[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75ER2AHH4Z49PRQPDX7Y2WN":3,"skill-same:01M75ER2AHH4Z49PRQPDX7Y2WN":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M75ER2AHH4Z49PRQPDX7Y2WN","six-rung-ladder",null,"Use when deciding whether to write a piece of code, add a dependency, or introduce an abstraction \u002F module \u002F config — the \"should I build this at all?\" filter, applied before building. ｜ 要決定「要不要寫這段 code／引這個依賴／加這層抽象或模組」時使用——「到底該不該做」的過濾網，動手之前先走一遍。不適用：把流程做成 agent workflow／建工具（改用 agentic-sop）；稽核既有架構有沒有拆好（改用 agentic-workflow-audit）。","s0912758806p\u002Fagentic-sop-to-work","s0912758806p","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F46482724?v=4","01M75EPRWVSC8MCRRXHZRWRS74","台服第一打工人(Gorman925)","01M75EPRXG3K3WAVQK2VBW7DW5",211,"MIT","https:\u002F\u002Fgithub.com\u002Fs0912758806p\u002Fagentic-sop-to-work\u002Fblob\u002Fmain\u002Fplugins\u002Fagentic-sop-kit\u002Fskills\u002Fsix-rung-ladder\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: six-rung-ladder\ndescription: Use when deciding whether to write a piece of code, add a dependency, or introduce an abstraction \u002F module \u002F config — the \"should I build this at all?\" filter, applied before building. ｜ 要決定「要不要寫這段 code／引這個依賴／加這層抽象或模組」時使用——「到底該不該做」的過濾網，動手之前先走一遍。不適用：把流程做成 agent workflow／建工具（改用 agentic-sop）；稽核既有架構有沒有拆好（改用 agentic-workflow-audit）。\n---\n\n# 極簡架構過濾網：Six-Rung Ladder\n\n## 角色與目標\n面對任何「要不要寫這段代碼／要不要引入這個東西」的決策時，當一道**逐級過濾網**。核心信念：**Lazy, not negligent（慵懶，但絕不疏漏）**。每一行代碼、每一個依賴、每一個抽象，都是未來的維護成本與攻擊面；最便宜、最安全的代碼，是那行你沒有寫的。\n\n這把梯子是 **decide → build → audit** 方法論的**最前段**：先用它擋掉不該做的，剩下該做的才交給 `agentic-sop` 去建、`agentic-workflow-audit` 去查。\n\n## 怎麼用\n請求從第 1 級開始往下走，**能在哪一級攔下，就在哪一級解決，絕不下沉**。一旦某級給出可行解就停，不要繼續往下找更重的方案。\n\n### 1. YAGNI — 業務真的需要嗎？\n不需要 → **直接拒絕**。先質疑需求本身，而不是急著找實現方案。\n\n### 2. Stdlib — 標準庫能解決嗎？\n優先用語言／執行環境的原生標準庫：大規模驗證、零供應鏈風險、零安裝、隨語言一起維護。\n> **這一級在本專案是機械化的，不是口號**：engine 純標準庫由 `kit\u002Ftests\u002Ftest_no_third_party.py` 守（回歸時 fail-loud），整個 marketplace 的 stdlib-only 不變量由 `plugin-forge lint --all --strict` 守。\n\n### 3. Native Platform — 平台原生特性夠用嗎？\n引入任何函式庫之前，先確認平台是否已提供（瀏覽器 `fetch` \u002F `URL` \u002F `Intl`、CSS 原生特性……往往足以取代一整包依賴）。\n\n### 4. Installed Dependency — 現有依賴能複用嗎？\n前三級都不行，先翻一遍已經裝好的依賴。**堅決不為了一個小功能引入新的供應鏈風險**——每個新依賴都是新的版本維護、安全漏洞與授權問題來源。\n> 同第 2 級：新依賴會被 `test_no_third_party` \u002F `plugin-forge lint` 擋下——這一級有 gate，不靠自律。