跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

learn-taste

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

emilkowalski · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add emilkowalski/skills --skill learn-taste

技能说明


name: learn-taste description: Turn a session's design corrections into rules, with their why, in DESIGN.md, a project skill, or a lint check. disable-model-invocation: true

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 bu
阅读完整来源 ↗