agentleFS
koinodkoinod/skills/brand-identity-analyzer/SKILL.md

brand-analyzer

Skill0 starsChanged 6 months agoMITView on GitHub

Analyze brands to generate comprehensive brand identity profiles (JSON). Use when the user wants to analyze a brand, create a brand profile, or needs brand data for ad generation. Stores profiles for reuse across Ad-Ready, Morpheus, and other creative workflows. Can list existing profiles and update them.

  • Reads credentials
  • Commits and pushes

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before running Ad-Ready when the brand isn't in the catalog

    line 21
  2. Distinctive:

    When the user mentions a brand that doesn't have a profile yet

    line 22
  3. Distinctive:

    Do NOT skip this step. The ad generation pipeline on ComfyDeploy needs the profile in the repo to work correctly.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Brand Analyzer: AI Brand Identity Profiler

Analyze any brand to generate a comprehensive brand identity JSON profile using Gemini Flash with Google Search grounding.

Overview

Brand Analyzer creates structured brand identity profiles by:

  1. Researching the brand via Google Search (official data, campaigns, visual identity)
  2. Analyzing brand behavior, visual patterns, photography style, tone of voice
  3. Generating a complete JSON profile following the standard template
  4. Storing the profile for reuse across all creative workflows

When to Use

  • User asks to "analyze a brand" or "create a brand profile"
  • Before running Ad-Ready when the brand isn't in the catalog
  • When the user mentions a brand that doesn't have a profile yet
  • To update/refresh an existing brand profile

Quick Commands

Analyze a brand and save to file

GEMINI_API_KEY="$KEY" uv run {baseDir}/scripts/analyze.py \
  --brand "Brand Name" \
  --output ./brands/Brand_Name.json

Analyze and auto-save to Ad-Ready brands catalog

GEMINI_API_KEY="$KEY" uv run {baseDir}/scripts/analyze.py \
  --brand "Heredero Gin" \
  --auto-save

The --auto-save flag automatically saves to ~/clawd/ad-ready/configs/Brands/{Brand_Name}.json

⚠️ MANDATORY: Push to GitHub After Every New Brand Profile

Every time a new brand profile is generated and saved, it MUST be pushed to GitHub immediately. This is non-optional — the ComfyDeploy deployment pulls brand profiles from the repo.

cd ~/clawd/ad-ready
git add configs/Brands/{Brand_Name}.json
git commit -m "Add brand profile: {Brand Name}"
git push origin main

Do NOT skip this step. The ad generation pipeline on ComfyDeploy needs the profile in the repo to work correctly.

Print to stdout

GEMINI_API_KEY="$KEY" uv run {baseDir}/scripts/analyze.py --brand "Nike"

Inputs

InputRequiredDescription
--brand✅Brand name to analyze
--outputOptionalOutput file path (default: stdout)
--auto-saveOptionalAuto-save to Ad-Ready brands catalog
--api-keyOptionalGemini API key (or set GEMINI_API_KEY env var)

Output Format

The generated JSON follows the standard brand identity template used by Ad-Ready:

{
  "brand_info": { "name", "tagline", "category", "positioning", "vision", "mission", "origin_story" },
  "brand_values": { "core_values", "brand_promise", "differentiators", "non_negotiables" },
  "target_audience": { "demographics", "psychographics" },
  "tone_of_voice": { "personality_traits", "communication_style", "language_register", ... },
  "visual_identity": { "logo", "color_system", "typography", "layout_principles" },
  "photography": { "style", "technical" },
  "campaign_guidelines": { "visual_tone", "model_casting", "product_presentation", ... },
  "brand_behavior": { "do_dont", "immutability" },
  "channel_expression": { "retail", "digital", "print" },
  "compliance": { ... }
}

Integration with Other Workflows

Ad-Ready

Brand profiles are automatically available as brand_profile options when generating ads.

Morpheus Fashion Design

Brand visual identity (colors, photography style, tone) can inform Morpheus campaigns.

Custom Workflows

Load any brand profile JSON to extract visual identity, tone of voice, or campaign guidelines for any creative task.

Analysis Methodology

The analyzer follows a 3-phase approach:

Phase 1: Official Research (via Google Search)

  • Brand website, corporate pages, official communications
  • Locks canonical data: name, founding, positioning, vision, mission, tagline

Phase 2: Campaign Research (via Google Search)

  • Google Images and Pinterest for advertising campaigns
  • Identifies 10+ distinct campaigns
  • Treats them as analytical reference material

Phase 3: Deductive Visual Analysis

  • Cross-sectional analysis of visual patterns
  • Identifies recurring photography style, color systems, typography
  • Fills visual identity fields not covered by official data

API Key

Uses Gemini API. Set via:

  • GEMINI_API_KEY environment variable
  • --api-key flag

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.