Token导航 LogoToken导航TokenDH.com
前端设计操作浏览器github未标认证来源可访问许可证需确认审计未展示

ring%3adev-frontend-visualRing%3adev 前端视觉

Agent Skill

用于辅助前端页面、组件、样式和交互逻辑的开发与维护。它适合让 Agent 生成或审查 React、Next.js、Vue、Tailwind、CSS 等相关代码,整理组件结构,或定位布局和性能问题。使用时需要结合项目现有设计系统、路由和构建方式,避免只生成孤立片段;涉及页面改动时,应配合本地预览和构建检查确认视觉效果。

总安装

523

周安装

22

GitHub Stars

180

下载量

183
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ring%3adev-frontend-visual(Ring%3adev 前端视觉)
来源仓库:https://github.com/lerianstudio/ring
仓库路径:skills/ring%3Adev-frontend-visual
安装命令:
npx skills add https://github.com/lerianstudio/ring --skill ring:dev-frontend-visual
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/lerianstudio/ring --skill ring:dev-frontend-visual

简介

用于辅助前端页面、组件、样式和交互逻辑的开发与维护,适合生成视觉一致的 UI 代码。

  • 支持基于现有设计系统生成 React、Next.js 组件结构。
  • 涉及页面改动时需配合本地预览确认视觉效果。
  • 通过 GitHub 仓库获取技能定义,需结合原始 README 确认具体用法。
  • ring%3adev-frontend-visual 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Dev Frontend Visual Testing (Gate 4)

Overview

Ensure all frontend components have snapshot tests covering all states, responsive viewports, and edge cases. Detect visual regressions before code review.

Core principle: If a user can see it, it must have a snapshot. All states, all viewports.

<block_condition>

  • Missing state snapshots = FAIL
  • Snapshot test failures = FAIL
  • sindarian-ui component duplicated in shadcn = FAIL </block_condition>

CRITICAL: Role Clarification

This skill ORCHESTRATES. Frontend QA Analyst Agent (visual mode) EXECUTES.

WhoResponsibility
This SkillGather requirements, dispatch agent, track iterations
QA Analyst Frontend AgentWrite snapshot tests, verify states, check duplication

Standards Reference

Standards Source (Cache-First Pattern): This sub-skill reads standards from state.cached_standards populated by dev-cycle Step 1.5. If invoked outside a cycle (standalone), it falls back to direct WebFetch with a warning. See shared-patterns/standards-cache-protocol.md for protocol details.

MANDATORY: Load testing-visual.md standards using the cache-first pattern below.

Required URL: https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/frontend/testing-visual.md

For the required standards URL above:
  IF state.cached_standards[url] exists:
    → Read content from state.cached_standards[url].content
    → Log: "Using cached standard: {url} (fetched {state.cached_standards[url].fetched_at})"
  ELSE:
    → WebFetch url (fallback — should not happen if orchestrator ran Step 1.5)
    → Log warning: "Standard {url} was not pre-cached; fetched inline"

<fetch_required> https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/frontend/testing-visual.md </fetch_required>


Step 1: Validate Input

REQUIRED INPUT:
- unit_id: [TASK id — this gate runs at task cadence, aggregating all subtasks]
- implementation_files: [union of changed files across all subtasks of the task]
- gate0_handoffs: [array of per-subtask implementation handoffs, one per subtask]

OPTIONAL INPUT:
- ux_criteria_path: [path to ux-criteria.md]
- gate3_handoff: [full Gate 3 output]

if any REQUIRED input is missing:
  → STOP and report: "Missing required input: [field]"

if gate0_handoffs is not an array:
  → STOP and report: "gate0_handoffs must be an array of per-subtask handoffs"

Step 2: Dispatch Frontend QA Analyst Agent (Visual Mode)

Task tool:
  subagent_type: "ring:qa-analyst-frontend"
  prompt: |
    **MODE:** VISUAL TESTING (Gate 4)

    **Standards:** Load testing-visual.md

    **Input:**
    - Task ID: {unit_id} (task-level — aggregates all subtasks)
    - Implementation Files (union across all subtasks): {implementation_files}
    - Per-Subtask Gate 0 Handoffs: {gate0_handoffs}
    - UX Criteria: {ux_criteria_path or "N/A"}

    **Scope:** Validate visual/snapshot coverage for the task (all subtasks aggregated), not a single subtask.

    **Requirements:**
    1. Create snapshot tests for all components
    2. Cover all states (Default, Empty, Loading, Error, Success, Disabled)
    3. Add responsive snapshots (375px, 768px, 1280px) for layout components
    4. Test edge cases (long text, 0 items, special characters)
    5. Verify no sindarian-ui component duplication in components/ui/

    **Output Sections Required:**
    - ## Visual Testing Summary
    - ## Snapshot Coverage
    - ## Component Duplication Check
    - ## Handoff to Next Gate

Step 3: Evaluate Results

Parse agent output:

if "Status: PASS" in output:
  → Gate 4 PASSED
  → Return success with metrics

if "Status: FAIL" in output:
  → If missing snapshots: re-dispatch agent to add missing
  → If duplication found: re-dispatch implementation agent to fix
  → Re-run visual tests (max 3 iterations)
  → If still failing: ESCALATE to user

Step 4: Generate Output

## Visual Testing Summary
**Status:** {PASS|FAIL}
**Components with Snapshots:** {count}
**Total Snapshots:** {count}
**Snapshot Failures:** {count}

## Snapshot Coverage
| Component | States | Viewports | Edge Cases | Status |
|-----------|--------|-----------|------------|--------|
| {component} | {X/Y} | {X/Y or N/A} | {description} | {PASS|FAIL} |

## Component Duplication Check
| Component in components/ui/ | In sindarian-ui? | Status |
|-----------------------------|------------------|--------|
| {component} | {Yes|No} | {PASS|FAIL} |

## Handoff to Next Gate
- Ready for Gate 5 (E2E Testing): {YES|NO}
- Iterations: {count}

Severity Calibration

SeverityCriteriaExamples
CRITICALComponent duplication, major visual regressionsindarian-ui duplicated in shadcn, layout completely broken
HIGHMissing state snapshots, snapshot failuresNo loading/error state snapshot, unexpected diff
MEDIUMIncomplete coverage, minor visual issuesMissing viewport size, edge case not tested
LOWDocumentation, test organizationMissing snapshot descriptions, file naming

Report all severities. CRITICAL = immediate fix. HIGH = fix before gate pass. MEDIUM = fix in iteration. LOW = document.


Anti-Rationalization Table

See shared-patterns/shared-anti-rationalization.md for universal anti-rationalizations. Gate-specific:

RationalizationWhy It's WRONGRequired Action
"Snapshots are brittle"Brittle = catches unintended changes. That's the point.Write snapshot tests
"We test visually in browser"Manual testing misses regressions. Automated is repeatable.Add snapshot tests
"Only default state matters"Error and loading states are user-facing.Test all states
"Mobile is just smaller"Layout changes at breakpoints. Test all viewports.Add responsive snapshots
"This shadcn component is better"sindarian-ui is PRIMARY. Don't duplicate.Check sindarian-ui first

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.43%
按下载量换算65

Claude

26.76%
按下载量换算49

Cursor

19.32%
按下载量换算35

Gemini CLI

8.65%
按下载量换算16

安全审计

暂无安全审计结果可展示。

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills