agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/brand-system/SKILL.md

brand-system

Skill2 starsChanged 2 months agoMITView on GitHub

Establish or update a client's visual identity, reusable tokens and graphic conventions from their preferences and supplied assets.

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

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read AGENTS.md, brand/BRAND.md, relevant positioning and audience pages, supplied references and any existing implementation files.

    line 11
  2. Distinctive:

    Update the guide, relevant tokens and consumers together within the requested scope.

    line 25
  3. Distinctive:

    Use the project's actual checks and renderer if available.

    line 29
  4. Very specific:

    Update Source Notes, index.md and log.md for durable decisions.

    line 31

“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

Workspace: all context paths below (identity, audience, strategy, voice, brand, raw, output, index, log, workspace preferences and context scripts) resolve from context/ in the kit root. Read both the root AGENTS.md and context/AGENTS.md. Skill-local references/ and flowchart scripts/ resolve from this skill directory.

Maintain the brand system

Read AGENTS.md, brand/BRAND.md, relevant positioning and audience pages, supplied references and any existing implementation files. Resolve paths within this repository. No brand is preinstalled.

For a new identity, capture the client's desired impression, constraints, existing assets and usage contexts. Propose a direction only when design work is requested. Label proposed rules as draft until the client adopts them. A missing brand guide does not authorize copying a reference creator's identity.

Central ownership

Use brand/BRAND.md for intent, status, usage rules and navigation. When implementation is needed, place exact reusable values in a central token file and licensed assets in brand/assets/. Create only the layers the actual deliverables need. Do not assume scripts or templates from another repository are present.

Separate source tokens, generated files, reusable templates, explorations and delivered assets. Link to audience and voice context instead of duplicating it. Keep compositions flexible while sharing meaningful typography and color roles.

Changes

For an existing system, inspect affected consumers before editing. A request for one graphic does not authorize a global palette change. Shared CSS can alter historical work: preserve delivered assets or pin their dependencies when necessary.

Update the guide, relevant tokens and consumers together within the requested scope. Never install branded example assets as defaults in the blank template. Keep product screenshots faithful to the real product.

Verify and hand off

Use the project's actual checks and renderer if available. Otherwise validate new artifacts with the tools used to build them. Inspect representative layouts for font loading, contrast, clipping and asset portability. Do not claim a build or visual check that was not run.

Update Source Notes, index.md and log.md for durable decisions. Return the authoritative files, adoption status and any unfinished migration.

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.