frontend-dev

Full-stack frontend development combining premium UI design, cinematic animations, AI-generated media assets, persuasive copywriting, and visual art. Builds complete, visually striking web pages with real media, advanced motion, and compelling copy. Use when: building landing pages, marketing sites, product pages, dashboards, generating media assets (image/video/audio/music), writing conversion copy, creating generative art, or implementing cinematic scroll animations.

Quality

86%

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

Quality

Content

85%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 well-architected multi-capability skill: highly actionable, with a clearly sequenced workflow that includes validation checkpoints and feedback loops, and excellent progressive disclosure that externalizes detail into a clean bundle. The main weakness is conciseness — the Copywriting section re-teaches concepts Claude already knows and the body is long.

Suggestions

Compress section 4 (Copywriting): replace the AIDA/PAS/FAB template blocks and headline/emotional-trigger/objection tables with a one-line pointer to a new references/copywriting-guide.md, keeping only the CTA formula and proof-types inline.

Trim the Creative Arsenal table (1.6) to the highest-value patterns or move the full list into references, since Claude can enumerate most of these on demand.

De-duplicate asset organization (it appears in both the 'Skill Structure' tree and the 'Project Structure / Assets' section) to recover tokens.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly directive, but the Copywriting section re-explains frameworks Claude already knows (AIDA/PAS/FAB templates, headline-formula tables, emotional-trigger and objection-handling tables) and the overall length (~575 lines) could be tightened, matching the 'mostly efficient but includes some unnecessary explanation' anchor rather than the lean anchor 5.	3 / 5
Actionability	Highly actionable throughout: concrete Tailwind classes, exact spring configs (stiffness/damping values), specific banned patterns, install commands, named scripts with sync/async patterns, and preset specs — copy-paste-ready guidance covering the common cases, matching the top anchor.	5 / 5
Workflow Clarity	A clear 6-phase sequence with explicit validation checkpoints (user confirmation before asset generation, 'do NOT proceed to Phase 5 until all assets are saved locally') and a final Quality Gates checklist with grep-based feedback loops, matching the anchor for clear sequence with explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	SKILL.md acts as an overview with well-signaled one-level-deep references ('See references/motion-recipes.md for full code. Summary:'), detail correctly externalized into 10 reference files plus scripts and templates, and the 48KB voice catalog kept out of the body — matching the clear-overview anchor.	5 / 5
	Total	18 / 20 Passed

Description

88%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, third-person description that clearly states both what the skill does and when to use it, with rich natural trigger terms and concrete capabilities. The only gap is the absence of file extensions and a few synonyms that would push trigger-term quality to the top anchor.

Suggestions

Add file-extension trigger terms (e.g. '.webp', '.mp4', '.mp3', '.html') and synonyms to the 'Use when' clause to reach comprehensive trigger coverage.

Tighten the opening 'Full-stack frontend development combining...' to lead with the most distinctive action (building complete pages with generated media + motion) to further reduce overlap with generic web-dev skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — premium UI design, cinematic animations, AI-generated media (image/video/audio/music), persuasive copywriting, generative art — and concrete build actions ('Builds complete, visually striking web pages with real media, advanced motion'), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what ('Full-stack frontend development combining... Builds complete, visually striking web pages...') and when ('Use when: building landing pages, marketing sites...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural keyword coverage ('landing pages, marketing sites, product pages, dashboards, generating media assets, conversion copy, generative art, cinematic scroll animations') that users would actually say, but missing file extensions and some synonyms, so it sits just below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The combination of AI media generation, generative art, and cinematic motion is a fairly distinct niche with clear triggers, though broad 'frontend development' phrasing creates minor overlap risk with general web-dev skills, placing it just below anchor 5.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (599 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/minimax/frontend-dev/SKILL.md
Commit: 030c20b

Reviewed: 1 day 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.