Individual skill
claude-inspired-artifact-design
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。
shared/skills/GLOBAL_CORE/claude-inspired-artifact-design/SKILL.md
Source commit bb7e2553a15fe690b7c9645c5a679b68f226145b
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Instructions only
- Last checked
- Nov 7, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 11
- Repository last updated
- Nov 4, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-architecture Repository topic
- agent-skills Repository topic
- ai-agents Repository topic
- antigravity Repository topic
- codex Repository topic
- mcp Repository topic
- multi-agent Repository topic
- design Derived category
- engineering Derived category
- design-interface Derived category
- engineering-web Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 1,844 bytesagents/openai.yamlasset · 253 bytesreferences/source-priority.mddoc · 2,645 bytesreferences/visual-artifact-guidance.mddoc · 1,506 bytes
Read excerpt
# 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。