\n\n### 5. One Line — 一行乾淨代碼行不行？\n與其引入抽象、新模組或新依賴，不如就地寫一行清晰直白的代碼。前提：乾淨、可讀、意圖明確，而非炫技式壓縮。\n\n### 6. The Minimum That Works — 最小可用閉環\n全走不通 → 只寫最小可用、能跑能驗的閉環。不過度設計、不預留花俏擴展點；先讓最小版本真正運作起來。\n\n## 死守紅線：Lazy, not negligent\n「慵懶」是對複雜度／抽象／依賴**保持吝嗇**；「絕不疏漏」是**有些東西一行都不准省**。下列防禦性代碼**永遠不適用上面的偷懶哲學**：\n\n- **跨信任邊界的防注入**：任何外部資料（用戶輸入、第三方回應、檔案內容、URL 參數……）一律當作不可信，做好校驗與轉義。\n- **容災與錯誤處理**：失敗路徑、超時、重試、降級，該寫的都要寫，不能假設一切正常。\n- **安全性**：權限校驗、機密處理、最小權限原則，不能因「先跑起來再說」而跳過。\n\n> 這條紅線與本專案既有鐵則「**防禦代碼不准省**」是同一條；對應的確定性 gate（如 `trace_gate` 防臆造）亦屬此列。在該懶的地方懶到極致，在該嚴的地方一步不讓。\n\n## 速查口訣\n| 級別 | 名稱 | 一句話 |\n|---|---|---|\n| 1 | YAGNI | 業務真需要嗎？不需要就拒絕。 |\n| 2 | Stdlib | 標準庫能不能搞定？（有 gate） |\n| 3 | Native Platform | 平台原生特性夠不夠用？ |\n| 4 | Installed Dependency | 現有依賴能不能複用？（有 gate） |\n| 5 | One Line | 一行乾淨代碼行不行？ |\n| 6 | Minimum That Works | 都不行就寫最小可用閉環。 |\n\n**紅線**：防注入、容災、安全性 — 防禦代碼不准省略。\n\n## 輸出格式\n被觸發時，對該決策逐級回報：**在第幾級攔下、為什麼、具體方案**（或：為何必須下沉到下一級）。若涉及外部輸入／失敗路徑／安全，明確點出哪條紅線項不得偷懶。最後一句結論：**做 ／ 不做 ／ 做最小版**。\n","# 極簡架構過濾網：Six-Rung Ladder\n\n## 角色與目標\n面對任何「要不要寫這段代碼／要不要引入這個東西」的決策時，當一道**逐級過濾網**。核心信念：**Lazy, not negligent（慵懶，但絕不疏漏）**。每一行代碼、每一個依賴、每一個抽象，都是未來的維護成本與攻擊面；最便宜、最安全的代碼，是那行你沒有寫的。\n\n這把梯子是 **decide → build → audit** 方法論的**最前段**：先用它擋掉不該做的，剩下該做的才交給 `agentic-sop` 去建、`agentic-workflow-audit` 去查。\n\n## 怎麼用\n請求從第 1 級開始往下走，**能在哪一級攔下，就在哪一級解決，絕不下沉**。一旦某級給出可行解就停，不要繼續往下找更重的方案。\n\n### 1. YAGNI — 業務真的需要嗎？\n不需要 → **直接拒絕**。先質疑需求本身，而不是急著找實現方案。\n\n### 2. Stdlib — 標準庫能解決嗎？\n優先用語言／執行環境的原生標準庫：大規模驗證、零供應鏈風險、零安裝、隨語言一起維護。\n> **這一級在本專案是機械化的，不是口號**：engine 純標準庫由 `kit\u002Ftests\u002Ftest_no_third_party.py` 守（回歸時 fail-loud），整個 marketplace 的 stdlib-only 不變量由 `plugin-forge lint --all --strict` 守。\n\n### 3. Native Platform — 平台原生特性夠用嗎？\n引入任何函式庫之前，先確認平台是否已提供（瀏覽器 `fetch` \u002F `URL` \u002F `Intl`、CSS 原生特性……往往足以取代一整包依賴）。\n\n### 4. Installed Dependency — 現有依賴能複用嗎？\n前三級都不行，先翻一遍已經裝好的依賴。**堅決不為了一個小功能引入新的供應鏈風險**——每個新依賴都是新的版本維護、安全漏洞與授權問題來源。\n> 同第 2 級：新依賴會被 `test_no_third_party` \u002F `plugin-forge lint` 擋下——這一級有 gate，不靠自律。\n\n### 5. One Line — 一行乾淨代碼行不行？\n與其引入抽象、新模組或新依賴，不如就地寫一行清晰直白的代碼。前提：乾淨、可讀、意圖明確，而非炫技式壓縮。\n\n### 6. The Minimum That Works — 最小可用閉環\n全走不通 → 只寫最小可用、能跑能驗的閉環。不過度設計、不預留花俏擴展點；先讓最小版本真正運作起來。\n\n## 死守紅線：Lazy, not negligent\n「慵懶」是對複雜度／抽象／依賴**保持吝嗇**；「絕不疏漏」是**有些東西一行都不准省**。下列防禦性代碼**永遠不適用上面的偷懶哲學**：\n\n- **跨信任邊界的防注入**：任何外部資料（用戶輸入、第三方回應、檔案內容、URL 參數……）一律當作不可信，做好校驗與轉義。\n- **容災與錯誤處理**：失敗路徑、超時、重試、降級，該寫的都要寫，不能假設一切正常。