Industry Evidence Map｜產業證據地圖
See who does what, with the evidence attached
公司角色與合作關係，逐項附上依據
For researchers organizing an industry: turn structured company and relationship records into a Markdown role map, source table and evidence-gap list. This is a table-based research map, not an interactive graph or current market database.
協助研究者整理產業：將結構化公司與關係資料輸出為 Markdown 角色地圖、來源表與證據缺口。成果是表格式研究地圖，不是互動網路圖或即時市場資料庫。
Watch the walkthrough / 觀看操作影片
Actual example — synthetic data
實際範例 — 合成資料
DemoCo supplies test sensors to ExampleWorks. The included demo maps Components → Assembly, links the relationship to source S1, and states that supply scale is unknown. The builder rejects relationships with unknown company IDs.
範例中 DemoCo 供應測試感測器給 ExampleWorks。實際輸出整理「零組件 → 組裝」角色，以 S1 對應供應關係，並清楚標示供應規模未知。不存在的公司編號會被拒絕。
| Input | Output |
|---|---|
| Entities, stages, roles, relationships and quoted sources | Role table + relationship table + source table + open questions |
| 公司、產業階段、角色、關係與來源摘錄 | 角色表＋關係表＋來源表＋證據缺口 |
Three steps
三步開始
- Unzip and open a terminal in the SKILL.md folder. Prepare JSON using references/input.md and examples/demo.json.
解壓後在 SKILL.md 資料夾開啟終端機，依 references/input.md 與 examples/demo.json 準備 JSON。 - Run the demo, then replace the input path with your own file.
先執行範例，再替換成自己的資料路徑。
python3 scripts/build.py --input examples/demo.json
- Read the Markdown tables printed in the terminal, or redirect to a new file. Your AI client can assist extracting records from authorized research using SKILL.md.
終端機直接顯示 Markdown 表格，也可另存新檔。可由自己的 AI 客戶端依 SKILL.md 將授權研究整理成輸入資料。
The script organizes supplied records; it does not independently discover company relationships or rate investments. Evidence labels and claim support need substantive review; a shared industry alone does not prove a supplier/customer link.
程式整理買家提供的紀錄，不會自行發現公司關係或評等投資。證據分類與主張支持程度需核對原文；同屬一個產業不代表存在供應關係。
Requirements and limits
環境與限制
Python 3.10+ recommended. Command-line tool, no GUI; standard library only and no model API calls. Tested on macOS; clean Windows/Linux installation is unverified. On Windows, replace python3 with py -3. Input schema and limits are in references/input.md.
建議 Python 3.10 以上，需要終端機操作，沒有圖形介面；只使用標準函式庫，不呼叫模型 API。已於 macOS 實測，Windows／Linux 全新安裝尚未驗證。Windows 可用 py -3 取代 python3；資料格式與限制見 references/input.md。
Invalid references and nonmatching quotations are rejected. Reference consistency does not establish source truth, completeness or whether a claim is supported in meaning. No automatic web search or news feed is included. Any AI-assisted preparation uses your own AI client and quota; integration varies by client.
錯誤来源編號或不吻合引文會被拒絕。引用吻合不代表來源真實、完整，也不保證主張的語意獲得支持。不含自動網路搜尋或新聞串流；AI 輔助整理使用買家自己的客戶端與額度，各客戶端整合方式不同。
Price and delivery
費用與交付
US$9 one-time purchase: version 0.1.0 Beta, Skill instructions, readable Python source and synthetic examples. No subscription, hosted service, model credits or manual research service. You provide the computer and pay for optional AI/data services.
US$9 一次買斷：交付 0.1.0 Beta、技能指引、可讀 Python 原碼與合成範例。不含訂閱、託管服務、模型額度或人工研究。買家自備電腦並負擔選用 AI／資料服務費用。
Support: [email protected] — installation questions, suggestions and reproducible bugs; no fixed response time or custom integration. Send synthetic examples and redacted errors, never keys or private documents.
聯絡信箱：[email protected]，受理安裝問題、修改建議與可重現錯誤；不承諾固定回覆時間或客製整合。請提供合成範例與去識別錯誤，不要寄送金鑰或私密文件。
