agentleFS
prateekjainprateekjain/ChiefOfStaff/skills/brand-setup/SKILL.md

brand-setup

Skill4 starsChanged 8 months agoMITView on GitHub

Research domains, validate business names, and generate a brand kit for a venture

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 8 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the venture's CLAUDE.md for name, one-liner, target audience

    line 23
  2. Very specific:

    Read docs/market-research.md for competitive landscape

    line 24
  3. Very specific:

    Read docs/gtm-strategy.md if it exists for positioning

    line 25
  4. Distinctive:

    Competitor conflict: Check if any direct competitor uses a similar name

    line 30
  5. Distinctive:

    If the current name has issues, propose 3-5 alternatives with pros/cons

    line 33
  6. Distinctive:

    Check domain availability and alternatives:

    line 36
  7. Very specific:

    Primary domain: Check [name].com, [name].ai, [name].io, [name].co using WebFetch to check DNS/WHOIS

    line 37
  8. Distinctive:

    Use this approach to check domains:

    line 42
  9. Distinctive:

    If it returns domain data = taken.

    line 46
  10. Very specific:

    Create docs/brand-kit.md in the venture repo with:

    line 54
  11. Distinctive:

    Add brand kit reference to venture's CLAUDE.md

    line 91
  12. Distinctive:

    Update the venture's landing page CSS variables if colors differ from current

    line 92

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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 Setup

Research and establish brand identity for a venture. This skill is run during VALIDATION stage (or when transitioning to MVP).

Input

Venture slug: $ARGUMENTS

Step 1: Read Context

  1. Read the venture's CLAUDE.md for name, one-liner, target audience
  2. Read docs/market-research.md for competitive landscape
  3. Read docs/gtm-strategy.md if it exists for positioning

Step 2: Name Validation

Research whether the venture name works:

  1. Trademark search: WebSearch for "[name] trademark" and "[name] software" to check for conflicts
  2. Competitor conflict: Check if any direct competitor uses a similar name
  3. Pronunciation/spelling: Is it easy to say, spell, and remember?
  4. SEO potential: WebSearch the name — how crowded are the results?
  5. If the current name has issues, propose 3-5 alternatives with pros/cons

Step 3: Domain Research

Check domain availability and alternatives:

  1. Primary domain: Check [name].com, [name].ai, [name].io, [name].co using WebFetch to check DNS/WHOIS
  2. Alternative domains: Try variations — get[name].com, use[name].com, try[name].com, [name]app.com, [name]hq.com
  3. Social handle availability: WebSearch for the name on Twitter/X, LinkedIn, GitHub
  4. Recommendations: Rank top 3 domain options by preference with estimated cost

Use this approach to check domains:

WebFetch: https://rdap.verisign.com/com/v1/domain/[name].com

If it returns domain data = taken. If 404 = likely available.

For .ai/.io domains:

WebSearch: "[name].ai domain" OR check via WebFetch to a WHOIS API

Step 4: Brand Kit Generation

Create docs/brand-kit.md in the venture repo with:

Identity

  • Name: [Final name]
  • Tagline: [Short tagline, 5-8 words]
  • One-liner: [Elevator pitch, 1 sentence]
  • Boilerplate: [2-3 sentence company description for bios, footers, etc.]

Voice & Tone

  • We sound like: [3 adjectives — e.g., confident, knowledgeable, approachable]
  • We don't sound like: [3 things to avoid — e.g., corporate, salesy, condescending]
  • Audience language: [Key terms the target audience uses naturally]
  • Example sentences: [3 examples of on-brand copy vs off-brand copy]

Visual Identity

  • Primary color: [Hex code + name — based on industry/audience psychology]
  • Secondary color: [Hex code]
  • Accent color: [Hex code — for CTAs, highlights]
  • Background: [Light/dark preference with hex]
  • Typography: [Font recommendations — heading + body]
  • Icon style: [Lucide/outline, filled, etc.]

Domain & Handles

  • Recommended domain: [Top pick with reasoning]
  • Alternative domains: [2-3 backup options]
  • Social handles: [Availability status for Twitter, LinkedIn, GitHub]
  • Email: hello@[domain]

Stage-Based Rollout

StageBrand Assets
VALIDATIONBrand name, colors, landing page tone, shared social posts
MVPOwn domain, own email, brand guidelines doc, Twitter/X account
LAUNCHFull social presence, content templates, email templates
GROWTHPR kit, partnership materials, branded assets

Step 5: Update Venture Docs

  1. Add brand kit reference to venture's CLAUDE.md
  2. Update the venture's landing page CSS variables if colors differ from current

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.