agentleFS
adityareddy-devadityareddy-dev/deskstudio/skills/taste/SKILL.md

taste

Skill43 starsChanged 23 days agoMITView on GitHub

Record what you liked or rejected about a job, by rubric axis, into .desk/taste.md so every later job starts from it. Use right after looking at an output, with the job id and a sentence.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use council, ui-ux-pro-max and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    council

    Convene the persona panel — six orthogonal review lenses — on a target. Cold independent fan-out, debate-to-consensus, synthesized verdict with recorded dissent and a roster manifest.

    Also in 3 projects that use this

  • StrayDragonSkill

    ui-ux-pro-max

    UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.

    Also in 3 projects that use this

  • BlockSkill

    frontend-design

    Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 1

    Distinctive

    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. Distinctive:

    Run: Do not run the loop. Instead:

    line 31
  2. Very specific:

    Write apply as an instruction a director can follow on the next job of this kind, in one line, under 30 words.

    line 35

“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “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

Record taste as the Design Manager. No desks are spawned and no model is called beyond this session: this command writes a file.

Deliverable and standard. An entry in .desk/taste.md, the file the Creative Director reads on top of the standards on every job. Entries are written in the rubric's axes so a director can act on them, in plain words, never in the user's prompt text verbatim.

Desks. None.

Inputs. A job id under .desk/jobs/, or last for the most recent state.json by updatedAt, then liked or rejected, then the user's sentence. show prints the file. forget N removes entry N. With no job id and a sentence, the entry is general and job is none.

Proof sizes. None.

Output. .desk/taste.md in the project, created if missing with the heading below, one entry appended:

# Taste

What the user approved and rejected, for the Creative Director to apply on top of the standards. Newest last.

## 1. liked, 2026-10-18, job 20261018-1830-launch-card-linkedin
- deliverable: social-card, pattern: editorial split, scores: average 8.75
- axes: hierarchy, composition
- note: the stat carried the card, keep the big figure left and the headline short on launch cards
- apply: on social cards for this brand, prefer the stat card and editorial split patterns, keep headlines under seven words

Run. Do not run the loop. Instead:

  1. Find .desk/ as step 0 of ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md describes, then the job: read its state.json for deliverable, pattern (from pick), the final scores, and the Art Director's notes.
  2. Map the user's sentence to one to three rubric axes (hierarchy, typography, spacing, colour, composition, originality, brand, copy). If it names a pattern, a colour move or a copy habit, say so in note.
  3. Write apply as an instruction a director can follow on the next job of this kind, in one line, under 30 words.
  4. Append the entry, numbered from the last one, with the date in America/Chicago. Never copy the user's sentence verbatim, rewrite it as an instruction.
  5. Emit one event: node "${CLAUDE_PLUGIN_ROOT}/scripts/emit-event.mjs" taste.add id=<job id or none> kind=liked|rejected axes=<comma list>.
  6. Reply in two lines: the entry number and the apply line.

For show, print the file. For forget N, remove that entry, renumber nothing, and emit taste.forget entry=N.

The ask: $ARGUMENTS

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.