CtrlK
BlogDocsLog inGet started
Tessl Logo

visual-ralph

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

63

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/oh-my-codex/skills/visual-ralph/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, actionable orchestration skill with a strong sequenced workflow, explicit validation checkpoints, a verdict feedback loop, and a copy-paste handoff template. It is efficient and free of padded explanation, with only minor verbosity and optional file-splitting opportunities.

DimensionReasoningScore

Conciseness

Efficient overall and free of concepts Claude already knows; every section is operational. Minor over-explanation remains, e.g., the OMX continuation-helper rationale paragraph and the near-duplicate '$web-clone is hard-deprecated' reminder.

4 / 5

Actionability

Provides concrete, mostly executable guidance — an executable `omx imagegen continuation` command, a copy-paste handoff template with placeholders, a required verdict shape, and a numeric threshold (score < 90). Minor gaps: template placeholders must be filled and several steps delegate to other skills' behavior.

4 / 5

Workflow Clarity

A clearly sequenced 7-step workflow with explicit validation checkpoints — a user-approval gate before implementation, a verdict-before-every-edit feedback loop (score < 90 -> edit plan -> rerun), and a completion checklist with pass criteria (verdict >= 90, build/lint/test).

5 / 5

Progressive Disclosure

No bundle files exist, so this is a single-file skill; it is well-organized into clearly headed sections (Purpose, Use when, Do not use when, Workflow, Completion checklist, Handoff template) with easy navigation. It is a moderately long monolithic file, and the handoff template/checklist could optionally live in separate references.

4 / 5

Total

17

/

20

Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, third-person, and distinctive, naming a clear orchestration niche with several concrete actions. Its main weakness is the absence of any explicit 'Use when' trigger guidance, which limits completeness.

Suggestions

Append a 'Use when...' clause naming concrete user triggers (e.g., 'Use when the user wants to build or restyle frontend UI from a generated mockup, static reference image, or live URL, with measured visual matching').

Add natural synonyms users actually say — 'mockup', 'screenshot', 'clone', 'website' — to broaden trigger coverage.

Briefly distinguish from sibling skills (e.g., note that live-URL cloning is owned here rather than by $web-clone) to reduce overlap ambiguity.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'orchestration for frontend UI', 'using $ralph with built-in visual verdict and pixel-diff evidence', 'leaves a reproducible design system' — with only minor gaps (the approval gate and iteration loop are not surfaced in the description).

4 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Good natural keyword coverage ('frontend UI', 'live URL', 'generated references', 'static references', 'design system', 'build or restyle'), but a few common user phrases like 'mockup', 'screenshot', or 'clone' are absent from the description.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche ('Visual Ralph orchestration', '$ralph', visual verdict + pixel-diff loop) but has minor overlap risk with closely related sibling skills ($ralph, $imagegen, $web-clone, $design) that the description does not fully disambiguate.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Yeachan-Heo/oh-my-codex
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.