design-first-ui-prompting

Use when you need design-first, spec-driven, skimmable prompts for UI generation. Covers prompt structure, constraints, variations, typography/spacing rules, and iteration workflow for consistent UI outputs.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent-skills/ui/design-first-ui-prompting/SKILL.md

Quality

Content

75%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 skill body is a tight, actionable prompt-building kit with clear structure and a sensible iteration workflow. It would benefit from one or two fully filled example prompts and more explicit iteration checkpoints to push actionability and workflow clarity higher.

Suggestions

Add one fully filled example prompt (GOAL/FORMAT/LAYOUT/.../CONSTRAINTS) so users can see the skeleton completed end-to-end, not just as blanks.

Make the iteration checkpoints explicit, e.g. 'After each variant: compare against the first output and confirm only ONE variable changed.'

Note where reference images/prompts are stored (the 'local reference pack' mentions refs/...) and consider an example directory layout for discoverability.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — a copy/paste prompt skeleton, terse rules, and checklists with no padded concept explanations — with only minor instances (e.g., restating 'Prompt like a design system, not a wish') that could be trimmed.	4 / 5
Actionability	Provides a fill-in-the-blanks prompt template, an example constraints card, and a concrete 2-pass workflow; it is executable guidance, though the template leaves blanks the user must reason through rather than fully copy-paste-ready examples.	4 / 5
Workflow Clarity	Sequences a clear iteration workflow — lock the system, change ONE variable at a time, 2-pass typography fix — with a tweak checklist; no destructive/batch operations so the validation cap does not apply, but explicit checkpoints are implicit rather than spelled out.	4 / 5
Progressive Disclosure	Well-organized sections (structure, rules, checklist, questions) at one level with no nested references; no bundle files exist to offload, so the inline content is appropriately placed with only minor gaps versus an ideal overview-to-detail split.	4 / 5
	Total	16 / 20 Passed

Description

80%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 clearly and concisely states what the skill does and when to use it, with a distinct niche and concrete coverage areas. Its main weakness is trigger-term coverage, which leans on jargon rather than the natural phrasings a user would utter.

Suggestions

Add natural user phrasings to the trigger, e.g. 'Use when the user asks to design a screen, mockup, or hero UI and wants consistent, repeatable outputs.'

Include common synonyms like 'UI mockup', 'screen design', or 'design system prompt' so it surfaces for varied requests.

Dimension	Reasoning	Score
Specificity	Lists several concrete elements — 'prompt structure, constraints, variations, typography/spacing rules, and iteration workflow' — but describes a domain/structure rather than discrete actions, leaving minor gaps versus the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both what ('design-first, spec-driven, skimmable prompts for UI generation...') and when ('Use when you need design-first, spec-driven, skimmable prompts for UI generation') with a concrete trigger clause.	5 / 5
Trigger Term Quality	Contains relevant terms like 'UI generation', 'prompts', 'constraints', and 'variations', but lacks the natural synonyms a user would say ('make a UI mockup', 'design a screen') and file-extension-style variations, so coverage is partial.	3 / 5
Distinctiveness Conflict Risk	'Design-first, spec-driven, skimmable prompts for UI generation' carves a clear niche unlikely to trigger for generic UI coding or general prompting skills, with minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MengTo/Skills
Path: agent-skills/ui/design-first-ui-prompting/SKILL.md
Commit: 9fb3bfb

Reviewed: 4 hours ago

Table of Contents

Discovery Implementation Validation

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.