |
| **未結的 issue/PR** | 最近更新或新建立的項目 | playbook 裡的 issue tracker |
| **進行中的任務** | 進行中或最近完成的任務 | playbook 裡的任務追蹤工具 |

### 1c. 整理成起草用的摘要

把 commit 依主題分組（不要列個別的 hash）。記下關閉的 issue、合併的 PR 或完成的任務。標出需要回覆的團隊訊息。

---

## Phase 2：起草並發布更新

### 2a. 撰寫訊息

讀 [references/message-composition.md](references/message-composition.md) 看訊息模式。

照 playbook 的 "Message Style" 區塊。一般原則：

- 先講出貨了什麼或改了什麼，不要先講過程
- 把相關的 commit 歸成主題
- 只在相關時才提到特定的人
- 保持好掃讀（短段落、條列）
- **像隊友一樣寫，不要像 AI**：不要狂用 emoji，不要含糊其辭，不要過度解釋團隊早就知道的背景。看 [references/message-composition.md](references/message-composition.md) 的 Communication Style 區塊。

### 2b. 預覽與核准

把草稿給使用者看。包含：
- 寫好的訊息
- 會貼到哪個頻道
- 是新訊息還是在 thread 裡回覆

**必須經過核准**：沒有使用者明確同意，絕對不要貼到外部頻道。

### 2c. 發布

用 playbook 裡的聊天工具貼出已核准的訊息。如果沒有可用的聊天工具，就輸出排好版的訊息，讓使用者手動貼。

### 2d. 更新 Playbook

貼完之後，更新 playbook 的 "Last Run" 區塊：
- 目前的時間戳記
- Thread key（如果適用）
- 這次貼了什麼的簡短摘要

---

## Phase 3：讀取並分類回饋

### 3a. 讀取回應

讀取設定的頻道裡，更新貼出之後的訊息。找：
- 對這則更新的直接回覆
- 頻道裡提到這個專案的新訊息
- 表情反應或確認回應

### 3b. 分類回饋

讀 [references/feedback-triage.md](references/feedback-triage.md) 看分類模式。

用 playbook 的 "Triage Rules" 區塊。預設分類：

| 類型 | 動作 |
|---|---|
| Bug 回報 | 建立 issue（label: bug） |
| 功能請求 | 建立 issue（label: enhancement） |
| 問題 | 起草回覆，等使用者核准 |
| Blocker | 立刻標出來，建議解法 |
| 確認回應 | 記下，不需要動作 |
| 離題 | 忽略 |

### 3c. 呈現並執行

呈現回饋摘要和建議的動作：

```
## Feedback Summary

- Daniel: "Can we add dark mode?" -> Create issue (enhancement)
- Rabin: "Auth is broken on staging" -> Create issue (bug, priority)
- Karen: "Looks good!" -> No action

Proceed with these actions?
```

**必須經過核准**：沒有使用者明確同意，絕對不要建立 issue、貼回覆或採取任何外部動作。

---

## Phase 4：規劃下一步

### 4a. 排優先順序

從所有收集到的背景資訊（commit、issue、任務、回饋），找出：
1. **Blockers**：阻擋進度的事
2. **高優先**：Bug、緊急請求、截止日
3. **接下來**：已規劃的工作、功能請求
4. **Backlog**：有最好、低優先的項目

### 4b. 呈現（不要貼出去）

把排好優先順序的清單給使用者看。這只供使用者自己規劃，**不要**貼到任何頻道。

```
## Suggested Priorities

1. [BLOCKER] Fix auth on staging (from Rabin's feedback)
2. [HIGH] Complete API endpoint for user profiles (current sprint)
3. [NEXT] Dark mode support (from Daniel's request)
4. [BACKLOG] Refactor database queries
```

---

## 自主權規則

| 動作 | 層級 |
|---|---|
| 讀取/建立 playbook | 直接做 |
| 探索工具（第一次執行） | 直接做，跟使用者確認偏好 |
| 收集背景資訊（git、聊天、issue） | 直接做 |
| 起草更新訊息 | 直接做，並顯示預覽 |
| **貼到外部頻道** | **需要核准** |
| **建立 issue/任務** | **需要核准** |
| **貼回覆給團隊** | **需要核准** |
| 更新 playbook 的 "Last Run" | 直接做 |
| 呈現計畫/優先順序 | 直接做 |

---

## 優雅降級

不管有多少工具可用，這個 skill 都能運作：

| 可用工具 | 體驗 |
|---|---|
| 只有 Git | 摘要 commit，輸出文字讓使用者手動貼 |
| Git + Chat | 完整的貼出/讀取循環，手動建立 issue |
| Git + Chat + Issues | 完整循環，自動建立 issue |
| Git + Chat + Issues + Tasks + Knowledge | 完整循環，附持續追蹤 |

