learn-taste

作者: emilkowalski

Turn a session's design corrections into rules, with their why, in DESIGN.md, a project skill, or a lint check.

npx skills add https://github.com/emilkowalski/skills --skill learn-taste

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

  1. 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.
  2. 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.
  3. 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.
  4. 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.
  5. 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:

SignalExampleWhat it tells you
Explicit correction"No, semi-transparent shadow, not a border"The rule, often with the why
Silent editUser changed duration: 400 to 200 in a file you wroteYour 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 addedWhat 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

For each one, capture the user's exact words (or the diff), what you had done, what they wanted instead, and any reason they gave.

Skip what isn't taste: functional bugs, content specific to one screen ("the headline should say Pricing"), and corrections to your understanding of the task.

Completion criterion: every turn has been read, and every correction is listed with its source quote or diff.

Phase 2: Filter

Walk every correction through this tree:

Would a fresh agent building a DIFFERENT component in this repo make the same mistake?
├── No (a one-off: this campaign's color, this page's layout) → Skipped
└── Yes
    ├── Does an existing rule cover it? Check DESIGN.md, CLAUDE.md / AGENTS.md, project skills.
    │   ├── Yes, and it says the same thing → The rule failed. Rewrite it stricter
    │   │   (a number, a token, "never") instead of adding a duplicate.
    │   ├── Yes, and it contradicts → Conflict. Show both; the user picks.
    │   └── No → continue
    ├── Can a violation be found by matching code? → Check candidate.
    │   Keep a one-line rule too, so the why is recorded somewhere.
    └── Did the user say it applies everywhere, not just here? → Ask where their global rules live.
        Otherwise it's a project rule.

Completion criterion: every Phase 1 correction ends as Skipped, Rewrite, Conflict, Check candidate, or a rule to generalize.

Phase 3: Generalize and find the why

Pick the narrowest level that would have prevented the mistake on the next, different component:

LevelExampleVerdict
Instance"The pricing card gets a shadow, not a border"Too narrow: it only protects this card
Class"Raised surfaces (cards, popovers, menus) separate from the background with shadow-raised, never a solid border"Write this
Universal"Never use borders"Too broad: breaks inputs, dividers, tables

If the same correction came up on two or more different components, that's evidence for the class level. If two levels both seem right, ask.

Write the rule strictly: values and token names from this codebase, "always" or "never", no "prefer" or "try to". Use softer wording only when the user framed it as a preference.

Then the why. Use the user's reason, in their words, when they gave one. Otherwise write your best candidate, mark it inferred, and put it in the questions for the user.

Self-test before proposing: read only the rule and its why, then picture the original task. Would an agent that knows nothing else produce what the user wanted? If it could still produce the wrong version, the rule is too vague. Add the value, the token, or the exception.

Completion criterion: every kept rule has a level and a why marked as the user's or inferred.

Phase 4: Decide where it goes

Check candidate?
├── Yes → lint rule, token restriction, or test, plus a one-line rule in DESIGN.md
└── No
    ├── Is DESIGN.md's section for this aspect over ~40 lines, AND relevant to only some tasks
    │   (motion rules don't matter when building a settings form)?
    │   └── Yes → move the whole section into a project skill and leave a one-line pointer in DESIGN.md
    └── Default → DESIGN.md at the repo root, under the matching section:
        Surfaces · Color · Typography · Spacing & layout · Motion · Interaction · Copy

Create DESIGN.md or the section if it's missing.

Make sure it gets read. A DESIGN.md that no agent loads changes nothing. If neither CLAUDE.md nor AGENTS.md points to it, propose adding this line to whichever one the project uses: Before building or changing UI, read DESIGN.md.

Entry format:

## Surfaces

- **Raised surfaces (cards, popovers, menus) use `shadow-raised`, never a solid border.**
  Why: a solid border makes a raised surface look flat and heavy; a semi-transparent shadow separates it from the background and adapts to both themes.
  <!-- 2026-11-12: "no, semi-transparent shadow, not a border" -->

The comment holds the date and the user's words. When a later correction conflicts, it shows which rule is newer and what the user actually said.

Phase 5: Report and stop

Present the report below, then stop.

Phase 6: Write on approval

Write only the approved items. Show the resulting diff of DESIGN.md (and any skill or config file). For a check, implement it and run it across the codebase. If it flags existing code, report the count and ask whether to make it a warning or fix the violations. Never fix them without asking, because that changes component code.

