agentleFS
JakeschincariolJakeschincariol/claude-illegal-codes/aura-farming/SKILL.md

aura-farming

Skill11 starsChanged 3 months agoMITView on GitHub

Maximum-aesthetic mode for any visual deliverable (Meta ads, slide decks, landing pages, social graphics, posters, UI) that bans every AI-slop tell, forces a real design direction, and audits the result before shipping; invoke via /aura-farming whenever a visual is being created and it needs to look like a designer made it.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Commit to a palette: one dominant color, one accent, neutrals.

    line 19
  2. Distinctive:

    Run the draft through this list and fix every failure:

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Aura Farming

Most AI-made visuals scream AI: purple gradients, glassmorphism, six identical rounded cards, emoji bullets, "Elevate Your Workflow." This mode farms aura instead. One strong direction, committed typography, disciplined spacing, and a slop audit before anything ships.

When to use

  • Creating any visual: ad creative, slide deck, landing page, social graphic, poster, app UI, thumbnail.
  • Reworking an existing visual that "looks AI-generated."

Behavior

1. Pick a direction before touching pixels

  • Name one aesthetic point of view in a sentence (for example "Swiss grid with one loud serif," "brutalist mono on bone white," "1970s print ad"). No direction, no drafting.
  • Two typefaces max, each with an assigned job. Never default to the system stack because it was there.
  • Commit to a palette: one dominant color, one accent, neutrals. No rainbow.
  • Choose a grid and stick to it. Every element aligns to something.

2. The banned list (hard no, zero exceptions)

  • Purple-to-blue gradients on dark backgrounds, and gradient text anywhere
  • Glassmorphism or frosted cards as a default texture
  • Emoji as bullet points or decoration
  • Center-aligning everything
  • Grids of identical rounded cards, each with icon plus title plus two lines
  • Sparkles, robots, glowing brains, handshakes, generic 3D blobs
  • Drop shadow on every element
  • Corporate Memphis people
  • Filler copy: elevate, unlock, seamless, supercharge, revolutionize
  • Fake testimonials and fake five-star ratings

3. Audit before shipping

Run the draft through this list and fix every failure:

  • Squint test: is exactly one element loudest, a clear second, and everything else quiet?
  • Spacing on one consistent scale (a base unit, multiplied)?
  • Type: max two families, sizes from a real scale, no orphan weights?
  • Contrast readable at target size (AA for UI)?
  • Did anything from the banned list survive? Remove it.
  • Honest question: would a working designer put this in a portfolio? If no, name the reason, fix it, re-audit.

Output

The finished visual plus a three-line audit note: the direction chosen, what got cut in the slop pass, and the one signature moment of the composition.

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.