imagegen-frontend-mobile

Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code.

Quality

50%

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 ./skills/imagegen-frontend-mobile/SKILL.md

Quality

Content

35%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 comprehensive in intent but heavily padded and repetitive, with abstract direction instead of executable prompts and no bundle/reference files to offload the large rule, config, and checklist content. It would benefit substantially from compression and progressive disclosure.

Suggestions

Collapse the repeated directives (readability, palette, consistency, no box-in-box, mockup framing) into a single canonical section and remove the restatements across sections 7/15/23/29/30/31/35/38 to recover token budget.

Move the ACTIVE BASELINE CONFIGURATION table, the full STYLE VARIATION ENGINE option lists, the 27-item QUALITY CHECK, and the EXAMPLE INTERPRETATIONS into separate reference files under references/ and link to them, improving progressive_disclosure.

Add at least one concrete, copy-paste-ready image-generation prompt template (with the locked design-bible variables filled) and an explicit validate-then-regenerate feedback checkpoint in section 36 to raise actionability and workflow_clarity.

Dimension	Reasoning	Score
Conciseness	At ~1465 lines the body is noticeably verbose and repetitive — the same directives (keep text readable, clean palette, consistency, no box-in-box) are restated across sections 7/15/23/29/30/31/35/38 — adding many tokens that do not earn their place beyond what Claude already understands about good mobile design.	2 / 5
Actionability	The skill gives high-level image-direction hints rather than concrete, executable steps; there is no copy-paste-ready prompt template, parameter spec, or worked generation command, only abstract directives like 'generate multiple screens' and 'lock an internal design bible'.	2 / 5
Workflow Clarity	Section 36 lists a clear 28-step response sequence and section 35 a 27-item quality checklist, giving a present sequence, but for a generative-image (batch) workflow there is no validate-then-fix feedback loop checkpoint — it only says 'regenerate if not strong enough', leaving checkpoints implicit.	3 / 5
Progressive Disclosure	The single SKILL.md is monolithic with 38 inline sections (config table, full style-variation engine, all examples, the full checklist) that clearly belong in separate reference files, yet no bundle files exist and there are no outbound references to split the load, so structure is present but organization is inline rather than disclosed.	3 / 5
	Total	10 / 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 and well-bounded with a clear what-not boundary, but lacks an explicit 'Use when...' trigger clause, which caps its completeness. Trigger-term coverage is good but could add common synonyms like 'mockups' and 'UI screens'.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks for mobile app screen mockups, app UI concepts, or multi-screen mobile flows' to lift completeness above 3.

Add common natural synonyms like 'mockups', 'UI screens', and 'app design' to broaden trigger-term coverage.

Reframe the priority list as discrete actions (e.g. 'Generate premium mobile screen images, design multi-screen app flows, apply controlled color palettes') to strengthen specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas — 'creating premium, app-native screen concepts and flows', 'controlled color palettes', 'textured surfaces', 'image-led composition', 'tasteful custom iconography', and 'clean phone mockup framing' — though they are framed as priorities rather than discrete actions, leaving minor coverage gaps.	4 / 5
Completeness	The 'what' is clear (premium mobile app screen/flow image generation), but there is no explicit 'Use when...' trigger clause; the 'when' is only weakly implied by 'Designed for iOS, Android, and cross-platform mobile products', which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Includes strong natural terms users would say — 'mobile app', 'screen concepts and flows', 'iOS', 'Android', 'onboarding/flows' — but is missing common synonyms like 'mockups', 'UI screens', or 'app design', so a few natural terms are absent.	4 / 5
Distinctiveness Conflict Risk	The explicit 'This skill generates images only. It does not write code.' boundary plus mobile-specific framing gives it a clear niche distinct from web/frontend/code skills, with only minor overlap risk against generic image-generation skills.	4 / 5
	Total	15 / 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
skill_md_line_count	SKILL.md is long (1466 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Leonxlnx/taste-skill
Path: skills/imagegen-frontend-mobile/SKILL.md
Commit: e79ca9e

Reviewed: 5 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.