Source profileQuality 88/100

MoizIbnYousaf/marketing-cli/skills/visual-style/SKILL.md

visual-style

Build a persistent visual brand identity for image generation. Defines how the brand looks visually — aesthetic, lighting, composition, mood — and writes it to brand/creative-kit.md so /image-gen and other creative skills produce consistent on-brand visuals. Three modes: Extract (from website/URL), Build (interview), Reference (mood board/examples). Use when starting any project that needs images, when the user says "visual style", "brand aesthetic", "image style", "visual identity", "how should

Source repository stars
27
Declared platforms
0
Static risk flags
0
Last source update
2026-07-28
Source checked
2026-07-28

Decision brief

What it does—and where it fits

Every brand has a voice. This skill gives it eyes.

Best for

  • Use when starting any project that needs images, when the user says "visual style", "brand aesthetic", "image style", "visual identity", "how should

Not for

  • Tasks that require unconfirmed production actions or broad system permissions.
  • Environments where the pinned source and install steps cannot be inspected.

Compatibility matrix

Platform support, with evidence labels

PlatformStatusEvidenceWhat to check
CodexNot declaredNo explicit evidencePortability before use
Claude CodeNot declaredNo explicit evidencePortability before use
CursorNot declaredNo explicit evidencePortability before use
Gemini CLINot declaredNo explicit evidencePortability before use
Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource
npx skills add https://github.com/MoizIbnYousaf/marketing-cli --skill "skills/visual-style"
Safe inspection promptEditorial

Inspect the Agent Skill "visual-style" from https://github.com/MoizIbnYousaf/marketing-cli/blob/f12fbcbe4929584697b309b9096c9427b0cfce8e/skills/visual-style/SKILL.md at commit f12fbcbe4929584697b309b9096c9427b0cfce8e. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

  1. 01

    On Activation

    1. Read brand/creative-kit.md if it exists. Check for a Visual Brand Style section. - If the section exists and is populated (not template comments): Refresh mode — show current style, offer to update or replace. - If the section is template/empty: Create mode — build from scrat…

    Read brand/creative-kit.md if it exists. Check for a Visual Brand Style section.If the section exists and is populated (not template comments): Refresh mode — show current style, offer to update or replace.If the section is template/empty: Create mode — build from scratch.
  2. 02

    Mode Selection

    "How do you want to define your visual brand style?"

    Extract — I'll analyze your website or existing assets to derive the visual identityBuild — I'll interview you about your visual preferences (5-7 questions)Reference — You provide mood boards, example images, or reference URLs and I'll synthesize a style
  3. 03

    Mode 1: Extract

    The user provides a URL or set of URLs (website, landing page, social profiles).

    Use WebFetch to scrape each URL.Analyze for visual patterns:Dominant colors (map to hex codes)
  4. 04

    Mode 2: Build

    Interview the user. Ask one question at a time via AskUserQuestion.

    Minimal and clean (Apple, Stripe)Warm and human (Mailchimp, Notion)Bold and energetic (Figma, Vercel)
  5. 05

    Mode 3: Reference

    The user provides mood boards, image URLs, or descriptions of their ideal visual style.

    If URLs: use WebFetch or Read to analyze the images/pages.If descriptions: extract the key visual patterns.Synthesize into Visual Brand Style format.

Permission review

Static risk signals and limitations

No configured static risk pattern was detected

This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial
SignalValueEvidence typeMeaning
Quality score88/100ComputedDocumentation, specificity, maintenance, and trust rules
Repository stars27SourceRepository attention, not individual Skill quality
Compatibility0 platformsSourceDeclared in the catalog source record
Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository
MoizIbnYousaf/marketing-cli
Skill path
skills/visual-style/SKILL.md
Commit
f12fbcbe4929584697b309b9096c9427b0cfce8e
License
MIT
Collected
2026-07-28
Default branch
main
View the original SKILL.md

/visual-style — Visual Brand Identity Builder

Every brand has a voice. This skill gives it eyes.

Voice-profile.md defines how the brand sounds. Visual Brand Style defines how it looks — the lighting, the composition, the mood that makes someone see an image and know it's yours before reading a word.


