一键导入
ui-visual-verification
Verify web and desktop UI changes with browser automation, screenshots, interaction checks, and visual comparison against expected behavior.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Verify web and desktop UI changes with browser automation, screenshots, interaction checks, and visual comparison against expected behavior.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Runtime instructions for Ask mode: answer directly without code mutation.
Runs configurable multi-round research with compare, review, and explore modes, visible progress, source collection, and final sourced answers.
Creates and maintains project-board tasks with correct dedupe, umbrella/root linking, dependencies, tags, authors, assignments, and autopilot queue placement.
Runtime instructions for Plan mode: produce implementation or investigation plans without code mutation.
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.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
| name | ui-visual-verification |
| description | Verify web and desktop UI changes with browser automation, screenshots, interaction checks, and visual comparison against expected behavior. |
| version | 1.0.0 |
| author | Sloppy Team |
| license | MIT |
| platforms | ["linux","macos","windows"] |
| metadata | {"hermes":{"tags":["Development","UI","Browser","Visual-Verification","QA","Screenshots"],"related_skills":["mode-build","test-authoring","development-code-review"]}} |
Use this skill when work affects a user interface, visual layout, web page, desktop screen, interactive flow, accessibility state, or any user-visible behavior that cannot be confidently verified by unit tests alone.
This skill complements automated tests. It does not replace focused unit, integration, or acceptance tests when those are available.
Use visual verification for changes involving:
Do not require browser or desktop visual verification for purely backend, CLI, data-model, or non-UI changes unless the user explicitly asks for it.
Before verification, identify:
Ask the user only when a required URL, credential, account, or expected flow is blocking. Otherwise proceed with the best available local verification.
For web apps:
Prefer browser automation tools when available, such as opening pages, clicking selectors, typing into fields, navigating URLs, and capturing screenshots. If browser automation is unavailable, report that limitation and use screenshots, logs, tests, or manual inspection as appropriate.
For desktop apps:
If the app cannot be launched, the display is unavailable, or interactive tools are missing, state the blocker and perform the strongest remaining validation.
When reporting UI verification, use:
## UI Verification
Surface:
- <URL, route, app window, or screen>
Flows checked:
- <flow/state> — <pass/fail/not checked>
Screenshots:
- <path or description> — <state captured>
Findings:
- <none or issue list with steps, expected, observed>
Limitations:
- <credentials unavailable, app failed to launch, no browser/display tools, or none>