agentleFS
pradeep-sankaran-07pradeep-sankaran-07/team-os-gdrive-template/.agents/skills/acme-brand/SKILL.md

acme-brand

Skill0 starsChanged 2 months agoMITView on GitHub

Apply the Acme Corp visual standard to any output: documents, decks, spreadsheets, HTML reports and charts. Load this whenever producing any company deliverable, on top of whatever other skill is running. Triggers: "make it branded", "add the logo", "use our branding", or any request for a report, deck, brief, one-pager or chart that leaves someone's screen. NOT for product UI (that is the product design system) and NOT for deciding what a public document may claim (use acme-marketing).

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Read assets/tokens/colors.css and assets/tokens/type.css.

    line 29
  2. Very specific:

    Every colour in the file appears in colors.css.

    line 56
  3. Distinctive:

    No em dashes, anywhere.

    line 58
  4. Very specific:

    If the logo file is not in the session and not in assets/, ask for it before producing the deliverable.

    line 74

≈ “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

Acme brand

The single source of visual truth. Every other skill consumes these values and none of them redefines a colour or a font. If you find a hex or a font name written literally inside another skill, that is a bug; move it here.

Step 1 - Read the tokens

Read assets/tokens/colors.css and assets/tokens/type.css. Use the token names, not the literal values, wherever the output format allows it (CSS, HTML, themes). Where the format cannot take a variable, copy the value from the token file rather than from memory.

Step 2 - Apply the standard

ElementRule
Primary--acme-primary
Accent--acme-accent, used sparingly, for emphasis only
Ink and surfaces--acme-ink, --acme-surface, --acme-muted
Headingsthe display face in type.css
Bodythe text face in type.css
Office fallbacka system face, for .docx and .xlsx only, where the brand faces cannot embed
Logotop left of the first page or slide, clear space equal to the logo height
Footersee below

The footer text is Acme Corp, then the domain, then Confidential, separated by pipes.

Charts follow the same palette: primary for the main series, accent for the one series being pointed at, muted greys for everything else. Never rainbow a chart.

Step 3 - Check before delivering

  • The logo is present and not stretched.
  • Every colour in the file appears in colors.css. A near-miss hex is invisible to the eye and wrong in the file, and the skill promotion gate rejects it.
  • No em dashes, anywhere.
  • The footer is on every page.

Boundary: when this does NOT apply

  • Product screens and prototypes. This template ships no product-UI skill; if you build a product, add one. Do not put a document header and footer on an app screen.
  • Deciding what a public document is allowed to say: that is acme-marketing. This skill controls how it looks, not what it claims. Answer both questions.
  • Generating an image: create-branded-image owns that, and it applies the house photographic style rather than this document layout.

Non-negotiables

  • One source of truth for colour and type. Never redefine a value locally.
  • If the logo file is not in the session and not in assets/, ask for it before producing the deliverable. Do not substitute a placeholder and do not draw one.
  • The footer's confidentiality line stays on internal documents even when they look polished.

Things that have gone wrong before

  • Change a font in one pass, everywhere, or not at all. Why: a font name written literally into a dozen places, with half of them updated, leaves the OS producing two different looks depending on which skill ran. That is what the token file is for. (2026-09-16)

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.