taste-learn
Skill0 starsChanged 5 months agoMITView on GitHub
Capture a new taste reference into the taste library. Use when the user says "learn this", "add to my taste refs", "taste-learn", or shares a link, screenshot, product, or piece of writing they want remembered. Works for interfaces and prose. Extracts the *why* and the reusable move, then appends an entry to the taste library at ~/.claude/taste/references.md.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- RahmanBuildsAI/ravyn-reel-kittheir own version, first seen Oct 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- RahmanBuildsAI/ravyn-reel-kit★ 9same 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.
- taste-auditSkill
- taste-helpSkill
- tasteSkill
- taste-sweepSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 26
Put new entries above the <!-- Append new references below.
≈ “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.
Files
Taste — learn
Capture one reference. The point is the why, not the link.
Input (args or this message)
- A URL → WebFetch it. Judge the design or the writing, not the page chrome.
- A screenshot or image in chat → read it.
- A piece of writing (copy, doc, name, message) → read it as prose.
- A product or feature named in prose → use what the user says plus what you know.
- Nothing clear → ask one line: "What am I learning, and what works or fails?"
Do
- Find the single sharpest thing that works or fails. Name the mechanism in taste terms — alignment, hierarchy, affordance, the arc, restraint; or for prose, clutter cut, plain words, active verbs, voice. Anti-patterns count too.
- Distill the move worth stealing.
- Append to the library at
~/.claude/taste/references.mdin its format: What / Why it works or fails / Steal. One tight line each. If the library doesn't exist yet, create~/.claude/taste/and seed it fromreferences.template.mdin thetasteskill's directory first. - Put new entries above the
<!-- Append new references below. -->marker. - Confirm what you added in one line. Don't lecture.
Rules
- One reference per call, unless the user lists several.
- A link with no why is not a reference. Derive the why or ask.
- Match the brevity of the entries already there.
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
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.