---

## 運作模式

這個 skill 會依不同的觸發詞做出不同反應：

| 觸發詞 | 行為 |
|---|---|
| "team update" / "post update" | 完整循環：收集、起草、發布、讀取回饋 |
| "check team chat" / "what did the team say" | 只做 Phase 3：讀取並分類回饋 |
| "standup" / "sync with team" | Phase 1 + 2：收集並發布，跳過回饋 |
| "project update" | Phase 1 + 2 + 4：收集、發布、規劃（跳過回饋分類） |
| "feedback loop" | Phase 3 + 4：讀取回饋並規劃 |

---

## 參考檔案

| 時機 | 讀這個 |
|------|------|
| 第一次執行：儲存 playbook | [references/playbook-format.md](references/playbook-format.md) |
| 第一次執行：偵測工具 | [references/discovery-patterns.md](references/discovery-patterns.md) |
| 撰寫更新訊息 | [references/message-composition.md](references/message-composition.md) |
| 分類團隊回饋 | [references/feedback-triage.md](references/feedback-triage.md) |

---
name: team-update
description: "Post project updates to team chat, gather feedback, triage responses, and plan next steps. Adapts to available tools (chat, git, issues, tasks). First run discovers tools and saves a playbook; subsequent runs execute from the playbook. Trigger with 'team update', 'post update', 'sync with team', 'standup', 'check team chat', 'feedback loop', 'project update', 'what did the team say'."
compatibility: claude-code-only
allowed-tools: "*"
---

# Team Update

Post project updates to team chat, read and triage feedback, and plan next steps. Adapts to whatever communication and project tools are available.

## The Playbook Pattern

This skill uses a **playbook** file at `.claude/team-update-playbook.md` in the project root.

- **First run**: Discover available tools, ask the user for preferences, execute, save a playbook
- **Subsequent runs**: Read the playbook, skip discovery, execute directly
- **User edits playbook**: Changes take effect immediately (channel, style, triage rules)

The playbook is plain markdown the user can edit. It captures tool configuration, channel preferences, message style, triage rules, and last-run metadata.

---

## Phase 0: Playbook Check

Check if `.claude/team-update-playbook.md` exists in the project root.

**If it exists**: Read it. All tool configuration, channel info, message style, and triage rules are in there. Jump to Phase 1 with known config.

**If it does not exist**: Run Phase 0b (Discovery) first.

---

## Phase 0b: Discovery (First Run Only)

Detect available capabilities by checking what MCP tools are connected and what local tools exist.

Read [references/discovery-patterns.md](references/discovery-patterns.md) for detection patterns.

### Capability Detection

Check for each capability category:

| Capability | How to detect | Fallback if missing |
|---|---|---|
| **Chat** | MCP tools matching `chat`, `slack`, `discord`, `teams` | Output formatted text for manual posting |
| **Git** | `git rev-parse --is-inside-work-tree` | Skip commit summaries |
| **Issues** | MCP tools matching `github`, `linear`, `jira` | Skip or output text list |
| **Tasks** | MCP tools matching `tasks`, `todos`, `asana` | Skip or output text list |
| **Knowledge** | Basalt Cortex (`~/Documents/basalt-cortex/`) | Search for related knowledge notes |

### User Preferences (Ask)

After discovery, ask the user to confirm:

1. **Channel**: Which chat space/channel to post updates to? (List discovered options)
2. **Identity**: Post as yourself or a bot identity? (e.g. Anthro Morphic)
3. **Repo scope**: Which repo(s) to track? (Default: current repo)
4. **Message style**: Brief standup, detailed changelog, or conversational update?
5. **Team context**: Any team members to be aware of? (Names, roles)
6. **Triage rules**: Any custom rules for handling feedback? (Or use defaults)

### Save Playbook

After discovery + user preferences, save the playbook to `.claude/team-update-playbook.md`.

Read [references/playbook-format.md](references/playbook-format.md) for the full template. Fill in all sections with discovered tools and user preferences. If a capability was not found, note it as "Not available" in the playbook.

Ensure `.claude/` is in `.gitignore` (the playbook contains space IDs and preferences that shouldn't be committed).

---

## Phase 1: Gather Context

Collect information from all available sources. Use the playbook's "Data Sources" section to know which tools to call.

### 1a. Determine Time Window

Check the playbook's "Last Run" section for the last update timestamp. If no previous run, ask the user how far back to go (default: 24 hours).

### 1b. Collect Data

Gather from each available source:

| Source | What to collect | Tool |
|---|---|---|
| **Git commits** | `git log --oneline --since=<last-update>` | Bash |
| **Chat messages** | Messages in the configured channel since last update | Chat MCP tool from playbook |
| **Open issues/PRs** | Recently updated or newly created items | Issue tracker from playbook |
| **Active tasks** | In-progress or recently completed tasks | Task tracker from playbook |

### 1c. Summarise for Drafting

Group commits by theme (not individual hashes). Note any issues closed, PRs merged, or tasks completed. Flag any team messages that need response.