\n- **安全性**：權限校驗、機密處理、最小權限原則，不能因「先跑起來再說」而跳過。\n\n> 這條紅線與本專案既有鐵則「**防禦代碼不准省**」是同一條；對應的確定性 gate（如 `trace_gate` 防臆造）亦屬此列。在該懶的地方懶到極致，在該嚴的地方一步不讓。\n\n## 速查口訣\n| 級別 | 名稱 | 一句話 |\n|---|---|---|\n| 1 | YAGNI | 業務真需要嗎？不需要就拒絕。 |\n| 2 | Stdlib | 標準庫能不能搞定？（有 gate） |\n| 3 | Native Platform | 平台原生特性夠不夠用？ |\n| 4 | Installed Dependency | 現有依賴能不能複用？（有 gate） |\n| 5 | One Line | 一行乾淨代碼行不行？ |\n| 6 | Minimum That Works | 都不行就寫最小可用閉環。 |\n\n**紅線**：防注入、容災、安全性 — 防禦代碼不准省略。\n\n## 輸出格式\n被觸發時，對該決策逐級回報：**在第幾級攔下、為什麼、具體方案**（或：為何必須下沉到下一級）。若涉及外部輸入／失敗路徑／安全，明確點出哪條紅線項不得偷懶。最後一句結論：**做 ／ 不做 ／ 做最小版**。\n",{"name":5,"description":7},"main","11ac66b3c849f734c4d5bb7989888851a2790557","plugins\u002Fagentic-sop-kit\u002Fskills\u002Fsix-rung-ladder",21,"https:\u002F\u002Fgithub.com\u002Fs0912758806p\u002Fagentic-sop-to-work","https:\u002F\u002Fgithub.com\u002Fs0912758806p","2026-10-30 15:33:50",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add s0912758806p\u002Fagentic-sop-to-work --skill six-rung-ladder",{"tool":37,"command":38},"bunx","bunx skills add s0912758806p\u002Fagentic-sop-to-work --skill six-rung-ladder",{"tool":40,"command":41},"pnpm","pnpm dlx skills add s0912758806p\u002Fagentic-sop-to-work --skill six-rung-ladder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fs0912758806p\u002Fagentic-sop-to-work\u002Fblob\u002Fmain\u002Fplugins\u002Fagentic-sop-kit\u002Fskills\u002Fsix-rung-ladder\u002FSKILL.md",true,[],[46,53,60,67,73,80],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M75ERQYY8P6Y0KKS1W3CET5B","second-opinion","Use when asked to get a second opinion on a finished DRAFT, fact-check or double-check a report's claims against its evidence, sanity-check before sign-off, or red-team an output for fabrication \u002F overreach \u002F invented IDs — even without the word \"honesty\". Works on an agentic-sop-kit run dir (FULL, uses the run's trace) or any plain document (DEGRADED, you supply the inputs). ｜ 要對一份已完成的 DRAFT 取得「第二意見」、在核准前查核報告主張是否有輸入佐證、抓臆造／灌水／過度宣稱／捏造編號時使用；吃 agentic-sop-kit 的 run 目錄（FULL，用 trace）或任何純文件（DEGRADED，需自備輸入）。不適用：稽核 agent 架構有沒有拆好／是不是 mega-agent（改用 agentic-workflow-audit）；審查原始碼品質／bug／資安（改用 \u002Fcode-review）。本 skill 只查「這次產出的主張 vs. 