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 VCnoC/Claude-Code-Zen-mcp-Skill-Work --skill gemini-frontendgit clone --depth 1 https://github.com/VCnoC/Claude-Code-Zen-mcp-Skill-WorkWrote 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/vcnoc/claude-code-zen-mcp-skill-work/gemini-frontend)<a href="https://agentmods.dev/skills/vcnoc/claude-code-zen-mcp-skill-work/gemini-frontend"><img src="https://agentmods.dev/badge/skills/vcnoc/claude-code-zen-mcp-skill-work/gemini-frontend/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/vcnoc/claude-code-zen-mcp-skill-work/gemini-frontend"><img src="https://agentmods.dev/badge/skills/vcnoc/claude-code-zen-mcp-skill-work/gemini-frontend.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 | $0.00000 | $0.05369 |
| Opus 5.5 | $0.00000 | $0.02148 |
| Sonnet 5.5 | $0.00000 | $0.01074 |
| Haiku 4.5 | $0.00000 | $0.00537 |
Grade A, and why
gemini-frontend 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 2mo 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 — 689 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gemini-frontend - Gemini CLI 前端开发专用 Skill
Description
专注于前端和移动端开发的 skill,通过 Gemini CLI(via clink)发挥多模态和超长上下文优势。
适用场景:
- React/Vue/Angular 组件开发
- React Native/Flutter 移动端开发
- 设计稿 → 前端代码实现
- UI/UX 实现和优化
- 前端项目重构
核心优势(基于 Gemini 3.0):
- 📷 多模态能力:直接理解设计稿、UI 截图
- 📚 超长上下文:100万 token,处理大型 monorepo
- 🎨 UI 理解:博士级推理能力,理解复杂 UI 逻辑
- 🚀 代码生成:擅长 React/Vue/Flutter 代码生成
⚠️ 重要说明
阶段命名澄清:
- 本 skill 的 Phase 1-5 是内部工作流阶段(Skill-level phases)
- 与 CLAUDE.md 的 P1-P4(分析问题、制定方案、执行方案、错误处理)是不同层级
- gemini-frontend 通常在 P3(执行方案) 阶段被 main-router 调用
- Phase 1-5 是在 P3 阶段内部顺序执行的子步骤
层级关系示例:
P3(执行方案) [CLAUDE.md 项目阶段]
└─ gemini-frontend skill [由 main-router 调用]
├─ Phase 1: 初始化 Gemini CLI 会话
├─ Phase 2: 需求分析与设计
├─ Phase 3: 代码生成
├─ Phase 4: 质量检查
└─ Phase 5: 文档生成
How It's Invoked(如何被调用)
调用方式: 由 main-router skill 自动路由
路由触发条件:
- 用户请求包含前端框架关键词(React, Vue, Angular, Flutter, React Native)
- 用户请求包含 UI/组件/页面 等关键词
- 用户提供设计稿/UI 截图
- frontend_score ≥ 50(参见 main-router 评分机制)
评分机制详解:
main-router 使用以下评分规则判断是否路由到 gemini-frontend:
| 评分项 | 分值 | 示例关键词 |
|---|---|---|
| Tier 1 关键词 | +30~35分 | React, Vue, Angular, component, 组件, 页面, UI, 前端 |
| Tier 2 关键词 | +15~20分 | Flutter, React Native, mobile, 移动端, iOS, Android |
| Tier 3 上下文 | +10分 | package.json 存在且包含前端依赖 |
| 图片附件 | +25分 | 设计稿、UI 截图 |
| 后端信号抵消 | -15~-25分 | API, backend, database, FastAPI, Django |
路由决策阈值:
- Score ≥ 80:自动路由到 gemini-frontend(高置信度)
- Score 50-79:询问用户是否使用 gemini-frontend(中置信度)
- Score < 50 且 backend_signals ≥ 2:全栈项目,建议任务分解
参数继承:
automation_mode: 从 main-router 继承(见 CLAUDE.md 共享概念)coverage_target: 从 main-router 继承(默认 85%,最低 70%)
示例流程:
用户请求: "帮我开发一个 React 登录组件"
↓
main-router 检测:
- "React" (Tier 1) → +35分
- "组件" (Tier 1) → +30分
- 总分: 65分
↓
路由决策: 50 ≤ 65 < 80 → 询问用户
↓
用户确认: "是"
↓
调用 gemini-frontend skill
↓
gemini-frontend 执行 Phase 1-5
↓
返回完整的 React 组件 + 文档 + 质量报告
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.
- 2mo ago First seen · 689 lines · 0 tokens per session scan A a26383d8c522
gemini-frontend is a skill published in the GitHub repository VCnoC/Claude-Code-Zen-mcp-Skill-Work (118 stars, last pushed 10mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,369 tokens. 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 2026-08-30.
gemini-frontend compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gemini-frontendVCnoC/Claude-Code-Zen-mcp-Skill-Work | Skill | 118 | 10mo ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| orca-emulator-androidstablyai/orca | Skill | 117k | yesterday | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | yesterday | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 889 | yesterday | MIT | A | 50 | Claude Code, Codex |