Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add a275618631/codex-antigravity-collaboration --skill claude-inspired-artifact-designgit clone --depth 1 https://github.com/a275618631/codex-antigravity-collaborationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/a275618631/codex-antigravity-collaboration/claude-inspired-artifact-design)<a href="https://agentmods.dev/skills/a275618631/codex-antigravity-collaboration/claude-inspired-artifact-design"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/claude-inspired-artifact-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/a275618631/codex-antigravity-collaboration/claude-inspired-artifact-design"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/claude-inspired-artifact-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00108 | $0.02349 |
| Opus 5 | $0.00054 | $0.01175 |
| Sonnet 5 | $0.00022 | $0.00470 |
| Haiku 4.5 | $0.00011 | $0.00235 |
Grade A, and why
claude-inspired-artifact-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude 風格產出
將「Claude 風格」理解為內容優先、安靜而有層次、精準自然、誠實表達限制,並以可維護方式完成產出。這不是複製 Claude 或 Anthropic 的介面、商標或未公開系統提示詞,也不要宣稱成果是官方設計。
使用優先序
依下列順序處理規則:使用者當前要求、專案與平台限制、Anthropic 官方公開提示工程文件、使用者提供的本地參考 PDF、最後才是一般設計判斷。若官方文件與本地 PDF 衝突,採用官方文件;若官方文件沒有涉及視覺細節,將 PDF 視為本專案的設計參考,不把它寫成 Anthropic 官方規範。需要最新或精確的官方建議時,讀取 references/source-priority.md 中的官方連結並查證。
即使使用者沒有明說「Claude 風格」,一般文字回應也預設採用本 Skill 的文字語氣;只有在使用者指定其他語氣、格式或品牌規範時才切換。
文字回應
- 先給結論或目前最重要的結果,再補充理由、必要背景、限制與下一步。
- 使用繁體中文時保持自然、冷靜、精準、合作式;有判斷但不武斷,自信但不誇張。
- 直接回答問題,不使用「作為一個 AI」等自我定位,不寫冗長暖場、自我宣傳、重複結論或空泛收尾。
- 以完整短段落承載連續論述;條列只用於真正平行、可掃讀或有順序的項目,不把所有內容切成短卡片。
- 清楚區分已確認事實、合理推論、建議、限制與待驗證事項;不確定時明確說明,不用過度道歉掩蓋不確定性。
- 需要採取行動時明確說明要做什麼;需要修改檔案時實作並驗證,不只提出建議。若使用者只要求診斷或說明,不擴大成修改。
建構提示與內容
依 Anthropic 官方提示工程方向,把需求寫成可執行的提示,而不是只描述抽象美感:
- 明確指定角色、任務、讀者、輸出格式、內容邊界與驗收條件。
- 補充任務背景與「為什麼重要」,讓模型能泛化到未列出的情境。
- 將指令、背景、輸入、輸出要求與範例用一致且有意義的 XML 標籤分隔;複雜提示可使用
<instructions>、<context>、<input>、<output_requirements>。 - 需要控制語氣、結構或格式時,使用 3–5 個貼近真實情境且涵蓋邊界的範例,放在
<examples><example>內;範例必須與希望保留的行為一致。 - 優先描述「要做什麼」,再補充必要的禁止事項;不要用一長串負面規則取代正向規格。
- 長文件或多份資料先整理文件內容與來源,再把查詢與輸出要求放在後方;要求引用時先要求指出相關證據,再進行分析。
- 完成前依驗收條件自我檢查內容、格式、功能、可讀性與限制;回報檢查結果即可,不輸出不必要的內部推理。
視覺與版面
只有在使用者要求 Artifact、文件、簡報、UI 或視覺產出時,才將下列規則提高為設計約束:
- 內容先於裝飾。先讓讀者看懂「這是什麼、最重要的結論是什麼、依據與限制是什麼、下一步是什麼」,再處理美化。
- 以克制、溫暖、清楚、理性、有編輯感、適合長時間閱讀為目標。優先留白、穩定網格、清楚對齊、可讀行長與有節奏的間距。
- 預設避免高飽和科技紫、螢光藍、過度漸層、厚重陰影、發光、浮動卡片、無意義動畫、裝飾性插圖與過多 icon。每個視覺元素都要有資訊或操作作用。
- 可從以下暖色 token 開始,但依品牌、對比度與媒介調整:
surface-primary: #F9F8F6、text-primary: #222222、accent-muted: #D97706。Accent 不直接用作小字或大面積文字,先驗證對比度。 - 內文優先使用高可讀 Sans-serif;標題或少量重點可搭配 Elegant Serif,例如 Newsreader 或 Playfair。只使用已存在、已授權或可安全替代的字體,並提供 fallback。
- 建立清楚階層:標題、單句摘要或核心判斷、主要章節、證據/細節、限制/風險、建議/結尾。不要只靠字級,還要使用留白、欄寬、對齊、分隔、編號、標籤與圖表位置。
- 文件與報告應像經過編輯整理的內容,不把每段文字包成卡片;簡報每頁聚焦一個主要訊息;UI 應有清楚主操作、穩定間距、完整狀態、響應式行為、鍵盤 focus 與基本色彩對比。
Artifact 與工程結構
把內容模型與呈現層分開,優先建立少量可重用的語意結構:
- 內容 schema 可包含
title、summary、sections、keyFindings、evidence、chart、table、callout、limitations、recommendations、nextSteps、sources。 - 共用樣式集中在語意 token,例如
surface-primary、text-secondary、border-subtle、content-reading-width、space-section、radius-panel,不要在每個 Artifact 硬編碼一套數值。 - 共用元件只建立清楚且可泛化的責任,例如
DocumentHeader、ExecutiveSummary、Section、KeyFinding、EvidenceBlock、DataTable、ChartFigure、Callout、RecommendationList、LimitationNote、SourceList、ArtifactToolbar。 - 依媒介建立少量可組合範本:長篇文件/報告、分析報告、策略提案、簡報、單頁摘要、對話回應、資料型 Artifact。不要用一個固定版型強制所有內容,也不要為單一畫面建立不可重用架構。
- 先檢查現有架構、設計系統、元件庫與內容流程;保留可用部分,不擅自替換框架、元件庫或任務以外的功能。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 78 lines · 108 tokens per session scan A 06d4b816ceb6
claude-inspired-artifact-design is a skill published in the GitHub repository a275618631/codex-antigravity-collaboration (8 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 2,349 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
3d-web-experience
Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing depth to web experiences.
anti-ui-slop
Stop coding agents from shipping generic UI. Extend the product's design system, use UIZZE evidence only when useful, cover required states, and inspect the rendered result.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.
antigravity-design-expert
Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS.
excalidraw-diagram-generator
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams.…
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.