Vibeship-spawner-skills ai-brand-kit

id: ai-brand-kit

install

source · Clone the upstream repo

git clone https://github.com/vibeforge1111/vibeship-spawner-skills

manifest: marketing/ai-brand-kit/skill.yaml

Directory Structure

/prompts /visual /social-media instagram-post-v2.md linkedin-header-v1.md /marketing hero-image-v3.md product-shot-v1.md /copy /social twitter-thread-v4.md linkedin-post-v2.md /email welcome-sequence-v1.md newsletter-v3.md /brand-checking visual-consistency-v1.md voice-consistency-v2.md

Prompt Template Format

# [Use Case] - v[Version]

## Purpose
[What this generates and why]

## Base Prompt
[Core reusable prompt text]

## Variables
- {PRODUCT}: [Description/example]
- {TONE}: [Options: professional|casual|urgent]
- {CTA}: [Call to action text]

## Brand Context
[Auto-injected brand guidelines]

## Negative Prompts
[What to explicitly avoid]

## Quality Benchmarks
- Reference 1: [Link to gold standard example]
- Reference 2: [Link to gold standard example]

## Usage Examples
[3-5 filled examples with results]

## Changelog
- v2 (2024-03): Added negative prompts for gradient avoidance
- v1 (2024-01): Initial version

Version control in git. Tag major versions. Deprecate outdated prompts.

name: Visual Style Tuning Workflow when: Training AI image generators on your brand aesthetic steps:
- step: Curate brand anchor image set details: | Select 15-25 existing brand images that best capture your aesthetic. Include variety: product shots, lifestyle, graphics, UI screenshots. Each image should be high quality and clearly "on brand."
  
  Avoid: Stock photos, inconsistent styles, outdated assets.
- step: Create Midjourney style reference details: | Upload anchors to Midjourney. Use --sref parameter with image URLs. Test with 20+ diverse prompts to validate consistency. Document which sref values (0-1000) work best for your brand.
  
  Example:
```
--sref https://brand.com/anchor1.jpg --sref 500
```
- step: Build DALL-E custom style details: | Use ChatGPT's DALL-E with detailed style instructions. Create Custom GPT with embedded brand guidelines. Include negative prompts in system instructions. Test across 10+ content types.
- step: Train Flux LoRA (advanced) details: | For maximum control, train Flux LoRA on 50-100 brand images. Requires technical setup but gives fine-grained style control. Host on Replicate or RunPod for team access. Version LoRA models by training date.
- step: Document prompt patterns details: | Record which prompt structures work best for your style. Note effective keywords, compositions, lighting terms. Build reusable prompt templates. Create negative prompt library.
- step: Establish quality gates details: | Define what "on brand" means measurably. Create comparison grid with gold standards. Set approval workflow for new AI assets. Track style drift over time.
name: Voice Training Methodology when: Teaching AI to write in your brand voice across contexts steps:
- step: Gather voice corpus details: | Collect 50-100 examples of your best brand writing. Organize by context: social, email, docs, ads, support. Include variety: short/long, formal/casual, urgent/evergreen.
  
  Quality over quantity but need volume for pattern detection.
- step: Extract voice patterns details: | Use Claude/GPT to analyze corpus and identify:
  - Sentence structure patterns (short/long, simple/complex)
  - Common opening/closing patterns
  - Recurring phrases or formulations
  - Punctuation style (em-dashes, semicolons, etc.)
  - Vocabulary level and technical density
  - Use of questions, imperatives, statements
  Create structured voice profile document.
- step: Build context-specific prompts details: | Don't use generic "brand voice" - create prompts for each context:
  - Twitter: [Voice characteristics + platform constraints]
  - Email newsletter: [Voice + format + CTA patterns]
  - Product docs: [Voice + clarity + technical level]
  - Support: [Voice + empathy + problem-solving]
  - LinkedIn: [Voice + professionalism + thought leadership]
  Each prompt embeds relevant corpus examples.
- step: Create anti-voice guidelines details: | Explicitly state what NOT to write:
  - Forbidden phrases: "delighted to announce", "game-changer"
  - Banned structures: "In today's world of X..."
  - Tone violations: Corporate jargon, excessive exclamations
  Negative examples teach as much as positive ones.
- step: Build Custom GPT / Claude Project details: | Create dedicated AI assistant with:
  - System instructions with voice guidelines
  - Corpus examples in knowledge base
  - Context-specific prompt templates
  - Brand terminology glossary
  Train team to use this vs generic ChatGPT.
- step: Quality benchmark and iterate details: | Generate 20+ examples across contexts. Compare against corpus gold standards. A/B test with team: "Which sounds more like us?" Refine prompts based on misses. Version voice guidelines as brand evolves.
name: Asset Variation System when: Need to generate multiple on-brand variations efficiently structure: | Build system for controlled variation within brand constraints:

Variation Dimensions

Define what CAN vary while staying on brand:
- Color: Primary palette variations, accent swaps
- Composition: 3-4 approved layout structures
- Imagery: Style-consistent image categories
- Copy: Tone spectrum by context (formal ↔ casual)
- Format: Dimensions/aspect ratios by channel
Constraint System

