claude

velocitai

Claude Code 专用 UI 自动化代理治理框架：Playwright + pytest POM 技能、规则和自我进化机制

158 on GitHubby Daniel Suov1.0.0MITupdated 1 month ago
/

Plugin velocitai from marketplace velocitai-dev in DanielSuo117/velocitai. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (14)

  • ui-automation-harness

    UI 回归测试子 skill 路由入口。

  • add-regression-point

    为已有 PageObject 增量添加回归测试点。触发：新增测试点、添加回归点、add test point、增加覆盖、扩展页面方法。

  • architecture

    POM 分层与 context 共享决策树。触发：架构、分层、POM、Page Object、基类设计、新增角色。

  • browser-config

    浏览器 viewport / headless / 超时分层配置。触发：viewport、浏览器配置、导航超时、headless、slow_mo、incognito。

  • case-round-trip

    共享 page 下用例离开起点后必须 UI 返回并断言。触发：往返闭合、case round trip、复位超时、scope 共享 page。

  • code-review-graph

    AST 知识图谱：变更审查、探索、调试、重构。触发：知识图谱、代码审查、影响分析、爆炸半径、重构。

  • gen-page-test

    一键生成 PageObject + 配套测试。触发：新增页面、生成页面、gen page、create page、添加页面对象。

  • locator-replacer

    替换占位定位符为真实选择器（六级优先级）。触发：替换定位符、locator、selector、定位失败、元素找不到、DOM 分析。

  • page-load-assertion

    is_page_loaded() 四种验证模式与调用层级。触发：页面断言、is_page_loaded、page loaded、页面加载验证。

  • quick-debug

    测试失败时免登跳转原地排查修复。触发：排查、纠错、debug、定位符失败、超时、元素找不到、断言失败。

  • save-verify-strategy

    表单保存后验证（Toast / 重定向 / 数据对比 / 富文本清空）。触发：保存验证、toast、重定向检测、Meta+A、保存成功判断。

  • selector-self-heal

    复核运行期自愈提案并写回 PageObject。触发：选择器失效、定位符漂移、自愈提案、proposals.jsonl、用例误报不通过。

  • test-runner

    运行 pytest + 结构化分析失败原因。触发：运行测试、跑测试、run test、pytest、失败分析、allure。

  • wait-strategy

    隐式等待为主、显式等待仅慢路径。触发：等待策略、timeout、wait、隐式等待、显式等待。

Hooks (4)

  • PreToolUse

    if command -v py >/dev/null 2>&1; then py -3 "${CLAUDE_PLUGIN_ROOT}/scripts/gate_cli.py" --mode write; elif command -v python3 >/dev/null 2>&1; then python3 "${CLAUDE_PLUGIN_ROOT}/scripts/gate_cli.py"

  • PreToolUse

    if command -v py >/dev/null 2>&1; then py -3 "${CLAUDE_PLUGIN_ROOT}/scripts/gate_cli.py" --mode commit; elif command -v python3 >/dev/null 2>&1; then python3 "${CLAUDE_PLUGIN_ROOT}/scripts/gate_cli.py

  • PreToolUse

    code-review-graph build

  • SessionStart

    code-review-graph status

View source on GitHub

Similar plugins

ruflo-browser

claude

Agentic browser automation with Playwright for testing, scraping, and UI interaction

10 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

playwright

claude

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

1 MCP server

anthropics/claude-plugins-official 47,076

ship-mate

claudecodex

Your AI development teammate. Turns a story file into a shipped, reviewed, and tested feature via orchestrator → architect → developer → PR reviewer → QA → Playwright.

1 skill · 2 commands · 6 agents

wshobson/agents 42,461

engineering-skills

claude

32 engineering skills: architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, Playwright (9 sub-skills), self-improving agent, Stripe integration, TDD guide, tech stack evaluator, Google Workspace CLI, a11y audit (WCAG 2.2), Azure cloud architect, GCP cloud architect, security pen testing, Snowflake development, adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection. v2.8.1 audits senior-fullstack / senior-frontend / senior-backend against karpathy-coder + Matt Pocock — each ships a 7-question forcing-question library, 4 customization profiles (JSON), deterministic decision engine, composition map into POWERFUL specialists, plus cs-fullstack-engineer / cs-frontend-engineer / cs-backend-engineer orchestrator agents (context: fork) + /cs-fullstack-review, /cs-frontend-review, /cs-backend-review, /cs-engineer-grill slash commands.

35 skills · hooks

alirezarezvani/claude-skills 29,725

webwright

claudecodex

Turn your coding agent into a SOTA browser agent. Drives a local Playwright workspace via one bash command at a time, saving screenshots and an action log into final_runs/run_<id>/, and visually self-verifies the result.

1 skill

microsoft/Webwright 6,027

computer-use

claude

Codex-style computer use for Claude Code. Drives Windows and macOS apps through the accessibility tree instead of screenshots, so it targets exactly, survives display scaling, and costs about 20x fewer tokens. It can also work on the same desktop while you keep working, telling your input apart from its own.

1 skill · 1 command · 1 MCP server · hooks

davepoon/buildwithclaude 3,741

Maintain velocitai?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted