agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/graphics-designer/SKILL.md

graphics-designer

Skill2 starsChanged 2 months agoMITView on GitHub

Create an individual graphic, carousel or banner using the client's supplied visual rules, or a neutral unbranded layout when requested.

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, 2 are distinctive, and 2 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.

  • 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, the content brief and relevant positioning, audience and voice pages.

    line 11
  2. Distinctive:

    Use dimensions from the requested destination or supplied brief.

    line 15
  3. Distinctive:

    Use approved brand rules when available.

    line 19
  4. Very specific:

    Keep working assets in output/<asset-name>/ or the user-selected destination.

    line 29

≈ “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

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.

Design a graphic

Read AGENTS.md, brand/BRAND.md, the content brief and relevant positioning, audience and voice pages. Read token files or reusable assets only if they actually exist. This template includes no preapproved visual kit.

Establish the information relationship before choosing a composition: a thesis, sequence, comparison, hierarchy, evidence or reflection. Keep the copy faithful to its source. A missing number or screenshot is not permission to invent one.

Use dimensions from the requested destination or supplied brief. Verify current platform requirements when exact compliance matters. Infer routine layout details; ask only when a missing choice changes the content or format materially.

Visual choices

Use approved brand rules when available. Otherwise create a plain unbranded draft when that fits the request: no invented logo, author signature, corporate palette, decorative footer or mandatory CTA. Mark temporary visual choices as draft choices rather than new brand policy.

Let spacing, hierarchy and truthful relationships carry the graphic. Do not force diagrams into quotes or turn every slide into identical cards. Use readable text and meaningful connector contrast. Keep authentic product screenshots intact and use supplied photography with known permissions.

For carousels, give each page a specific job and maintain continuity. Include a call to action only when the brief provides a useful next step.

Build and inspect

Choose tools actually available in the environment. HTML/CSS or SVG works for exact text and diagrams; an image-generation tool is useful for suitable illustration work. Use flowchart for editable process maps. The skill does not assume a bundled browser, renderer or design MCP.

Keep working assets in output/<asset-name>/ or the user-selected destination. Save editable source alongside the export. Use local or licensed fonts and verify actual font loading when rendering.

Inspect the rendered asset at its intended size and a small viewing size. Check text accuracy, hierarchy, clipping, contrast, connector collisions and missing assets. Fix visible defects and rerender. If rendering or inspection is unavailable, deliver the source and state the exact unverified step.

Return file links, dimensions and relevant limitations. Producing one graphic does not authorize changing shared brand rules or publishing it.

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.