Define what MUST stay consistent:
- Logo usage and clear space
- Typography hierarchy and font pairings
- Voice principles (even as tone varies)
- Visual style references (same aesthetic DNA)
Variation Prompts

Create prompts with controlled randomness:
```
Generate Instagram post with:
- Style: {BRAND_STYLE_REF}
- Color: {random: primary_palette}
- Composition: {random: [layout_1, layout_2, layout_3]}
- Subject: {PRODUCT}
- Must include: {BRAND_ELEMENTS}
- Never include: {BRAND_NEGATIVES}
```
Batch Generation

Use variation prompts to generate 10-20 options. Team selects best 2-3. Refine winners. Archive losers.

Version Control

Track which variations perform best. Retire low performers from rotation. Update prompts based on learnings.

name: Brand Consistency Checker when: Validating AI-generated content meets brand standards implementation: | Create AI-powered brand validation system:

Visual Consistency Checker

Prompt for image validation:

You are a brand consistency validator for {BRAND}.

Brand Guidelines:
- Color palette: {COLORS}
- Typography: {FONTS}
- Visual style: {STYLE_DESCRIPTION}
- Must avoid: {NEGATIVES}

Analyze this image and check:
1. Color usage: In palette? Proportions correct?
2. Typography: Approved fonts? Proper hierarchy?
3. Style: Matches brand aesthetic? Reference images?
4. Violations: Any forbidden elements?
5. Overall: Brand-aligned? (1-10 score)

Output: Pass/Fail + specific issues + suggestions

Copy Consistency Checker

Prompt for text validation:

You are a brand voice validator for {BRAND}.

Voice Guidelines:
- Tone: {TONE_DESCRIPTION}
- Forbidden phrases: {BLOCKLIST}
- Example corpus: {EXAMPLES}

Analyze this copy:
"{TEXT_TO_CHECK}"

Check:
1. Voice match: Sounds like brand? (1-10)
2. Forbidden phrases: Any violations?
3. Tone appropriateness: Right for {CONTEXT}?
4. Improvements: Specific suggestions to strengthen

Output: Pass/Fail + issues + rewrite suggestions

Automated Workflow

Integrate checkers into approval flow:

AI generates content
Auto-run consistency checker
If Pass: Send to human review
If Fail: Show issues, suggest fixes, regenerate
Track failure patterns to improve base prompts

Feedback Loop

When humans override checker (approve "fails" or reject "passes"), capture feedback to refine validation prompts.

name: Multi-Channel Brand Deployment when: Launching brand across multiple AI-powered channels strategy: | Coordinate consistent brand rollout across AI touchpoints:

Channel Inventory

Map all AI-enabled brand touchpoints:
- Social: Twitter/X, LinkedIn, Instagram, TikTok
- Email: Newsletters, campaigns, transactional
- Content: Blog, docs, landing pages
- Support: Chatbots, help articles, FAQs
- Ads: Google, Meta, LinkedIn
- Internal: Slack bots, notion, docs
Context Mapping

For each channel, define:
- Voice variation: How does brand tone adapt?
- Visual requirements: Dimensions, format, style
- Prompt templates: Channel-specific generation prompts
- Quality benchmarks: Gold standard examples
- Approval workflow: Who reviews before publish?
Rollout Sequence

Don't launch everywhere simultaneously:
1. Start with 1-2 high-impact channels
2. Generate 20+ examples, refine prompts
3. Run for 2-4 weeks, gather feedback
4. Update prompts based on learnings
5. Expand to next channel tier
6. Cross-pollinate learnings
Consistency Monitoring

As you scale across channels:
- Weekly brand audits across channels
- Track style drift metrics
- User perception surveys
- A/B test variations within brand
- Update central brand guidelines
- Sync prompt libraries across channels

name: Brand Evolution Management when: Brand needs to evolve while maintaining AI consistency process: | Manage brand changes without breaking AI systems:

Version Your Brand

Treat brand like code:

v1.0: Initial brand launch
v1.1: Minor refinements (color tweaks, voice adjustments)
v2.0: Major evolution (rebrand, new positioning)

Changelog Everything

Document what changed and why:

# Brand v2.0 - March 2024

## Visual Changes
- Updated color palette: Warmer tones (old cold blues)
- New typography: Inter → Geist Sans
- Simplified logo: Removed gradient

## Voice Changes
- Tone: More conversational, less corporate
- Removed: Jargon, buzzwords
- Added: Humor, personality

## AI Impact
- Update all Midjourney srefs with new color palette
- Retrain DALL-E custom GPT on new visual examples
- Update voice corpus with recent best writing
- Deprecate old prompt templates (archive in /archive)
- Create v2 prompts in /prompts/v2

Migration Strategy

Don't flip switch overnight:

Create parallel v2 prompt library
Generate examples with both v1 and v2
A/B test with team and users
Gradually shift traffic to v2
Archive v1 (don't delete - might need to reference)
Update all AI training (GPTs, Claude Projects, etc.)

