跳到正文
cccskills
免费在 GitHub 公开

visual-ralph

Builds or restyles interfaces against an approved image or live web page. It guides repeated visual checks and pixel comparisons, then preserves reusable styling rules and components alongside screenshots and verification evidence.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

查看安装方法

适用场景

  • Building an interface from an approved mockup
  • Restyling an interface to match a live web page
  • Preserving reusable styles and components from a visual implementation

包含的文件(1)

  • SKILL.md5.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Visual Ralph Skill

Use $visual-ralph for measured frontend implementation from an approved generated reference, static image, or live-URL baseline. The loop is:

description / URL -> approved reference -> $ultragoal implementation -> Visual Ralph verdict + pixel diff -> reusable design system.

For URL cloning, this skill owns the migrated $web-clone use case; preserve URL, viewport, fidelity, and interaction notes here. Do not invoke standalone $web-clone.

Shared operating, delegation, state, hook, team, cancellation, and verification invariants live in templates/AGENTS.md. Follow that source instead of duplicating its rules here.

Use when

  • The user wants a web/app UI built or restyled against a visual target.
  • A live URL or generated raster mockup needs measured implementation and pixel-level iteration.
  • The result must leave reusable repo-native tokens/components, not only a matching screenshot.

Do not use it for a durable DESIGN.md brief ($design), non-visual backend work, comparison-only fixes that can be executed directly, or deterministic SVG/code-native assets.

Workflow

1. Ground the repository

Inspect package manager/scripts, frontend framework and routes, styling/token conventions, screenshot tooling, and reusable components. Choose stack-specific commands only when repository evidence supports them.

2. Establish a reference

For a live URL, capture or document an artifact containing source URL and permission/scope, viewport(s), route/state, seed/login assumptions, baseline screenshot path or capture command, visible-control parity notes, and exclusions (backend/API/auth, personalized data, crawling, third-party widgets).

For a generated concept, use $imagegen with classification ui-mockup, viewport/aspect ratio, surface, layout hierarchy, typography, color mood, exact text, no logos/watermarks/unrequested marks, and readable/feasible UI details. In OMX runtime, queue the continuation checkpoint before the built-in image tool:

omx imagegen continuation <session-id> --artifact <slug-or-filename> --generated-dir "$CODEX_HOME/generated_images/<session>" --work-dir ".omx/artifacts/visual-ralph/<slug>"

Copy the approved reference into .omx/artifacts/visual-ralph/<slug>/reference.png; do not leave it only under $CODEX_HOME/generated_images.

3. Approval gate

Stop after generation or URL capture and obtain approval of one reference image/state (or a targeted regeneration/capture adjustment). Before approval, do not implement or invoke $ultragoal. After approval, the image/baseline is the visual source of truth; major pivots require an explicit user request.

4. Hand off to $ultragoal

Pass the approved reference/baseline, URL and permission note when applicable, viewport/content state, interaction parity and exclusions, user description, detected frontend context, screenshot command/viewport, and the completion checklist. The active Ultragoal execution lane edits, runs, captures, and iterates after approval until matched or blocked.

5. Verdict before every edit

For each iteration, capture the current screenshot with viewport/state, run Visual Ralph verdict (using vision when needed), and treat its JSON as authoritative. If score < 90, turn differences[] and suggestions[] into the next edit plan and rerun before editing. Required verdict keys: score, verdict, category_match, differences[], suggestions[], reasoning.

6. Secondary diff evidence

Use pixel diff/pixelmatch overlays only to locate hotspots and translate them into edits; they never replace the verdict. Record final reference, screenshot, and diff artifacts for auditability.

7. Reusable design system

Encode the match in existing repo-native CSS variables, theme tokens, config, component variants, stories, or DESIGN.md updates. Capture applicable colors, spacing, typography/weights, radii, shadows/elevation, and important variants/states. Extend existing patterns rather than adding a parallel layer.

Completion evidence and stop conditions

Do not declare done until the approved reference/baseline and reproduction command (viewport, route, state, output path) are saved; final verdict is >= 90; secondary diff evidence is recorded; reusable tokens/components exist; equivalent build/lint/test verification passes; no unapproved pivot occurred; and remaining differences are documented. Stop at the approval gate or report a concrete blocker when evidence cannot satisfy these conditions.

Handoff template

$ultragoal "Implement the approved frontend reference.
Reference: <workspace reference or URL-derived artifact>
Source URL and permission/scope: <when applicable>
Viewport/content state: <viewport, route/state, seed/login assumptions>
Interaction parity and exclusions: <visible controls and known limits>
Route/surface: <route or component>
Screenshot command: <command and viewport>
Run Visual Ralph verdict before every next edit; pass threshold >= 90.
Use pixel diff only as secondary evidence.
Extract reusable tokens/components for colors, spacing, typography, radii, shadows, and variants.
Run the repository's equivalent verification before completion.
Do not make major design pivots unless explicitly requested."

Task: {{ARGUMENTS}}

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Clean up working code by identifying duplication, dead code, unnecessary layers, and error paths that hide failures. Preserve behavior with targeted tests, simplify the requested files in stages, and report verification results and remaining risks.

中文简介正在准备中。当前显示英语简介。

  • Simplify bloated or repetitive AI-generated code
  • Remove unused code and unnecessary wrappers
  • Review fallback paths that hide errors
Yeachan-Heo/oh-my-codex3.4万2026年10月20日 更新

analyze

免费

Investigate repository behavior, architecture, or possible causes without changing files. Trace relevant code and supporting material, then rank explanations by evidence and confidence, with concrete file references and clear distinctions between observations, conclusions, and unresolved questions.

中文简介正在准备中。当前显示英语简介。

  • Investigate possible causes of a bug
  • Understand behavior across multiple files
  • Explain architecture and tradeoffs
Yeachan-Heo/oh-my-codex3.4万2026年10月20日 更新

ask

免费

Ask Claude or Gemini through a locally installed command-line tool for focused questions, reviews, brainstorming, or second opinions. Save the prompt, original response, summary, and next steps in a reusable Markdown file.

中文简介正在准备中。当前显示英语简介。

  • Get a second opinion on a proposed approach
  • Ask Claude or Gemini to review work
  • Save brainstorming results for later use
Yeachan-Heo/oh-my-codex3.4万2026年10月20日 更新

autopilot

免费

Take an idea or issue through requirements clarification, reviewed planning, implementation, and verification. Supervise all stages in one recoverable OMX workflow, preserving artifacts and progress so work can resume or return to planning when findings require changes.

中文简介正在准备中。当前显示英语简介。

  • Deliver an issue from requirements clarification through verification
  • Turn an initial idea into a reviewed implementation plan
  • Resume interrupted work from its saved phase
Yeachan-Heo/oh-my-codex3.4万2026年10月20日 更新

Run a persistent research workflow with a defined goal and explicit acceptance checks. It saves progress and finishes only when a recorded result passes either a validation script or an architect review of the research output.

中文简介正在准备中。当前显示英语简介。

  • Research with explicit acceptance criteria
  • Verify research results with a script
  • Require review approval before completing research
Yeachan-Heo/oh-my-codex3.4万2026年10月20日 更新

Find the replacement for a research command removed in OMX 0.21. This migration notice directs existing autoresearch-goal usage to $autoresearch, the canonical research loop that requires validation before proceeding.

中文简介正在准备中。当前显示英语简介。

  • Check the replacement for a removed research command
  • Update requests to use $autoresearch
  • Confirm which command owns the research mission lifecycle
Yeachan-Heo/oh-my-codex3.4万2026年10月20日 更新

查看 Yeachan-Heo 的全部技能

报告此技能的问题