On Activation

  1. Read brand/creative-kit.md if it exists. Check for a ## Visual Brand Style section.
    • If the section exists and is populated (not template comments): Refresh mode — show current style, offer to update or replace.
    • If the section is template/empty: Create mode — build from scratch.
    • If creative-kit.md doesn't exist: create it first with mktg init, then proceed.
  2. Read brand/voice-profile.md if it exists — personality informs visual tone (e.g., playful voice = warm/bright visuals, authoritative = clean/precise).
  3. Read brand/positioning.md if it exists — angles inform visual metaphors (e.g., "the simple alternative" = minimalist aesthetic).
  4. If no brand files exist, proceed anyway — ask the user directly. Progressive enhancement, not gating.

Mode Selection

Use AskUserQuestion:

"How do you want to define your visual brand style?"

  1. Extract — I'll analyze your website or existing assets to derive the visual identity
  2. Build — I'll interview you about your visual preferences (5-7 questions)
  3. Reference — You provide mood boards, example images, or reference URLs and I'll synthesize a style

Mode 1: Extract

The user provides a URL or set of URLs (website, landing page, social profiles).

  1. Use WebFetch to scrape each URL.
  2. Analyze for visual patterns:
    • Dominant colors (map to hex codes)
    • Typography (serif vs sans-serif, weight, spacing)
    • Photography style (studio, candid, illustration, none)
    • Layout patterns (dense, airy, grid-heavy, asymmetric)
    • Mood (corporate, playful, premium, technical, warm)
  3. Synthesize findings into the Visual Brand Style format.
  4. Present to user via AskUserQuestion: "Here's what I extracted from your site. Does this capture your visual brand, or should I adjust?"

Fallback: If WebFetch is unavailable, switch to Build mode and tell the user why.


Mode 2: Build

Interview the user. Ask one question at a time via AskUserQuestion.

Question 1: Aesthetic anchor "Pick the closest match to how your brand should look visually:"

  • Minimal and clean (Apple, Stripe)
  • Warm and human (Mailchimp, Notion)
  • Bold and energetic (Figma, Vercel)
  • Premium and dark (Linear, Raycast)
  • Editorial and photographic (Medium, Substack)
  • Something else (describe it)

Question 2: Lighting and mood "What lighting feels right for your brand's images?"

  • Warm and golden (golden hour, ambient glow)
  • Bright and airy (soft diffused, clean whites)
  • Dramatic and contrasty (rim lighting, dark backgrounds)
  • Natural and candid (daylight, real environments)
  • Neon and digital (glowing screens, dark mode)

Question 3: Composition "How should images be composed?"

  • Single focal point with lots of breathing room
  • Rich and detailed — fill the frame
  • Asymmetric and editorial — off-center subjects
  • Geometric and structured — grid-aligned elements

Question 4: What to avoid "What should your images NEVER look like?" (Free text — the user's avoidances are often more revealing than their preferences)

Question 5: Reference "Name a brand, website, or aesthetic that captures what you're going for — even if it's in a completely different industry."

Optional Question 6: Existing assets "Do you have any images that already feel on-brand? Describe them or share URLs."

Synthesize answers into the Visual Brand Style format.


Mode 3: Reference

The user provides mood boards, image URLs, or descriptions of their ideal visual style.

  1. If URLs: use WebFetch or Read to analyze the images/pages.
  2. If descriptions: extract the key visual patterns.
  3. Synthesize into Visual Brand Style format.
  4. Present for confirmation.

Output Format

Write the ## Visual Brand Style section into brand/creative-kit.md. Preserve all existing sections (Brand Colors, Typography, Visual Style). Only add/update the Visual Brand Style section.

