agentleFS
wedabrowedabro/bro-skills/.agents/skills/brandkit/SKILL.md

brandkit

Skill3 starsChanged 45 days agoMITView on GitHub

Generate premium brand-identity imagery, logo systems, brand-guideline boards, visual-world directions, and identity mockups. Use for image-based brand exploration and presentation systems. Produce brand visuals only; do not implement websites, design mobile product screens, or write application code.

We split this skill into the rules it gives an agent

10 rules. 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 72 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a coherent identity system with a defensible concept, not a collection of unrelated logo mockups.

    line 8
  2. Distinctive:

    Check small-size recognition, monochrome behavior, consistency, legibility, and category distinctiveness.

    line 16
  3. Distinctive:

    Keep logo geometry simple enough to recognize at favicon size.

    line 21
  4. Distinctive:

    Use sparse, readable typography and realistic mockups that reveal how the identity behaves.

    line 23
  5. Distinctive:

    Avoid generic orbit marks, random shields, meaningless hexagons, fake embossing, and crowded logo walls.

    line 24
  6. Distinctive:

    Keep palette disciplined and provide monochrome or single-color behavior when relevant.

    line 25
  7. Distinctive:

    Do not fabricate legal claims, awards, partnerships, or cultural symbolism without grounding.

    line 26
  8. Distinctive:

    Treat reference brands as directional evidence, never as shapes to copy.

    line 27
  9. Distinctive:

    Read only the relevant section of references/full-guide.md:

    line 31
  10. Very specific:

    Use rg -n "<heading>" references/full-guide.md.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 72 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 Kit Image Generation

Create a coherent identity system with a defensible concept, not a collection of unrelated logo mockups.

Workflow

  1. Extract brand audience, category, positioning, personality, competitors, cultural constraints, and required applications.
  2. State a short strategic idea and derive two or three distinct logo concepts from meaning, not decoration.
  3. Choose one direction and lock logo logic, palette, typography, imagery, layout grid, and material language.
  4. Generate a focused board or requested identity assets using realistic, relevant applications.
  5. Check small-size recognition, monochrome behavior, consistency, legibility, and category distinctiveness.

Non-negotiables

  • Build the symbol from a clear idea: monogram, product action, metaphor fusion, negative space, or construction geometry.
  • Keep logo geometry simple enough to recognize at favicon size.
  • Show one coherent system rather than many unrelated styles on one board.
  • Use sparse, readable typography and realistic mockups that reveal how the identity behaves.
  • Avoid generic orbit marks, random shields, meaningless hexagons, fake embossing, and crowded logo walls.
  • Keep palette disciplined and provide monochrome or single-color behavior when relevant.
  • Do not fabricate legal claims, awards, partnerships, or cultural symbolism without grounding.
  • Treat reference brands as directional evidence, never as shapes to copy.

Detailed reference

Read only the relevant section of references/full-guide.md:

  • Strategy and logo ideation: search BRAND STRATEGY FIRST or LOGO CONCEPT METHODS.
  • Board layouts: search BOARD COMPOSITION DNA.
  • Category-specific directions: search VISUAL MODES.
  • Typography, taglines, imagery, mockups, and color: search the matching heading.
  • Prompt construction and final QA: search PROMPT TEMPLATE or FINAL OUTPUT STANDARD.

Use rg -n "<heading>" references/full-guide.md; do not load the complete guide for a narrow request such as a logo concept or palette exploration.

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.