메뉴
Visual diff/screenshot comparison verdict
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Diagnose and fix build/CI failures automatically
Concurrent code generation via multi-model picker
UI/UX design and frontend component generation
OMP self-improvement — analyse own skills/agents and propose improvements
Clone and adapt a web page/design to the codebase
Trace→deep-interview pipeline for deep investigation
| name | visual-verdict |
| description | Visual diff/screenshot comparison verdict |
| trigger | visual-verdict:, /visual-verdict, /omp:visual-verdict |
| autoinvoke | false |
| Field | Value |
|---|---|
| ID | visual-verdict |
| Keywords | visual-verdict:, /visual-verdict |
| Tier | QA Tool |
| Source | src/skills/visual-verdict.mts |
Compares visual diffs or screenshots to render a pass/fail verdict. Accepts before/after image paths or URLs, runs a pixel-level diff, and produces a structured verdict with diff percentage, bounding boxes of changed regions, and a human-readable summary.
interface SkillInput { trigger: string; args: string[]; }
interface SkillOutput { status: "ok" | "error"; message: string; }
export async function activate(input: SkillInput): Promise<SkillOutput>
export function deactivate(): void
Extension-only skill. Triggers visual diff comparison in Copilot. The CLI prints guidance directing users to the Copilot CLI slash command.
P3 scope: Integration with Playwright screenshot capture and CI diff reporting (as specified in SPEC-omp-2.0 §5) are deferred to P3. The current implementation accepts user-supplied image paths only.