Backward Compatibility

Some systems might still need v1:

Keep v1 prompts available but deprecated
Document which systems use which version
Set sunset date for v1 retirement
Migrate systems incrementally

anti-patterns:

name: Style drift without monitoring why_bad: | AI output quality degrades silently over time. Prompts that worked great 3 months ago produce increasingly off-brand results as models update, team members change prompts, or brand context gets lost. instead: | Set up monthly brand audits. Compare current AI output against gold standards. Track drift metrics. When quality drops, investigate root cause: prompt degradation, model changes, or brand evolution. Update prompts and retrain before drift becomes crisis.
name: Inconsistent prompt libraries why_bad: | Team members create ad-hoc prompts in their own ChatGPT/Claude sessions. No central repository. Brand knowledge siloed. Copy from marketing sounds different than copy from sales. Every person reinvents the wheel. instead: | Centralize prompts in version-controlled repository. Team must use approved prompts for brand content. Contribute improvements back to library. Review and approve changes like code. Build Custom GPTs or Claude Projects that embed approved prompts.
name: No governance or approval workflow why_bad: | Anyone can generate and publish AI content without review. Brand consistency depends on individual judgment. No quality control. When something off-brand ships, no way to know who/how/why. instead: | Implement approval gates. AI-generated content must pass automated brand checker + human review before publish. Define who can approve what. Track all AI-generated assets. Require metadata: prompt used, model version, approver, date. Audit trail for accountability.
name: Over-constraining creativity why_bad: | Prompts so rigid they prevent good ideas. "Always use this exact structure" kills innovation. Brand guidelines become straitjacket. AI can't adapt to context. Output feels robotic and formulaic. instead: | Define brand constraints (voice, visual style) but allow creative variation within those bounds. Encourage experimentation with new prompts. Review innovations monthly - promote best to prompt library. Brand should enable creativity, not prevent it.
name: Under-training AI on brand why_bad: | Expect AI to understand brand from 2-3 example images or brief description. Insufficient training data. Models lack context to generate consistently. Every output requires heavy editing. instead: | Invest in comprehensive training. Visual: 15-25 anchor images minimum. Voice: 50+ examples across contexts. Create Custom GPTs with full brand knowledge base. Build Midjourney style references. Train Flux LoRAs for critical use cases. More training = less editing.
name: Ignoring cultural and accessibility context why_bad: | Brand prompts optimized for one market/language/culture. AI generates content that doesn't translate, offends, or excludes. Accessibility as afterthought. Alt text generic. Color contrast ignored. instead: | Build cultural awareness into prompts. For global brands, create locale-specific variations. Include accessibility requirements in all visual prompts: contrast ratios, alt text structure, readable typography. Test AI output with diverse users. Update prompts based on feedback.
name: Missing negative prompts why_bad: | Only tell AI what to include, not what to avoid. Models make assumptions that contradict brand. Generate off-brand elements because you didn't explicitly forbid them. "Don't use gradients" never specified, so gradients appear everywhere. instead: | For every positive brand guideline, create negative counterpart. Visual negatives: gradients, stock photo aesthetics, clichés. Voice negatives: jargon, buzzwords, corporate speak. Build comprehensive blocklists. Include in all prompts. Prevents drift.

handoffs: triggers: - when: Need to define brand positioning before building AI assets delegate_to: brand-positioning context: | Brand positioning must be clear before encoding in AI. Delegate to brand-positioning skill to establish core message, audience, differentiation. Return with positioning doc to translate into AI-readable guidelines.

- when: Need to generate specific visual assets at scale
  delegate_to: ai-image-generation
  context: |
    Once brand style is defined and prompts created, delegate bulk
    visual generation to ai-image-generation skill. Provide brand
    prompts, style references, and quality benchmarks. They handle
    technical generation workflow.

- when: Need to write copy in established brand voice
  delegate_to: copywriting
  context: |
    After voice training and prompt library built, delegate actual
    copywriting to copywriting skill. Provide voice prompts, corpus
    examples, and context. They produce final copy using brand system.

- when: Need to create social media content with brand
  delegate_to: social-media-management
  context: |
    Hand off brand prompts and visual assets to social-media-management
    for channel-specific content creation and scheduling. They handle
    platform optimization within brand constraints.

- when: Need to design marketing assets with brand
  delegate_to: marketing-design
  context: |
    Provide brand guidelines, visual style references, and prompt
    library to marketing-design for creating campaign assets. They
    handle design execution using brand system.

Vibeship-spawner-skills ai-brand-kit

Brand Essence (AI-Readable)

Visual DNA

Voice Training Set

Prompt Library Index

Directory Structure

Prompt Template Format

Variation Dimensions

Constraint System

Variation Prompts

Batch Generation

Version Control

Visual Consistency Checker

Copy Consistency Checker

Automated Workflow

Feedback Loop

Channel Inventory

Context Mapping

Rollout Sequence

Consistency Monitoring

Version Your Brand

Changelog Everything

Migration Strategy

Backward Compatibility