## Visual Brand Style

- **Primary Aesthetic:** [derived aesthetic, e.g., "warm tech minimalism with editorial photography"]
- **Lighting:** [specific lighting direction, e.g., "soft diffused with rim lighting accents, warm color temperature"]
- **Backgrounds:** [background treatment, e.g., "dark slate (#0F172A) with warm accent gradients"]
- **Composition:** [layout approach, e.g., "single focal point, generous negative space for text overlay"]
- **Mood:** [emotional tone, e.g., "calm empowerment — powerful but approachable, like a quiet expert"]
- **Avoid:** [explicit exclusions, e.g., "generic stock photos, cold blue tech grids, floating 3D cubes, busy compositions"]
- **Reference Prompts:**
  1. [A proven prompt that captures the brand look — ready to paste into image gen]
  2. [A second prompt showing a different use case in the same style]
  3. [Optional third prompt for edge cases]

Reference Prompts are critical. These are the style anchors that /image-gen uses when generating on-brand images. They should be complete, narrative prompts (not keywords) that produce images distinctly this brand.


Refresh Mode

When ## Visual Brand Style already exists:

  1. Present the current style summary.
  2. AskUserQuestion: "Your visual brand style was last defined [date]. What would you like to do?"
    • Update specific fields (which ones?)
    • Rebuild from scratch
    • Add new reference prompts
    • Keep it as-is

Progressive Enhancement

LevelContextOutput quality
L0No brand filesGeneric but functional — asks user directly, writes style from scratch
L1voice-profile.md existsPersonality-aligned — playful voice gets warm visuals
L2+ creative-kit.md colors/typographyColor-constrained — prompts incorporate brand palette
L3+ positioning.mdFull alignment — visual metaphors match positioning angles

Anti-Patterns

Anti-patternWhy it failsInstead
Locking into one rigid styleBrands need versatility — a blog header and an error page shouldn't look identicalDefine the core aesthetic but include "also works for: [alternative moods]" in reference prompts
Ignoring existing creative-kit.md sectionsOverwriting colors/typography the user already defined breaks trust and loses workRead and preserve existing sections, only add/update Visual Brand Style
Generic descriptions like "modern and clean"Every brand says this — it gives image-gen nothing to work withBe specific: "warm rim lighting on dark backgrounds, single subject, f/2.0 bokeh"
Skipping the Avoid listWhat to avoid is often more distinctive than what to include — it prevents the genericAlways ask what the brand should NEVER look like
Writing keyword prompts instead of narrativeImage gen models produce better results from flowing descriptions than comma-separated termsReference prompts should read like a scene description, not a tag list

Related Skills

  • /image-gen — reads the Visual Brand Style this skill creates to generate on-brand images
  • /brand-voice — builds the verbal identity; visual-style builds the visual identity
  • /creative — produces multi-mode creative briefs that reference creative-kit.md
  • /paper-marketing — designs in Paper MCP using creative-kit.md for design system

Alternatives

Compare before choosing

Computed 1007

event4u-app/agent-config

design-intelligence

Grounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.

Computed 9827

MoizIbnYousaf/marketing-cli

higgsfield-generate

Use when the user wants to generate an image or video via Higgsfield AI. Covers 30+ models: Soul V2, Seedance 2.0, Kling 3.0, Veo 3.1, GPT Image 2, Nano Banana 2. Also covers Marketing Studio — branded ad video/image with avatars and products. Use whenever: "generate an image", "make a video", "animate this photo", "image-to-video", "img2vid", "edit this image with AI", "produce a clip", "create an ad", "make a UGC video", "marketing video", "brand video", "TV spot", "import product from URL", "

Computed 9727

MoizIbnYousaf/marketing-cli

creative

Generate visual asset briefs, ad copy variants, AI image prompts, video scripts, and storyboards. Full creative production system with 5 specialized modes: product photos, product video, social graphics, talking heads, and ad creative. Make sure to use this skill whenever the user mentions any visual or creative marketing need — ad creative, image prompts, video scripts, thumbnails, banners, social graphics, product photography, storyboards, or marketing visuals of any kind. Even if they just sa

Computed 9542,015

coreyhaines31/marketingskills

site-architecture

When the user wants to plan, map, or restructure their website's page hierarchy, navigation, URL structure, or internal linking. Also use when the user mentions "sitemap," "site map," "visual sitemap," "site structure," "page hierarchy," "information architecture," "IA," "navigation design," "URL structure," "breadcrumbs," "internal linking strategy," "website planning," "what pages do I need," "how should I organize my site," or "site navigation." Use this whenever someone is planning what page