證據」誠實度，只產 DRAFT，核准永遠人擁有。","https:\u002F\u002Fgithub.com\u002Fs0912758806p\u002Fagentic-sop-to-work\u002Fblob\u002Fmain\u002Fplugins\u002Fsecond-opinion-honesty\u002Fskills\u002Fsecond-opinion\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M75ERKM6DKSHDZA89VDHZ7NE","plugin-forge","Use when creating, scaffolding, or linting a Claude Code plugin — generate a grammar-conformant plugin skeleton, or validate a plugin \u002F whole marketplace against house invariants (manifest, frontmatter, stdlib-only, hook protocol, test harness). ｜ 要新建 \u002F scaffold 一個 Claude Code plugin，或 lint 既有 plugin \u002F 整個 marketplace 是否符合房規時使用。","https:\u002F\u002Fgithub.com\u002Fs0912758806p\u002Fagentic-sop-to-work\u002Fblob\u002Fmain\u002Fplugins\u002Fplugin-forge\u002Fskills\u002Fplugin-forge\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M75ERHM911ZJ2NDWG7BT1H24","good-plugin","demo good plugin","https:\u002F\u002Fgithub.com\u002Fs0912758806p\u002Fagentic-sop-to-work\u002Fblob\u002Fmain\u002Fplugins\u002Fplugin-forge\u002Fpluginforge\u002Fexamples\u002Fgood_plugin\u002Fskills\u002Fgood-plugin\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M75ERF3B5R0G5VK82N2W1V56","bad-plugin","https:\u002F\u002Fgithub.com\u002Fs0912758806p\u002Fagentic-sop-to-work\u002Fblob\u002Fmain\u002Fplugins\u002Fplugin-forge\u002Fpluginforge\u002Fexamples\u002Fbad_plugin\u002Fskills\u002Fbad-plugin\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M75ERA23TTWG2VJHD9RSD1RH","alcoa-guard","Use when checking a record \u002F dataset \u002F GMP document for ALCOA+ data integrity — attribution, contemporaneity (backdating), completeness, accuracy (recompute \u002F in-spec), consistency — before a human approves. DEGRADED mode lints any CSV\u002FJSON record against a declared .alcoa.json contract; FULL mode snaps onto an agentic-sop-kit run dir. ｜ 要檢查紀錄\u002F資料\u002FGMP 文件的資料完整性（ALCOA+：可歸屬、同步性\u002F防 backdating、完整、正確、一致）時使用。輸出為 DRAFT，人擁有最終判定；確定性檢查只覆蓋可機械驗證的部分，其餘列為人判斷清單，絕不臆造。","https:\u002F\u002Fgithub.com\u002Fs0912758806p\u002Fagentic-sop-to-work\u002Fblob\u002Fmain\u002Fplugins\u002Falcoa-guard\u002Fskills\u002Falcoa-guard\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M75ER7NGRZZWJPF2CFEJV4G6","sop-flow","Run the agentic-sop-kit workflow (extract→compute→report, or a declared topology) and report the DRAFT result. Works out-of-the-box (bundled demo) even before a project adopts the kit.","https:\u002F\u002Fgithub.com\u002Fs0912758806p\u002Fagentic-sop-to-work\u002Fblob\u002Fmain\u002Fplugins\u002Fagentic-sop-kit\u002Fskills\u002Fsop-flow\u002FSKILL.md",[],[]]