visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict…
Skill by Yeachan-Heo
Chalk Labs
Need help deploying visual-ralph?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/yeachan-heo-visual-ralph-addd68
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, frontend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
visual-ralph- Description
- Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
- License
- MIT
- Instructions
- 80 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: templates/AGENTS.md
Files (1)
- SKILL.md
SKILL.md (first lines)
# Visual Ralph Skill
Use `$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 `$web-clone`.
Shared operating, delegation, state, hook, team, cancellation, and verification invariants live in [`templates/AGENTS.md`](../../templates/AGENTS.md). Follow that source instead of duplicating its rules here.
## Use when
- The user wants a web/app UI built or restyled against a visual target.
- A live URL or generated raster mockup needs measured implementation and pixel-level iteration.
- The result must leave reusable repo-native tokens/components, not only a matching screenshot.
Do not use it for a durable `DESIGN.md` brief (`$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 `$imagegen` with classification `ui-mockup`, viewport/aspect ratio, surface, layout hierarchy, typography, color mood, exact text, no logos/watermarks/unrequested marks, and readable/feasible UI details. In OMX runtime, queue the continuation checkpoint before the built-in image tool:
```bash
omx imagegen continuation <session-id> --artifact <slug-or-filename> --generated-dir "$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
```text
$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}}From Yeachan-Heo/oh-my-codex, MIT.
More from Yeachan-Heo/oh-my-codex
- 0.849score
performance-goal
Yeachan-Heo
Run an evaluator-gated performance optimization workflow over Codex goal mode with durable OMX artifacts and safe goal handoffs.
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.847score
analyze
Yeachan-Heo
Run read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference…
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
ask
Yeachan-Heo
Ask a local external advisor CLI (Claude or Gemini) and capture a reusable artifact
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
wiki
Yeachan-Heo
Persistent markdown project wiki stored under repository omx_wiki with keyword search and lifecycle capture
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
autoresearch
Yeachan-Heo
Stateful validator-gated research loop with native-hook persistence
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
best-practice-research
Yeachan-Heo
[OMX] Bounded best-practice research wrapper using official/upstream evidence first
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
git-master
Yeachan-Heo
Git expert for atomic commits, rebasing, and history management
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
cancel
Yeachan-Heo
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
autopilot
Yeachan-Heo
[OMX] Canonical autonomous orchestrator: $deep-interview -> $ralplan -> $ultragoal
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
ultragoal
Yeachan-Heo
Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
worker
Yeachan-Heo
Team worker protocol (ACK, mailbox, task lifecycle) for tmux-based OMX teams
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.844score
visual-ralph
Yeachan-Heo
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict…
SkillAFreshness: A★ 33.6KClaude Code +9
Signals
- Stars
- 33,621
- Forks
- 2,549
- Open issues
- 1
- Last commit (this folder)
- Sep 9, 2026 (1 month ago)
- Last release
- Oct 24, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Yeachan-Heo/oh-my-codex
- Website
- oh-my-codex.dev
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from Yeachan-Heo
- 0.849score
performance-goal
Yeachan-Heo
Run an evaluator-gated performance optimization workflow over Codex goal mode with durable OMX artifacts and safe goal handoffs.
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.847score
analyze
Yeachan-Heo
Run read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference…
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
best-practice-research
Yeachan-Heo
[OMX] Bounded best-practice research wrapper using official/upstream evidence first
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
autoresearch
Yeachan-Heo
Stateful validator-gated research loop with native-hook persistence
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
git-master
Yeachan-Heo
Git expert for atomic commits, rebasing, and history management
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
cancel
Yeachan-Heo
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillAFreshness: A★ 33.6KClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get visual-ralph running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
visual-ralph skill. Agent Mart. https://agentmart.dev/skills/yeachan-heo-visual-ralph-addd68 (last updated 2026-10-24)