agentleFS
Sign inStart free
obakeng-developsobakeng-develops/taste/skills/taste-audit/SKILL.md

taste-audit

Skill0 starsChanged 5 months agoMITView on GitHub

Audit an interface or a piece of writing against the taste model and the user's reference library. Use when the user says "taste audit", "taste-audit", "is this any good", "critique this", "what's wrong with this UI", "edit this copy", or shares a screen, URL, component, or text for a taste pass. One-shot report ranked by severity; applies no fixes (use /taste to build, /taste-learn to capture).

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Harrypatria/tastemaker★ 4same 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 repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Read the taste library at ~/.claude/taste/references.md (if it exists).

    line 18
  2. Distinctive:

    Read it aloud in your head — flag what stumbles.

    line 38
  3. Distinctive:

    No fixes applied. This is diagnosis.

    line 52

≈ “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

Taste — audit

Critique one target against the taste model. Report only — no edits.

Target (args or this message)

  • Screenshot or image → read it.
  • URL → WebFetch and judge the rendered result.
  • Front-end code / component / CSS → read it, infer how it renders.
  • Writing (copy, doc, message, name) → judge it as prose.
  • Nothing → ask one line what to audit.

Calibrate first

Read the taste library at ~/.claude/taste/references.md (if it exists). Judge against the user's taste, not a generic ideal. If a finding fights a saved reference, the reference wins.

What to check

For interfaces — three layers, in order:

  1. Jank: alignment/grid, typeface count, body text (15–25px, line-height 1.3–1.45, 45–90 chars/line), spacing rhythm, drift.
  2. Affordances: does each element show how it works? Right control for the job? Broken conventions — on purpose or by accident?
  3. Story: does the flow have an arc? Does hierarchy answer the real question first? Are empty, error, and success states there? Restraint or clutter?

For writing — Zinsser:

  • Clutter: dead words, "in order to", "the fact that", empty qualifiers, adverbs that repeat the verb.
  • Plain words: fancy where simple would do; jargon.
  • Verbs and voice: passive where active is stronger; weak verbs.
  • One thought per sentence; warm, human voice.
  • Read it aloud in your head — flag what stumbles.

Report

Open with a one-line verdict. Then findings in severity order, one line each, location plus the specific fix:

  • Jank / Clutter — floor problems; cheap and high-leverage, fix first.
  • Affordance / Clarity gaps — confusing controls, or unclear sentences.
  • Story / Voice misses — weak arc or missing states; flat or stiff prose.
  • Polish — optional. Close with the single highest-leverage change.

Rules

  • Be specific. Name the mechanism, not "feels off".
  • Praise only what teaches — and suggest /taste-learn to capture it.
  • No fixes applied. This is diagnosis. Skip empty buckets; don't pad.

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.

Check your setup, free