analyze-frame
當接收到新需求或 Event Storming 產出後觸發。分析問題類別（CBF/IDF/RIF），生成完整的規格目錄結構。實現「需求與實作分離」、「規格即文檔、文檔即規格」。
npx skills add majiayu000/claude-skill-registry --skill analyze-frame-knowlet-pf-skills --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Analyze Frame Skill ## 觸發時機 - 接收到新需求描述時 - Event Storming 工作坊產出後 - 使用者要求分析問題框架時 ## 核心任務 將需求分析為 Problem Frames 的五種基本類別，並輸出結構化的規格目錄。 --- ## Problem Frame 類別定義 ### CBF (Commanded Behavior Frame) - 命令行為框架 - **特徵**：Operator 發出命令，Machine 控制 Controlled Domain 執行狀態變更 - **對應 Sub-agent**：`command-sub-agent` - **典型場景**：建立訂單、更新資料、執行交易 - **CQRS 角色**：Command Side ### IDF (Information Display Frame) - 資訊顯示框架 - **特徵**：使用者查詢資訊，系統回傳資料（無狀態變更） - **對應 Sub-agent**：`query-sub-agent` - **典型場景**：查詢報表、搜尋資料、讀取詳情 - **CQRS 角色**：Query Side ### RIF (Required Behavior Frame) - 反應式框架 - **特徵**：系統對事件做出反應，通常是非同步處理 - **對應 Sub-agent**：`reactor-sub-agent` - **典型場景**：事件監聽、訊息處理、系統整合 ### WPF (Workpieces Frame) - 工作件框架 - **特徵**：對工作產物（文件、報告）進行編輯與管理 - **典型場景**：文件編輯、報表生成 ### TF (Transformation Frame) - 轉換框架 - **特徵**：輸入資料經過轉換產生輸出 - **典型場景**：資料轉換、格式轉換、ETL --- ## 輸出：規格目錄結構 在 `docs/specs/{feature-name}/` 目錄下生成完整規格： ``` docs/specs/{feature-name}/ ├── frame.yaml # 問題框架定義 (核心) ├── acceptance.yaml # 驗收測試規格 (在根目錄) │ ├── requirements/ # 需求層 (What) - 純業務語言 │ └── cbf-req-1-{feature}.yaml │ ├── machine/ # 機器層 (How) - Application 層 │ ├── machine.yaml # Machine 定義 │ ├── controller.yaml # API 入口規格 │ └── use-case.yaml # Use Case 規格 │ ├── cont
- 觸發時機
- 核心任務
- Problem Frame 類別定義
- CBF (Commanded Behavior Frame) - 命令行為框架
- IDF (Information Display Frame) - 資訊顯示框架
- RIF (Required Behavior Frame) - 反應式框架
- WPF (Workpieces Frame) - 工作件框架
- TF (Transformation Frame) - 轉換框架
- 輸出：規格目錄結構
- 命名規範
- frame.yaml 規格格式
- requirements/req-{n}-{feature}.yaml 格式
- machine/use-case.yaml 格式
- controlled-domain/aggregate.yaml 格式
python ~/.claude/skills/analyze-frame/scripts/validate_spec.py docs/specs/create-workflow/
python ~/.claude/skills/analyze-frame/scripts/validate_spec.py docs/specs/create-workflow/ docs/specs/query-dashboard/
python ~/.claude/skills/analyze-frame/scripts/validate_spec.py docs/specs/*/ || exit 1
mkdir -p docs/specs/{feature-name}/{requirements,machine,controlled-domain,cross-context,acceptance,runbook}
cp ~/.claude/skills/analyze-frame/templates/frame.yaml docs/specs/{feature-name}/What does the analyze-frame skill do?
當接收到新需求或 Event Storming 產出後觸發。分析問題類別（CBF/IDF/RIF），生成完整的規格目錄結構。實現「需求與實作分離」、「規格即文檔、文檔即規格」。
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill analyze-frame-knowlet-pf-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.