Not in the top 1,000 by GitHub stars
a275618631/codex-antigravity-collaboration
Reference architecture and working case study for Codex × Antigravity agent-runtime collaboration.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
shared/skills/GLOBAL_CORE/artifact-storage-policy/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/checklist-validator/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/claude-inspired-artifact-design/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/codex-settings-sync/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/context-pack-builder/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/mac-health/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/model-worker-routing/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/output-contract/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/prompt-portability/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/save-to-notion/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/skill-evaluator/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/web-research-citation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bb7e2553a15f
No earlier version was observed for comparison.
shared/skills/GLOBAL_CORE/writing-style-intake/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bb7e2553a15f
No earlier version was observed for comparison.
Verified commit bb7e2553a15fe690b7c9645c5a679b68f226145b
git clone --filter=blob:none --no-checkout https://github.com/a275618631/codex-antigravity-collaboration.git .hotskills/a275618631-codex-antigravity-collaboration && git -C .hotskills/a275618631-codex-antigravity-collaboration checkout --detach bb7e2553a15fe690b7c9645c5a679b68f226145b
# Copy each selected skill directory from .hotskills/a275618631-codex-antigravity-collaboration into .agents/skills/<skill-name>/Heat
1.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- artifact-storage-policy
shared/skills/GLOBAL_CORE/artifact-storage-policy - checklist-validator
shared/skills/GLOBAL_CORE/checklist-validator - claude-inspired-artifact-design
shared/skills/GLOBAL_CORE/claude-inspired-artifact-design - codex-settings-sync
shared/skills/GLOBAL_CORE/codex-settings-sync - context-pack-builder
shared/skills/GLOBAL_CORE/context-pack-builder - mac-health
shared/skills/GLOBAL_CORE/mac-health - model-worker-routing
shared/skills/GLOBAL_CORE/model-worker-routing - output-contract
shared/skills/GLOBAL_CORE/output-contract - prompt-portability
shared/skills/GLOBAL_CORE/prompt-portability - save-to-notion
shared/skills/GLOBAL_CORE/save-to-notion - skill-evaluator
shared/skills/GLOBAL_CORE/skill-evaluator - web-research-citation
shared/skills/GLOBAL_CORE/web-research-citation - writing-style-intake
shared/skills/GLOBAL_CORE/writing-style-intake
How it works
artifact-storage-policy
When your agent uses it
管理 Codex 交付物的專案識別、Google Drive/GitHub 路由、檔名、儲存位置與回讀驗證;凡工作報告、外部保存、交付成果或新 repository 選擇涉及遠端儲存時使用。
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
1,261 tokensWhen the skill is activated
Reference documents
529 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 目的
- 觸發條件
- 外部平台分流
- Input Schema
- Resolution Workflow
- 交付物索引與摘要錨點
- Date and historical-file rules
