CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/minimax/frontend-dev/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 delivers highly concrete, executable design and motion guidance wrapped in a well-sequenced workflow with genuine validation gates. Its weaknesses are the inlined copywriting material and redundant per-framework directory trees that pad the token budget, and the missing templates/ and canvas-fonts/ directories that the Visual Art workflow depends on.

Suggestions

Add the missing templates/ (viewer.html, generator_template.js) and canvas-fonts/ files to the bundle, or remove the §5 references to them — the interactive-mode workflow currently instructs reading a file that does not exist.

Move the copywriting frameworks (AIDA/PAS/FAB explanations, headline formulas, emotional triggers, objection handling) into a references/copywriting.md file and keep only the framework selection rule and CTA formula inline, cutting a large block of knowledge Claude already has.

Collapse the five per-framework directory trees into the existing single framework table (framework → asset location → component location) to remove the duplicated structural boilerplate.

DimensionReasoningScore

Conciseness

The design and motion sections are dense and assume Claude's competence (exact Tailwind classes, spring configs, easing curves), but the ~580-line body includes content Claude already knows — full AIDA/PAS/FAB framework explanations, headline formula tables, and five near-duplicate per-framework directory trees — which is more than the minor trimming of anchor 4.

3 / 5

Actionability

Largely executable guidance: concrete spring configs ("stiffness: 300, damping: 30"), easing values, install commands, asset naming patterns ("{type}-{descriptor}-{timestamp}.{ext}"), and a real script bundle with a required env var. A few steps remain abstract ("Craft optimized prompts") and the main build flow has no inline code, so it falls short of fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

Six sequenced phases with explicit validation checkpoints ("MUST confirm before generating", "do NOT proceed to Phase 5 until all assets are saved locally") and a terminal Quality Gates checklist containing a feedback loop ("grep the output... If ANY found, STOP and replace with generated assets before delivering"), matching the top anchor.

5 / 5

Progressive Disclosure

References are one level deep and well-signaled ("read as needed", the §3.4 reference list, the §2.3 pointer to motion-recipes.md) and the structure tree matches the actual bundle — but the body instructs "Read templates/viewer.html first" and references canvas-fonts/, and neither templates/ nor canvas-fonts/ exists in the bundle, breaking §5's interactive mode. Missing referenced paths plus inlined content that could live in references place this at the some-structure anchor rather than the good-structure one.

3 / 5

Total

15

/

20

Passed

Description

83%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 description that clearly states what the skill does and when to use it, with a well-constructed trigger list covering the five capability pillars. Slightly held back by buzzword-leaning capability language and missing common synonyms in the trigger terms.

DimensionReasoningScore

Specificity

Names the domain and lists several specific capabilities ("premium UI design, cinematic animations, AI-generated media assets, persuasive copywriting, and visual art"; "Builds complete, visually striking web pages"), though these read as capability areas rather than concrete operations and include mild buzzwords ("premium", "visually striking"), keeping it below the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both what ("Builds complete, visually striking web pages with real media, advanced motion, and compelling copy") and when via a concrete "Use when:" clause enumerating trigger scenarios, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Good natural-keyword coverage ("landing pages, marketing sites, product pages, dashboards", "generating media assets (image/video/audio/music)", "writing conversion copy", "cinematic scroll animations"), but common synonyms like "website", "homepage", "hero section", or "TTS/text-to-speech" are missing, so it does not reach the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The AI media-generation and generative-art angle is a clear niche with distinct triggers, but generic web-dev triggers like "dashboards" and "landing pages" create minor overlap risk with general frontend skills, so it sits just below minimal-conflict.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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
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.