ui-craftsman

Use this skill when the user wants to generate UI, build a design system, clone a site's aesthetic, or browse the community UI gallery. Triggers on /ui-ref, /ui-show, /ui-system, /ui-share, or natural-language requests naming a reference site.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

68%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.

A compact, actionable skill body with clearly sequenced multi-mode workflows and good use of a scripts/ bundle for detail. The main weakness is Mode 3's batch file generation into the project directory lacking validation against overwrites.

Suggestions

Add a pre-write check in Mode 3 (e.g., confirm or back up existing tokens.css/Button.tsx/README.md before overwriting) and a post-generation verification step so the batch write is not destructive.

Define the 'aesthetic classes' used for direction-B/C/D in a references/ file and link to it, or enumerate them inline so Mode 2 is fully deterministic.

Consolidate the repeated 'include the localhost preview URL and describe what is visible' guidance into the 'During a Session' section rather than restating it per mode.

Dimension	Reasoning	Score
Conciseness	Largely lean and directive with numbered steps and no padding about React/Playwright basics, though the 'include the localhost URL / describe what is visible' guidance is restated across multiple sections and could be consolidated.	4 / 5
Actionability	Concrete executable commands with full paths (validate.py, extract.py, serve.py, share.py) and specific outputs, but a few gaps remain such as the undefined '<hash>' and the vague 'aesthetic classes based on description' for direction-B/C/D.	4 / 5
Workflow Clarity	Workflows are well sequenced with URL validation and an iterate-on-feedback loop in Mode 1, but Mode 3 batch-writes eight files (tokens.css, components/*.tsx, README.md) into the user's project directory with no pre-check against overwriting or post-generation verification, so the destructive/batch cap holds this at 3.	3 / 5
Progressive Disclosure	Body is a well-sectioned overview that points to the scripts/ bundle by path and defers full share.py args to '--help', but the aesthetic-class catalog referenced by Mode 2 has no dedicated reference file and is only partially inlined.	4 / 5
	Total	15 / 20 Passed

Description

92%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.

A strong, specific description that clearly states both capabilities and trigger conditions with concrete slash commands and natural-language cues. Minor room to add a few more synonyms for UI-generation requests.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions — 'generate UI', 'build a design system', 'clone a site's aesthetic', 'browse the community UI gallery' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (generate UI / build design system / clone aesthetic / browse gallery) and when ('Triggers on /ui-ref, /ui-show... or natural-language requests naming a reference site') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage with explicit slash-command triggers (/ui-ref, /ui-show, /ui-system, /ui-share) plus natural terms like 'reference site' and 'design system', though common synonyms like 'mockup' or 'wireframe' are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche in aesthetic cloning and design-system synthesis with distinct slash-command triggers, giving minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ProwlrBot/prowlr-marketplace
Path: skills/ui-craftsman/SKILL.md
Commit: 32f0050

Reviewed: 3 days 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.