- Fail-closed conditions
- Audit fields
Files
SKILL.mdcore4,303 bytesreferences/storage-contract.mddoc2,036 bytes
Read SKILL.md
# 交付物儲存政策
## 目的
先確認專案、目的地與既有位置,再建立或寫入外部交付物。此 Skill 是工作報告、Google Drive 保存與 GitHub repository 選擇的共同政策;不負責搬移歷史檔案,也不取代平台專用工具。
## 觸發條件
- 產出或保存工作報告、設定改版、稽核結果或其他正式成果。
- 使用者要求保存到 Google Drive、GitHub,或同時保存到兩者。
- 需要選擇新 repository、專案資料夾或交付目錄。
- 需要判斷是否沿用既有專案、分支或版本。
## 外部平台分流View the complete source on GitHubchecklist-validator
When your agent uses it
當需要在寄出、發布、合併、部署、歸檔或交接前,對文件、流程、程式碼變更或分析成果做內容、風險與 readiness 最終檢查時使用;本 Skill 不負責最後回報格式。
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
515 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Trigger
- Input Schema
- Workflow
- Output Schema
- Validation
- KPI
Files
SKILL.mdcore1,732 bytes
Read SKILL.md
# 檢查清單驗證器
## Trigger
使用者要求「幫我檢查」、「交付前驗證」、「確認有沒有漏」、「ready check」時啟用。
## Input Schema
必填:
- `artifact`
- `checklist_type`
選填:
- `custom_rules`View the complete source on GitHubclaude-inspired-artifact-design
When your agent uses it
僅當使用者明確要求 Claude 風格、Claude-inspired Artifact,或接近 Claude 式的文件、簡報、UI、Dashboard、HTML、Markdown、React 等產出時使用;一般文字與設計任務不觸發。
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
535 tokensWhen the skill is activated
Reference documents
1,223 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 執行邊界
- 提示與驗收
- 禁止事項
Files
SKILL.mdcore1,844 bytesagents/openai.yamlasset253 bytesreferences/source-priority.mddoc2,645 bytesreferences/visual-artifact-guidance.mddoc1,506 bytes
Read SKILL.md
# Claude 風格產出
只有明確的 Claude/Claude-inspired 要求才套用本 Skill。它提供內容優先、安靜有層次、精準自然且誠實表達限制的設計方向,不複製 Claude 或 Anthropic 的介面、商標、未公開提示詞,也不宣稱成果是官方設計。
## 執行邊界
- 先遵循使用者要求、專案與平台限制,再查證 Anthropic 官方公開提示工程文件;需要最新或精確的官方建議時,讀取 [source-priority.md](references/source-priority.md)。
- 產出 Artifact、文件、簡報或 UI 時,才讀取 [visual-artifact-guidance.md](references/visual-artifact-guidance.md) 的條件式視覺與工程細節。
- 先檢查既有架構、設計系統、內容 schema 與元件庫;只做完成任務所需的最小修改,保留既有功能與可維護性。
- 回覆先給結論,再補充依據、限制與下一步;明確區分事實、推論與待驗證事項。
## 提示與驗收
需要設計提示時,明確指定角色、任務、讀者、格式、內容邊界與驗收條件;複雜輸入可用一致的 XML 標籤分隔。完成前檢查內容正確性、可讀性、功能與專案既有 lint/typecheck/test/build 要求,僅回報實際執行或尚待驗證的項目。View the complete source on GitHubcodex-settings-sync
When your agent uses it
管理、備份、匯出、同步、還原與檢查 Codex 專屬設定(Thin AGENTS.md、default.rules、config.toml、execution profiles)與同步工具。支援「同步設定」「更新 Codex 設定」「套用到另一台 Mac」「完成後同步」等語意。
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
452 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. 權威歸屬 (Canonical Ownership)
- 2. 核心同步規則
Files
SKILL.mdcore1,519 bytes
Read SKILL.md
# Codex 設定同步
## 1. 權威歸屬 (Canonical Ownership)
- **Shared Artifacts 權威庫**:`a275618631/codex-antigravity-collaboration`(擁有 Shared Protocol、13 項 Global Core Skills 與 Canonical Registry)。
- **Codex-specific Artifacts 權威庫**:`a275618631/codex-settings-sync`(擁有 Codex Thin Adapter、Codex 權限規則 `default.rules`、可攜設定與同步工具)。
- **Antigravity-specific Artifacts 權威庫**:`a275618631/antigravity-config`(擁有 Antigravity Thin Adapter 與專屬外掛設定)。
## 2. 核心同步規則
1. 修改 Codex 設定、使用者技能或同步工具前,先於本地執行含時間戳快照的既有備份;全部修改完成並通過靜態檢查後再執行一次最終匯出。
2. GitHub `migration/*` / `master` 是設定同步的來源庫;Google Drive 僅作備份與災難復原,不得在日常套用時與 GitHub 混合覆蓋。
3. 不同步內建 `.system` skills、plugin cache、credentials、tokens、OAuth/auth state、OS schedulers、local paths、session DBs、temp files。
