emilkowalski/skills is a collection of guidance for coding agents that helps them make better interface and animation decisions. Designers and engineers use the skills to choose more appropriate motion, styling, and interaction details when building user interfaces. The catalogue entries are examples of the project's agent skills.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add emilkowalski/skills --skill learn-tastegit clone --depth 1 https://github.com/emilkowalski/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/emilkowalski/skills/learn-taste)<a href="https://agentmods.dev/skills/emilkowalski/skills/learn-taste"><img src="https://agentmods.dev/badge/skills/emilkowalski/skills/learn-taste/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/emilkowalski/skills/learn-taste"><img src="https://agentmods.dev/badge/skills/emilkowalski/skills/learn-taste.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.02145 |
| Opus 5.5 | $0.00012 | $0.00858 |
| Sonnet 5.5 | $0.00006 | $0.00429 |
| Haiku 4.5 | $0.00003 | $0.00215 |
Grade A, and why
learn-taste scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- learn-taste — 98% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Taste
Every correction a user makes is taste the agent didn't have. If it isn't written down, the next session makes the same mistake and the user corrects it again. This skill finds those corrections, turns each one into a rule with its reason, and writes it where the next agent will read it.
It does ONE thing: write rules. It never changes component code, and it never adds a rule the user didn't express.
Hard Rules
- Only the user's taste. Every rule traces back to something the user said, edited, or confirmed. Never add a rule because it seems like good practice. That's your taste, and your taste is what the user was correcting.
- Never invent a why. If the user gave no reason, propose one marked inferred and get it confirmed before writing. A wrong why is worse than none: the next agent extends the reasoning to cases it doesn't fit.
- Propose, then stop. Present every candidate and write only what the user approves. A wrong rule repeats in every future session, exactly like the mistake would have.
- A check beats a sentence. If a violation can be found by matching code (a banned value, a raw hex instead of a token, a forbidden property), propose a lint rule, a token restriction, or a test. A check runs every time. A sentence in a long file gets skipped when the agent's context is full.
- Write for an agent that wasn't here. No "like we discussed" or "the card from earlier". Name the class of component, the value, the token, the file.
Workflow
Phase 1: Collect corrections
Read the current conversation from the first turn. If the user names earlier sessions and you can read their transcripts (Claude Code stores them as JSONL under ~/.claude/projects/<project>/), read those too.
Explicit corrections are the minority. Look for all five signals:
| Signal | Example | What it tells you |
|---|---|---|
| Explicit correction | "No, semi-transparent shadow, not a border" | The rule, often with the why |
| Silent edit | User changed duration: 400 to 200 in a file you wrote |
Your default was wrong and their value is the rule. Find these through notices that a file changed outside your edits, or by diffing a file against what you last wrote |
| Repeated nudge | "Smaller." → "Still too big." → "Ok" | Your default was off by the total distance. Record where they landed, not the steps |
| Revert or rejection | "Undo that", picking variant B over A, deleting something you added | What not to do. The why is usually missing, so it goes to Phase 3's questions |
| Confirmed non-obvious choice | "Yes, keep the icon outside the button" | A choice a fresh agent might not repeat. Record it only if a fresh agent would plausibly do otherwise |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +4 lines · -55 tokens per session d624b8cd475e
- 2d ago First seen · 154 lines · 85 tokens per session scan A 3f972e374bda
learn-taste is a skill published in the GitHub repository emilkowalski/skills (56,949 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 2,145 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-13.
learn-taste compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| learn-tasteemilkowalski/skills | Skill | 57k | yesterday | MIT | A | 30 | Claude Code |
| kiro-steering-customgotalab/cc-sdd | Skill | 3.8k | 24d ago | MIT | A | 14 | Claude Code, Codex |
| run-memorygooseworks-ai/goose-skills | Skill | 1.3k | 8d ago | MIT | A | 72 | Claude Code, Codex |
| memory-importPrismer-AI/PrismerCloud | Skill | 1.4k | 24d ago | MIT | A | 111 | Claude Code, Codex |
| deja-reflectvshulcz/deja-vu | Skill | 1.6k | today | MIT | A | 49 | Claude Code |
| identity-snapshotdavekilleen/Dex | Skill | 516 | 16d ago | MIT | A | 74 | Claude Code, Codex |
| memorix-sessionsAVIDS2/memorix | Skill | 935 | 4d ago | Apache-2.0 | A | 31 | Claude Code |