离线环境下构建或审查前端界面的设计指引
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add wangzhe04/ruyi-workbench-oss --skill frontend-design-craft --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Frontend Design Craft?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wangzhe04-frontend-design-craft)More formats (shields.io, HTML) on the badges page.
---
name: 前端设计精修
description: 离线环境下构建或审查前端界面的设计指引
---
# Frontend Design Craft
Use this skill when building or reviewing frontend UI in an offline Windows environment.
Inspired by the popular Claude plugin category for frontend design, but implemented as local-only guidance plus Workbench tools.
Workflow:
1. Use `project_snapshot` and `dependency_inventory` to understand the app stack.
2. Use `frontend_audit` before and after edits to catch offline CDN usage, viewport issues, font scaling, and generic visual patterns.
3. Avoid CDN fonts, icon CDNs, remote images, hosted JS, and remote CSS. Bundle assets locally.
4. Prefer the app's existing component system and icons. If none exists, use simple HTML/CSS with local assets.
5. Start or inspect the dev server with `powershell_run`; open the page with `browser_open`; verify with `desktop_screenshot`.
6. For fixed UI controls, use stable dimensions, responsive constraints, and text wrapping. Do not let labels resize boards, toolbars, or tiles.
Output expectations:
- Mention the files changed.
- Include the local URL or file path that was verified.
- Report any offline asset risks found by `frontend_audit`.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