4. 另一台電腦套用前,先執行本地 vs 遠端 Diff 比對,保留目標電腦專有能力,不進行盲目覆蓋。View the complete source on GitHubcontext-pack-builder
When your agent uses it
當需要把長對話、專案歷史、研究資料或零散筆記濃縮成可交接給 Codex、其他 AI Agent 或人類接手的 Context Pack 時使用。
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
345 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Trigger
- Input Schema
- Workflow
- Output Schema
- Validation
- KPI
Files
SKILL.mdcore1,196 bytes
Read SKILL.md
# 上下文包建立器
## Trigger
使用者要求「整理上下文」、「交接給 Codex」、「做 context pack」、「把長對話濃縮」時啟用。
## Input Schema
必填:
- `raw_context`
選填:
- `target_agent`
- `project_goal`View the complete source on GitHubmac-health
When your agent uses it
macOS 系統健康診斷、客觀根因分析 (RCA)、安全優化計畫與 Before/After 效果驗證技能。當使用者反映 Mac 卡頓、變慢、發熱、記憶體不足、空間耗盡、要求優化或驗證改善效果時使用。
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,447 tokensWhen the skill is activated
Reference documents
2,744 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. 核心分析與判斷準則 (RCA Calibration Principles)
- 2. Agent 標準輸出順序
- 3. 安全操作分級 (Safety Levels)
Scripts executed separately
compare.pydiagnose.pymac_health/__init__.pymac_health/collectors.pymac_health/comparator.pymac_health/mole_adapter.pymac_health/optimizer.pymac_health/parsers.pytests/test_diagnose.pytests/test_live_workloads.py
Files
README.mddoc5,986 bytesSKILL.mdcore4,656 bytescompare.pyruns2,147 bytesdiagnose.pyruns3,754 bytesdocs/FUTURE_WORK.mddoc679 bytesdocs/SAFETY.mddoc1,995 bytesmac_health/__init__.pyruns116 bytesmac_health/collectors.pyruns11,213 bytesmac_health/comparator.pyruns6,358 bytesmac_health/mole_adapter.pyruns8,231 bytesmac_health/optimizer.pyruns10,944 bytesmac_health/parsers.pyruns13,246 bytestests/fixtures/df.txtdoc175 bytestests/fixtures/iostat.txtdoc164 bytestests/fixtures/memory_pressure.txtdoc110 bytestests/fixtures/pmset_therm.txtdoc146 bytestests/fixtures/power.jsonasset423 bytestests/fixtures/ps_cpu.txtdoc665 bytestests/fixtures/swapusage.txtdoc80 bytestests/fixtures/vm_stat.txtdoc869 bytestests/test_diagnose.pyruns12,475 bytestests/test_live_workloads.pyruns4,863 bytes
Read SKILL.md
# mac-health 技能指引 (Agent Skill Guide)
本技能規範 AI Agent 如何使用 `diagnose.py`、`optimizer.py`、`compare.py` 進行嚴謹、客觀、不誇大結論的 macOS 系統健康診斷與改善閉環。
---
## 1. 核心分析與判斷準則 (RCA Calibration Principles)
1. **嚴格分級分類**:
- `CONFIRMED BOTTLENECK`:必須有明確、充分且不可辯駁的實質證據(例如:Critical 記憶體壓力且 Free < 20%、CPU 持續 > 85% 且特定進程獨佔、SSD 可用空間 < 15GB)。
- `LIKELY CONTRIBUTOR`:指標處於 Warning 且有單一巨量進程(> 2GB RAM / > 50% CPU)。
- `ATTENTION`:歷史 Swap 較高、短暫 I/O 觀測較忙、或 Memory Free 位於 30%~40% 邊界但無失控進程。
- `NORMAL`:指標處於安全區間。
- `UNKNOWN`:無法確定或無足夠權限取得之數據。View the complete source on GitHubmodel-worker-routing
When your agent uses it
Route a task to the existing Ox Alpha worker only when the user explicitly names Ox Alpha; preserve normal Codex behavior for all other tasks.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
826 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Trigger
- Workflow
- Result and user-facing behavior
Files
SKILL.mdcore3,592 bytesSKILL.mdcore3,592 bytesSKILL.mdcore3,592 bytesagents/openai.yamlasset205 bytes
Read SKILL.md
# Model Worker Routing
Use this skill only for an explicit opt-in route. Do not infer delegation from task size, cost, token usage, or coding difficulty.
