agentleFS
vivian-chivivian-chi/growing-brand/skills/brand-init/SKILL.md

brand-init

Skill1 starsChanged 4 months agoMITView on GitHub

Use when the user wants to set up, initialize, or start brand memory in a project ("/brand-init", "start remembering my brand", "set up growing-brand"), or accepts the brand-memory skill's first-run offer. Creates the brand/ folder, seeds it by scanning the project's existing design work (CSS, tokens, components, style guides) when there is any, asks up to three one-line identity questions, and hands off to the ambient brand-memory skill. Cold start with empty files is fully supported.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. cofoundy/brand-skills★ 79same name
    2. skyf0xx/gambit★ 29same name
    3. sawzhang/coffee-mcp★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

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. Very specific:

    If brand/journal.md already exists → this project is already growing.

    line 15
  2. Very specific:

    Write these into tokens.md and moves.md, every seeded line marked (observed — unconfirmed).

    line 31
  3. Distinctive:

    Ask up to three, each answerable in one line, each skippable — stop early if the user is brief or busy:

    line 35
  4. Very specific:

    Write the answers into core.md as rules marked (seeded), phrased in the user's own words as much as possible.

    line 41
  5. Distinctive:

    Cold start is fine: No existing work + all questions skipped = empty templates, and that's a valid start: the tool is designed to begin …

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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-init — start brand memory in this project

One-time setup. Everything after this is ambient (see the brand-memory skill): the user just works, the brand grows.

1 · Check

If brand/journal.md already exists → this project is already growing. Give the short status summary (brand-memory §4) and stop. If a brand/ folder exists but isn't ours (no journal, different content), use growing-brand/ as the folder name instead and say so in one line.

2 · Create

Copy the four templates from this skill's templates/ directory into brand/: core.md · tokens.md · moves.md · journal.md. (If the templates aren't available at that path, recreate them from the structure shown in each — header comment + empty sections.)

3 · Seed from existing work (only if there is any)

Scan whatever design surface the project already has — stylesheets, tailwind/theme configs, token files, components, an existing site, a style guide:

  • Colors by frequency → the recurring palette, not every hex that appears once.
  • Type: families in use, the weights and sizes that repeat.
  • Space & shape: spacing steps, radius values, border/shadow habits.
  • Moves: recurring patterns visible in the code or pages (how heroes are built, imagery style, what never appears).

Write these into tokens.md and moves.md, every seeded line marked (observed — unconfirmed). Restraint: seed only what repeats — 12 lines the files can defend beat 40 lines of inventory. These lines harden into confirmed rules (or fall away) as journal evidence arrives.

4 · Three questions (optional, one at a time)

Ask up to three, each answerable in one line, each skippable — stop early if the user is brief or busy:

  1. "Name one piece of design — yours or anyone's — you'd be proud to have made. What's the one thing that makes it good?"
  2. "What's the look you never want — the thing that would make you say 'that's not us'?"
  3. "Three words your design should feel like — and one it must never feel like?"

Write the answers into core.md as rules marked (seeded), phrased in the user's own words as much as possible. Skipped questions cost nothing: core grows from the journal either way.

5 · Done — say only this much

Three lines max: where the files live, that from now on it grows by itself while they work (no routine, nothing to run), and that the files are theirs to edit — hand edits are the strongest signal.

Cold start is fine. No existing work + all questions skipped = empty templates, and that's a valid start: the tool is designed to begin knowing nothing.

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.