agentleFS
phoenixvnphoenixvn/claude-code-agency/.claude/skills/team-brand/SKILL.md

team-brand

Skill0 starsChanged 7 months agoMITView on GitHub

Multi-agent orchestration for complete brand identity creation. 6 agents, 6 phases, with user approval gates. USER APPROVAL GATE — User selects brand direction. USER APPROVAL GATE — Approve strategy before visual work. brand-designer: - 3 color palette options (primary, secondary, accent, neutrals — with hex codes, psychology rationale) - 3 typography pairings (heading + body, with character samples) - Logo concept descriptions (2-3 directions: symbol meaning, style, type treatment) ui-designer: - Design tokens (spacing, border-radius, shadows) - Component style foundation…

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Create brand positioning statement: "For [target], [brand] is the [category] that [benefit] because [reason to believe]."

    line 30
  2. Distinctive:

    Create writing style guide aligned with brand personality

    line 52
  3. Distinctive:

    Write 3-5 sample paragraphs in brand voice

    line 58
  4. Distinctive:

    Verify brand guidelines are complete and actionable

    line 79

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

/team-brand — Full Branding Pipeline

Multi-agent orchestration for complete brand identity creation. 6 agents, 6 phases, with user approval gates.

Instructions

Phase 1: Discovery (creative-director)

Spawn creative-director to:

  • Review client brief for brand context
  • Analyze industry, competition, and audience
  • Define brand strategy direction
  • Present 2-3 brand personality options via AskUserQuestion:
    • Option A: [Personality + rationale]
    • Option B: [Personality + rationale]
    • Option C: [Personality + rationale]

USER APPROVAL GATE — User selects brand direction.

Phase 2: Brand Strategy (brand-lead)

Spawn brand-lead to:

  • Build Brand Pyramid:
    • Attributes (what the brand has)
    • Benefits (what the brand gives)
    • Values (what the brand believes)
    • Personality (how the brand acts)
    • Essence (one-word brand truth)
  • Define brand voice matrix: | Dimension | Do | Don't | Example |
  • Create brand positioning statement: "For [target], [brand] is the [category] that [benefit] because [reason to believe]."

USER APPROVAL GATE — Approve strategy before visual work.

Phase 3: Visual Identity (PARALLEL: brand-designer + ui-designer)

Spawn in parallel:

brand-designer:

  • 3 color palette options (primary, secondary, accent, neutrals — with hex codes, psychology rationale)
  • 3 typography pairings (heading + body, with character samples)
  • Logo concept descriptions (2-3 directions: symbol meaning, style, type treatment)

ui-designer:

  • Design tokens (spacing, border-radius, shadows)
  • Component style foundation based on each color/type option
  • Responsive breakpoints

USER APPROVAL GATE — User selects from presented options.

Phase 4: Content Voice (content-lead)

Spawn content-lead to:

  • Create writing style guide aligned with brand personality
  • Define tone variations by channel:
    • Website: [tone]
    • Social Media: [tone]
    • Email: [tone]
    • Formal/Legal: [tone]
  • Write 3-5 sample paragraphs in brand voice
  • Define vocabulary: preferred terms, avoided terms

USER APPROVAL GATE

Phase 5: Guidelines Compilation (brand-lead)

Spawn brand-lead to compile comprehensive brand guidelines:

  • Brand story and positioning
  • Visual identity (approved colors, typography, logo concepts)
  • Voice and tone guidelines
  • Design tokens and component styles
  • Usage rules (do's and don'ts)
  • Application examples (web, social, print, email)

Save to:

  • deliverables/design/brand-guidelines.md (client deliverable)
  • .claude/docs/brand-guidelines.md (agency reference — used by all agents)

Phase 6: Sign-off (creative-director)

Spawn creative-director to:

  • Review all deliverables for consistency and quality
  • Verify brand guidelines are complete and actionable
  • Present summary to user

Mark branding complete in production/session-state/active.md. Suggest next: /design-system for detailed component specs, or /wireframe for page layouts.

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.