## Trigger
Trigger only when the current user request explicitly contains Ox Alpha, including these forms:
- `本任務用 Ox Alpha`
- `本任務交給 Ox Alpha`
- `這個任務用 Ox Alpha`
- `這次用 Ox Alpha`
- `請用 Ox Alpha 執行本任務`
- `用 Ox Alpha 做這個任務`View the complete source on GitHuboutput-contract
When your agent uses it
任務完成前需要一致交付格式、修改清單、驗證結果、風險或待確認事項時使用;適用於程式碼、設定、文件、Skills、同步與多步驟任務收尾,不取代內容或安全檢查。
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
299 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 必要欄位
- 高風險附加欄位
Files
SKILL.mdcore1,020 bytes
Read SKILL.md
# 交付契約
收尾時用最少必要資訊讓使用者知道成果是否完成、改了什麼、如何驗證,以及還有哪些限制。
## 必要欄位
```text
完成狀態
- ...
修改清單
- ...(無修改則寫「無」)
驗證View the complete source on GitHubprompt-portability
When your agent uses it
需要把 Codex / Claude 的全域規則、skill 原則、工作流程或提示詞移植到 Gemini、ChatGPT、Claude 網頁版、API、或其他不具備本機檔案修改能力的平台時使用。
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
421 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 目標
- 流程
- 輸出格式
- 判斷原則
Files
SKILL.mdcore1,366 bytes
Read SKILL.md
# 提示詞移植
## 目標
把規則轉成目標平台真正能執行的版本,刪除平台不支援的本機操作要求,保留思考品質與交付品質。
## 流程
1. 確認目標平台:Gemini 網頁版、Claude 網頁版、ChatGPT、API、Codex、Claude Code。
2. 判斷平台能力:是否可讀寫檔案、是否可用工具、是否可執行程式、是否可上網、是否支援自訂指令。
3. 保留跨平台原則:繁中、先理解、列假設、低成本優先、少做多餘功能、查證、結論清楚。
4. 刪除或降級不適用規則:本機檔案修改、Git、`.env`、同步腳本、工作區路徑、工具權限。
5. 壓縮成適合目標欄位的長度;必要時提供完整版與短版。
View the complete source on GitHubsave-to-notion
When your agent uses it
將 Codex 對話、回答、決策、工作流程與可重用知識整理到使用者的 Notion 知識 Hub;僅在使用者明確要求保存、歸檔或更新到 Notion 時觸發,一般報告不自動寫入。
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
547 tokensWhen the skill is activated
Reference documents
2,213 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 寫入門檻與驗證
- 最小工作流程
- 路由參考
Files
SKILL.mdcore1,856 bytesagents/openai.yamlasset191 bytesreferences/notion-templates.mddoc5,436 bytesreferences/workspace-routing.mddoc1,183 bytes
Read SKILL.md
# Save To Notion
將可重用的結論、流程、決策、版本變更與下一步整理成結構化 Notion 內容,不保存原始聊天流水帳。
## 寫入門檻與驗證
- 只有使用者明確指定 Notion 作為目的地,或明確要求保存/歸檔到 Notion,才執行實際寫入;否則只提供可貼上的草稿。
- 寫入前先用 Notion `fetch("self")` 驗證目前帳號與 Workspace,再重新讀取目標 Data Source schema;不得沿用快取欄位、舊 URL 或舊 schema。
- 帳號、Workspace、目標頁面或 Data Source 不一致時停止寫入並回報,不自動切換、建立或搬移資料庫。
- 建立前搜尋相同主題,決定更新既有頁面或建立新頁面;歷史頁面不自動搬移、複製或刪除。
## 最小工作流程
1. 讀取現行工作區標準與目標 schema,確認內容分類與目的地。View the complete source on GitHubskill-evaluator
When your agent uses it
建立、修改、比較、瘦身或優化 Codex / Claude / Agent Skills 時使用。特別適用於「評估這個 skill 是否更好」、「吸收官方 skill 優點」、「降低 token」、「提高觸發準確率」、「建立測試 prompt」。
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
532 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 目標
- 評估流程
- 比較表格式
- 修改原則
- 完成回報
Files
SKILL.mdcore1,755 bytes
Read SKILL.md
# Skill 評估器
## 目標
用可比較的方式優化 skill,而不是憑感覺改。優先提升觸發準確率、可用率、輸出一致性、token 效率與安全性。
## 評估流程
1. 讀取現有 skill 的 `name`、`description`、核心流程與輸出格式。
2. 讀取候選 skill 或官方範例,只吸收明顯更好的設計,不照搬無關內容。
3. 用以下維度比較:觸發準確、步驟清楚、輸出契約、驗證方式、token 成本、安全邊界、可重用資源。
4. 產生 5-10 個真實測試 prompt:包含 should-trigger、should-not-trigger、模糊口語、近似但不該觸發情境。
5. 若能執行測試,做舊版 vs 新版比較;不能執行時,至少做人工靜態檢查。
