agentleFS
OpenClaudiaOpenClaudia/openclaudia-skills/skills/brand-research/SKILL.md

brand-dev

Skill723 starsChanged 5 months agoMITView on GitHub

Fetch brand info (name, description, logos, industry) from brand.dev API and save logos locally. Use when the user asks to look up a brand, fetch a logo, get brand info, or add a company with its logo.

  • Reads credentials

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Industry/category: if available

    line 28
  2. Very specific:

    ALWAYS download logos locally for serving.

    line 32
  3. Very specific:

    Other web projects: check for existing static/, assets/, images/, or public/ directories

    line 38
  4. Very specific:

    If no convention exists: create a logos/ directory under the project's static asset root

    line 39
  5. Distinctive:

    If the brand has no logos in the API response, note this and suggest using a fallback icon.

    line 73

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.dev Skill

Fetch brand data from the brand.dev API and save logos locally for serving.

Step 1: Get the Domain

Extract the target domain from the user's input. Strip protocol and trailing slashes (e.g., "https://example.com/" -> "example.com").

Step 2: Fetch Brand Info

# BRANDDEV_API_KEY must be set in your environment
curl -s "https://api.brand.dev/v1/brand/retrieve?domain=${DOMAIN}" \
  -H "Authorization: Bearer ${BRANDDEV_API_KEY}" \
  -H "Content-Type: application/json"

Extract from the response:

  • Brand name (.brand.title or .brand.name)
  • Description (.brand.description)
  • Logo URLs (from .brand.logos[]) — prefer icon/square logos for card layouts, full logos for headers
  • Industry/category if available

Step 3: Download Logos Locally

ALWAYS download logos locally for serving. Never reference external media.brand.dev URLs in production code — they can change or go down.

Where to save

The save location depends on the project. Look for existing patterns:

  • Next.js / static sites: public/logos/<context>/ (served as /logos/<context>/)
  • Other web projects: check for existing static/, assets/, images/, or public/ directories
  • If no convention exists: create a logos/ directory under the project's static asset root

Naming Convention

  • <brand-slug>.<ext> where:
    • <brand-slug> is the lowercase brand name, spaces replaced by hyphens (e.g., miss-a not miss_a)
    • <ext> matches the original file extension (png, webp, jpg, svg)
  • Optionally group by context subdirectory (e.g., partners/, customers/) if the project has multiple logo collections

Download Command

mkdir -p <logo-dir>
curl -sL "<logo-url>" -o "<logo-dir>/<brand-slug>.<ext>"

Verify Download

ls -la <logo-dir>/<brand-slug>.<ext>

Step 4: Return Results

Provide the user with:

  • Brand name
  • Description
  • Industry
  • Local logo path — the path to use in code (relative to the project's static root)
  • Original source URL (for reference only)

Important Rules

  1. Always save images locally — never use media.brand.dev URLs directly in production code.
  2. Use local paths in code — reference relative to the project's static asset serving root.
  3. Prefer square/icon logos for card layouts (they fit better in grid cards).
  4. Prefer full/horizontal logos for headers and hero sections.
  5. If the brand has no logos in the API response, note this and suggest using a fallback icon.

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.

Reviews can't be read right now.

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.