Required Output Format

Rules to add

#You saidRuleWhyWhere
1"no, semi-transparent shadow, not a border"Raised surfaces use shadow-raised, never a solid borderSolid borders look flat and heavy; shadows adapt to both themesDESIGN.md › Surfaces
2Changed duration: 400 → 200 in Dropdown.tsxDropdowns open in 200msinferred: 400ms felt sluggish on a surface opened many times a dayDESIGN.md › Motion

Needs your answer

Each inferred why, each ambiguous generalization level, and each global-or-project question. One line each, with your recommendation.

Conflicts

The existing rule, the new correction, and which one you'd keep.

Make it a check

Each check candidate with its exact implementation (the rule config or test), and what it would flag in the current codebase.

Skipped

One line per skipped correction and why, so the user can override.

Close with: "Say write all or write 1, 3, and answer the questions above."

If the session had no taste corrections, say so in one line. That's a good result, not a failure.

Invocation Variants

InvocationBehavior
/learn-tasteCurrent session, full workflow, stop at the report
/learn-taste <sessions>Also read the named or most recent N session transcripts
write all / write 1, 3Write the approved items from the last report
/learn-taste pruneRead DESIGN.md and propose merges for duplicates, fixes for contradictions, and stricter wording for vague rules. Same propose-then-stop rule

来自 emilkowalski 的更多技能

animate
emilkowalski
从零开始构建动画,按顺序做出决定,以判断动画是否合适——是否应该动画化,目的为何,使用哪种工具,哪些属性,哪种曲线和时长,如何被打断,如何退出。编写实现代码。当被要求为某物添加动画、增加动态效果、让组件有生命力,或构建过渡效果时使用。若要批评现有动态效果,使用review-animations;若要审计整个代码库,使用improve-animations。
animate-expo
emilkowalski
在 React Native 和 Expo 中构建动画,按照决定动画效果是否自然的顺序做出选择——是否需要动画、在哪个线程运行、使用哪些属性、采用弹簧还是定时动画、手势如何交接,以及如何降级。使用 Reanimated、Gesture Handler、Expo Router 和 expo-haptics 编写实现。适用于在 Expo 应用中为任何内容添加动画、添加手势、底部面板、屏幕过渡、按压反馈或触觉反馈,或修复设备上卡顿的动画。用于……
developmentdesign
animation-performance
emilkowalski
Keep web animations inside the frame budget — animate composite-only properties, keep motion off the main thread when the page is busy, and find the cause when an animation drops frames. Use when an animation is janky, choppy, stutters, or drops frames; when choosing which property to animate; when deciding between CSS and JS animation on performance grounds; or when reaching for `will-change` or GPU layers. For choosing easing, duration, or whether to animate at all use animate; for...
developmentdesign
animation-vocabulary
emilkowalski
反向查找词汇表,将关于网页动画或运动效果的模糊描述转化为精确术语(例如:“弹出窗口打开时的弹跳效果” → 弹入;“iOS的橡皮筋滚动” → 橡皮筋回弹)。当用户问“那个叫什么来着……”,或描述一个运动效果但
researchdesigncreative
apple-design
emilkowalski
苹果界面设计与流畅物理动效的方法论,专为网页端转化。适用于构建或审查手势驱动UI、弹簧动画、拖拽/滑动/面板交互、动量与可中断过渡、半透明材质与纵深、排版(光学字号、字距、行距)、减弱动态效果,或苹果风格界面背后的设计基础(反馈、空间一致性、克制)。
ask-emil
emilkowalski
询问哪种技能或流程适合你的情况。一个用于路由到此仓库中各项技能的路由器。
developmentproductivity
ask-sonner
emilkowalski
Sonner(React 弹窗通知库)使用指南——安装并接入 Toaster、选择合适的 toast() 调用、处理 promise 和加载状态的 toast、更新、关闭和持久化 toast、样式、主题和图标、定位以及多个 Toaster。适用于使用 Sonner 或排查相关问题的情况——例如 toast 不显示、重复显示、样式丢失、忽略 Tailwind 类、被模态框遮挡,或不跟随深色模式。
break-ui
emilkowalski
Try to break a piece of UI by feeding it worst-case data — long names, unbreakable emails, one-letter names, missing fields, huge counts, zero items, long labels, non-Latin text, emoji, extreme numbers — then render it behind a "Demo data / Worst case" toggle and report everything that broke, with the fix for each. Use when the user asks to stress-test, break, or find edge cases in a component or screen, or to "try the worst case". For visual design critique use emil-design-eng; for motion...
testingdesigndevelopment