6. 修改 skill 時保持精簡;把長參考移到 `references/`,把重複程式放到 `scripts/`。View the complete source on GitHubweb-research-citation
When your agent uses it
需要查最新資訊、官方公告、文章、價格、法規、API 文件、產品規格、公司/人物狀態,或需要引用來源與日期時使用。
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
240 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 流程
- 輸出格式
- 注意
Files
SKILL.mdcore829 bytes
Read SKILL.md
# 網路研究與引用
## 流程
1. 先判斷資訊是否可能過期;若可能,必須查證。
2. 優先官方來源、原始文件、研究論文、法規原文;技術問題優先官方 docs。
3. 比對發布日期與事件日期。
4. 區分事實、來源主張與自己的推論。
5. 回覆附來源連結,避免長篇逐字引用。
## 輸出格式
```text
結論:...View the complete source on GitHubwriting-style-intake
When your agent uses it
建立、撰寫、改寫或完成文字交付物前,用最少必要問題確認風格;使用者已指定風格、提供足夠範例或說「你決定」時直接執行,不重複盤問。
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
485 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 決策邊界
- 寫作規則
Files
SKILL.mdcore1,596 bytesagents/openai.yamlasset254 bytesreferences/style-options.mddoc1,357 bytes
Read SKILL.md
# 文字風格確認
先判斷風格資訊是否真的會改變成品,再決定詢問或直接寫作。此 Skill 負責風格邊界與自然度,不取代 DOCX、簡報、PDF 或試算表等專用技能。
## 決策邊界
1. 檢查使用者是否已提供語氣、正式程度、讀者、目的、格式或參考範例。
2. 若資訊足以執行,簡短重述採用風格後直接開始。
3. 使用者說「你決定」、「照原文」或要求延續既有風格時,對缺漏採用保守合理預設,不追問。
4. 校正錯字、短句翻譯、單句改寫或固定格式填入,不額外詢問。
5. 只有缺少的讀者、目的、格式或語氣會明顯改變成品時,才問一個關鍵問題並提供精簡選項;不要進行第二輪盤問。
## 寫作規則
View the complete source on GitHubSkills included
- artifact-storage-policy
- checklist-validator
- claude-inspired-artifact-design
- codex-settings-sync
- context-pack-builder
- mac-health
- model-worker-routing
- output-contract
- prompt-portability
- save-to-notion
- skill-evaluator
- web-research-citation
- writing-style-intake
Repository facts
- License
- MIT
- Created
- Aug 21, 2026
- Last pushed
- Nov 4, 2026
- Forks
- 1
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 2 notes
shared/skills/GLOBAL_CORE/model-worker-routing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedshared/skills/GLOBAL_CORE/model-worker-routing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 3 dangerous shell commandsin 3 files: mac-health/README.md:180 mac-health/SKILL.md:78 mac-health/docs/SAFETY.md:32
- 14 network referencesin 5 files: claude-inspired-artifact-design/references/source-priority.md:14 save-to-notion/references/workspace-routing.md:5 artifact-storage-policy/references/storage-contract.md:9 and 2 more
- No hidden or obfuscated text
- No instruction overrides
- 10 executable scriptsin 10 files: mac-health/compare.py:1 mac-health/diagnose.py:1 mac-health/mac_health/__init__.py:1 and 7 more
- 2 references to secretsin 2 files: mac-health/SKILL.md:78 mac-health/docs/SAFETY.md:37
- No requests to vote in Hot
Show all 29 signals by file
shared/skills/GLOBAL_CORE/artifact-storage-policy/references/storage-contract.md
shared/skills/GLOBAL_CORE/claude-inspired-artifact-design/references/source-priority.md
- Network accessline 14
- Prompting best practices:<https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices> - Network accessline 15
- Prompt engineering overview:<https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview> - Network accessline 16
