meta-thinking-framework SKILL.md skillA
meta-thinking-framework from labs21-dev/agents-stack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add labs21-dev/agents-stack/meta-thinking-framework@git:20260912.9d47cf0Pins git:20260912.9d47cf0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- labs21-dev/agents-stack
- Path
meta-thinking-framework/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260912.9d47cf0, committed Sep 12, 2026
- Size
- 8,165 bytes
- Repository stars
- 27
- License
- none declared
當使用者面對複雜、模糊、需要深度拆解的問題時使用——包含產品定義、市場痛點分析、用戶行為/付費問題、商業決策、系統或 agent 架構設計，特別是失敗成本高或不可逆的「還沒想清楚就要做決定」場景。透過六個標準鏡頭（頂層思維、本質、底層邏輯、逆向思考、經濟學、心理學）+ 變數驅動的額外鏡頭系統化拆解問題，並輸出可執行的決策草案。不適用於單純的事實查詢、目標明確的執行任務（寫一段 code、翻譯、查資料），或可輕易回滚的低風險決策。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Meta-Thinking Framework（六鏡元思考框架） ## 何時觸發這個 skill 使用者的請求符合以下任一特徵時啟動： - 問題本身模糊、多變數、沒有標準答案（"為什麼用戶不付費"、"怎麼找市場痛點"） - 需要做一次重要決策而非執行既定任務 - 使用者明確要求"深度分析"、"本質"、"底層邏輯"、"框架"等字眼 - 系統/產品/agent 架構設計，且失敗成本高 **不要用在**：查天氣、寫一段 code、翻譯文本這類目標明確、無需拆解假設的任務。 ## 核心心法 > 不要直接跳到答案。先分層拆解，再往下收斂成決策。 > 六個標準鏡頭是「已驗證過的一致性骨架」，但不是上限。若步驟 2 抽出的關鍵變數中有任一個是六鏡的機制都解釋不了的，允許引入額外鏡頭——數量不預設，但每個額外鏡頭必須通過「反事實對比法」證明其必要性（見下）。 > 不預設使用者已經想清楚，也不順著使用者的預設立場走——在抓到樞紐不確定性、並由使用者填掉它之前，不下最終判斷（抗諂媚，操作化見步驟 6b）。雙向鋼人論證是此心法的執行形：先把正反兩邊各自推到最強，再讓真正的衝突顯露出來，而不是對著弱版本輸出。 ## 執行流程 1. **定範圍**（頂層思維）：一句話問題 + 這次思考要產出什麼決策/輸出 + 失敗成本是否可逆 2. **抽核心**（本質）：留下 2–3 個真正關鍵的變數，丟掉表象和噪音。 - **額外鏡頭觸發點**：逐一檢查每個核心變數——若任一變數的機制無法被六鏡中任何一個充分解釋，標記為「需要額外鏡頭」，進入步驟 2b。 3. **建模型**（底層邏輯）：畫出變數間的機制、狀態轉換、不變規則。 - **降級 checkpoint**：建完模型後檢查——若核心變數間機制單純、不存在真正的權衡取捨，允許跳過步驟 4-6，直接走步驟 7 的簡化版輸出（但仍先跑一次步驟 6b 閘門檢查——簡化不等於跳過樞紐不確定性）。小題大作也是損耗。 4. **壓測試**（逆向思考）：這個模型最可能怎麼垮？反過來做會怎樣？ 5. **疊激勵**（經濟學）— *視問題性質選用*：資源、成本、機會成本、誘因結構是否對齊 6. **疊人性**（心理學）— *視問題性質選用*：偏誤、情緒、認知負荷、信任感。 - **利害關係人矩陣**（組織/多方決策必跑）：這個決策影響誰？各方誘因是否對齊？誰可能抵抗？此為分析失準的最大盲點。 6b. **樞紐問題閘門**（視情況，但優先於急著收斂）：走完步驟 2–6 後，若出現一個「會改變結論、且只有使用者能回答、分析推不出來」的樞紐不確定性——停下，只問使用者**一個**最關鍵的問題，等回答後再跑步驟 7–8。 …
Read the whole file at its exact version.
How to install
mdr add labs21-dev/agents-stack/meta-thinking-framework@sha256:75997d1c3dbab7caThe line at the top of this page pins the label git:20260912.9d47cf0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_j3bx2i32bvglpsqt)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 12, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8165 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
labs21-dev/agents-stack · 27 stars · license none declared · pushed 2026-09-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_j3bx2i32bvglpsqt GET https://markdownregistry.com/api/v1/resolve?ref=labs21-dev/agents-stack/meta-thinking-framework GET https://markdownregistry.com/api/v1/blob/75997d1c3dbab7ca98b51f973016208cb5eacae7ae593cd58a4f7e18717cb0d9
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.