---

## Phase 2: Draft and Post Update

### 2a. Compose Message

Read [references/message-composition.md](references/message-composition.md) for message patterns.

Follow the playbook's "Message Style" section. General principles:

- Lead with what shipped or changed, not process
- Group related commits into themes
- Mention specific people only when relevant
- Keep it scannable (short paragraphs, bullet points)
- **Write like a teammate, not an AI** — no emoji spam, no hedging, no over-explaining context the team already has. See the Communication Style section in [references/message-composition.md](references/message-composition.md).

### 2b. Preview and Approval

Show the draft to the user. Include:
- The composed message
- Which channel it will be posted to
- Whether it's a new message or thread reply

**APPROVAL REQUIRED**: Never post to external channels without explicit user approval.

### 2c. Post

Post the approved message using the chat tool from the playbook. If no chat tool is available, output the formatted message for the user to post manually.

### 2d. Update Playbook

After posting, update the "Last Run" section of the playbook with:
- Current timestamp
- Thread key (if applicable)
- Brief summary of what was posted

---

## Phase 3: Read and Triage Feedback

### 3a. Read Responses

Read messages from the configured channel since the update was posted. Look for:
- Direct replies to the update
- New messages in the channel that reference the project
- Reactions or acknowledgements

### 3b. Classify Feedback

Read [references/feedback-triage.md](references/feedback-triage.md) for classification patterns.

Use the playbook's "Triage Rules" section. Default classification:

| Type | Action |
|---|---|
| Bug report | Create issue (label: bug) |
| Feature request | Create issue (label: enhancement) |
| Question | Draft reply for user approval |
| Blocker | Flag immediately, suggest resolution |
| Acknowledgement | Note, no action needed |
| Off-topic | Ignore |

### 3c. Present and Act

Present a summary of feedback with proposed actions:

```
## Feedback Summary

- Daniel: "Can we add dark mode?" -> Create issue (enhancement)
- Rabin: "Auth is broken on staging" -> Create issue (bug, priority)
- Karen: "Looks good!" -> No action

Proceed with these actions?
```

**APPROVAL REQUIRED**: Never create issues, post replies, or take external actions without explicit user approval.

---

## Phase 4: Plan Next Steps

### 4a. Prioritise

From all gathered context (commits, issues, tasks, feedback), identify:
1. **Blockers**: Things preventing progress
2. **High-priority**: Bugs, urgent requests, deadlines
3. **Next up**: Planned work, feature requests
4. **Backlog**: Nice-to-haves, low-priority items

### 4b. Present (Not Posted)

Show the prioritised list to the user. This is for the user's planning only -- do NOT post it to any channel.

```
## Suggested Priorities

1. [BLOCKER] Fix auth on staging (from Rabin's feedback)
2. [HIGH] Complete API endpoint for user profiles (current sprint)
3. [NEXT] Dark mode support (from Daniel's request)
4. [BACKLOG] Refactor database queries
```

---

## Autonomy Rules

| Action | Level |
|---|---|
| Read/create playbook | Just do it |
| Discover tools (first run) | Just do it, confirm preferences with user |
| Gather context (git, chat, issues) | Just do it |
| Draft update message | Just do it, show preview |
| **Post to external channel** | **Approval required** |
| **Create issues/tasks** | **Approval required** |
| **Post replies to team** | **Approval required** |
| Update playbook "Last Run" | Just do it |
| Present plan/priorities | Just do it |

---

## Graceful Degradation

The skill works at any level of tool availability:

| Available tools | Experience |
|---|---|
| Git only | Summarise commits, output text for manual posting |
| Git + Chat | Full post/read cycle, manual issue creation |
| Git + Chat + Issues | Full cycle with automated issue creation |
| Git + Chat + Issues + Tasks + Knowledge | Full cycle with persistent tracking |

---

## Operating Modes

The skill responds to different trigger phrases:

| Trigger | Behaviour |
|---|---|
| "team update" / "post update" | Full cycle: gather, draft, post, read feedback |
| "check team chat" / "what did the team say" | Phase 3 only: read and triage feedback |
| "standup" / "sync with team" | Phase 1 + 2: gather and post, skip feedback |
| "project update" | Phase 1 + 2 + 4: gather, post, plan (skip feedback triage) |
| "feedback loop" | Phase 3 + 4: read feedback and plan |

---

## Reference Files

| When | Read |
|------|------|
| First run — saving playbook | [references/playbook-format.md](references/playbook-format.md) |
| First run — detecting tools | [references/discovery-patterns.md](references/discovery-patterns.md) |
| Composing update messages | [references/message-composition.md](references/message-composition.md) |
| Classifying team feedback | [references/feedback-triage.md](references/feedback-triage.md) |