- Anthropic Prompt Library 入口:<https://docs.anthropic.com/en/prompt-library> - Network accessline 17
- Anthropic Prompt Generator 說明:<https://www.anthropic.com/news/prompt-generator>
shared/skills/GLOBAL_CORE/mac-health/README.md
- Dangerous shell operationline 180
- **無 sudo / 提權需求**:一般使用者權限即可完整運作。
shared/skills/GLOBAL_CORE/mac-health/SKILL.md
shared/skills/GLOBAL_CORE/mac-health/compare.py
- Executable scriptline 1
#!/usr/bin/env python3
shared/skills/GLOBAL_CORE/mac-health/diagnose.py
- Executable scriptline 1
#!/usr/bin/env python3
shared/skills/GLOBAL_CORE/mac-health/docs/SAFETY.md
shared/skills/GLOBAL_CORE/mac-health/mac_health/__init__.py
- Executable scriptline 1
Executable file
shared/skills/GLOBAL_CORE/mac-health/mac_health/collectors.py
- Executable scriptline 1
Executable file
shared/skills/GLOBAL_CORE/mac-health/mac_health/comparator.py
- Executable scriptline 1
Executable file
shared/skills/GLOBAL_CORE/mac-health/mac_health/mole_adapter.py
- Executable scriptline 1
Executable file
shared/skills/GLOBAL_CORE/mac-health/mac_health/optimizer.py
- Executable scriptline 1
Executable file
shared/skills/GLOBAL_CORE/mac-health/mac_health/parsers.py
- Executable scriptline 1
Executable file
shared/skills/GLOBAL_CORE/mac-health/tests/test_diagnose.py
- Executable scriptline 1
Executable file
shared/skills/GLOBAL_CORE/mac-health/tests/test_live_workloads.py
- Executable scriptline 1
Executable file
shared/skills/GLOBAL_CORE/save-to-notion/SKILL.md
- Network accessline 12
- 只有使用者明確指定 Notion 作為目的地,或明確要求保存/歸檔到 Notion,才執行實際寫入;否則只提供可貼上的草稿。 - 寫入前先用 Notion `fetch("self")` 驗證目前帳號與 Workspace,再重新讀取目標 Data Source schema;不得沿用快取欄位、舊 URL 或舊 schema。 - Network accessline 13
- 寫入前先用 Notion `fetch("self")` 驗證目前帳號與 Workspace,再重新讀取目標 Data Source schema;不得沿用快取欄位、舊 URL 或舊 schema。
shared/skills/GLOBAL_CORE/save-to-notion/references/notion-templates.md
shared/skills/GLOBAL_CORE/save-to-notion/references/workspace-routing.md
- Network accessline 5
- Notion 帳號:`a275618631@gmail.com` - Workspace:`Dan Wu's Notion` - Hub:`工作控制中心`(`https://app.notion.com/p/440e62ad3eb382c4977201bf8ba9b217`) - Network accessline 6
- Workspace:`Dan Wu's Notion` - Hub:`工作控制中心`(`https://app.notion.com/p/440e62ad3eb382c4977201bf8ba9b217`) - 工作區架構總綱:`https://app.notion.com/p/3a6e62ad3eb3811fb01ccc6b41c34d5d` - Network accessline 7
- Hub:`工作控制中心`(`https://app.notion.com/p/440e62ad3eb382c4977201bf8ba9b217`) - Network accessline 8
- 工作區架構總綱:`https://app.notion.com/p/3a6e62ad3eb3811fb01ccc6b41c34d5d`
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 29 facts
- Network access in prose of documentationartifact-storage-policy/references/storage-contract.md:9Low confidence
- Network access in prose of documentationartifact-storage-policy/references/storage-contract.md:10Low confidence
- Network access in prose of documentationclaude-inspired-artifact-design/references/source-priority.md:14Low confidence
- Network access in prose of documentationclaude-inspired-artifact-design/references/source-priority.md:15Low confidence
- Network access in prose of documentationclaude-inspired-artifact-design/references/source-priority.md:16Low confidence
- Network access in prose of documentationclaude-inspired-artifact-design/references/source-priority.md:17Low confidence
- Dangerous shell operation in prose of documentationmac-health/README.md:180Low confidence
- Dangerous shell operation in prose of the SKILL.mdmac-health/SKILL.md:78Low confidence
- Access to secrets in prose of the SKILL.mdmac-health/SKILL.md:78Low confidence
- Executable script in code of a file that runsmac-health/compare.py:1High confidence
- Executable script in code of a file that runsmac-health/diagnose.py:1High confidence
- Dangerous shell operation in prose of documentationmac-health/docs/SAFETY.md:32Low confidence
- Access to secrets in prose of documentationmac-health/docs/SAFETY.md:37Low confidence
- Executable script in prose of a file that runsmac-health/mac_health/__init__.py:1Low confidence
- Executable script in prose of a file that runsmac-health/mac_health/collectors.py:1Low confidence
- Executable script in prose of a file that runsmac-health/mac_health/comparator.py:1Low confidence
- Executable script in prose of a file that runsmac-health/mac_health/mole_adapter.py:1Low confidence
- Executable script in prose of a file that runsmac-health/mac_health/optimizer.py:1Low confidence
- Executable script in prose of a file that runsmac-health/mac_health/parsers.py:1Low confidence
- Executable script in prose of a testmac-health/tests/test_diagnose.py:1Low confidence
- Executable script in prose of a testmac-health/tests/test_live_workloads.py:1Low confidence
- Network access in prose of the SKILL.mdsave-to-notion/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdsave-to-notion/SKILL.md:13Low confidence
- Network access in prose of documentationsave-to-notion/references/notion-templates.md:5Low confidence
- Network access in prose of documentationsave-to-notion/references/notion-templates.md:17Low confidence
- Network access in prose of documentationsave-to-notion/references/workspace-routing.md:5Low confidence
- Network access in prose of documentationsave-to-notion/references/workspace-routing.md:6Low confidence
- Network access in prose of documentationsave-to-notion/references/workspace-routing.md:7Low confidence
- Network access in prose of documentationsave-to-notion/references/workspace-routing.md:8Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md shared/skills/GLOBAL_CORE/artifact-storage-policy/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md shared/skills/GLOBAL_CORE/artifact-storage-policy/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md shared/skills/GLOBAL_CORE/artifact-storage-policy/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md shared/skills/GLOBAL_CORE/artifact-storage-policy/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md shared/skills/GLOBAL_CORE/artifact-storage-policy/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.