learn-taste
Skill6.4k starsChanged todayMITView on GitHub
Turn a session's design corrections into rules, with their why, in DESIGN.md, a project skill, or a lint check.
6 other projects use a version of this, 2 of them edited; 1 of 1 edited versions we compared changed its rules.
How people change it
1 of 1 edited versions changed its rules.
Of the 1 edited version we compared: 1 made changes of their own.
Rules people drop
- 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.dropped by 1 of 1
We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- christofferbergj/agent-skillsedited, first seen Nov 16, 2026
- atpaawej/opencode-skillpackword for word, first seen Nov 16, 2026
- malinskibeniamin/skillstheir own version, first seen Nov 16, 2026
- anis-dr/skillsedited, first seen Nov 16, 2026
- boraoztunc/skillsword for word, first seen Nov 15, 2026
- emilkowalski/skillsword for word, first seen Nov 15, 2026
Who's talking about sanity-io/sanity
- sanity-io/sanity-plugin-media“(feat) Option to insert multiple images”GitHub · May 21, 2024 · 15 reactions
- nuxt-modules/sanity“Typegen cannot generate types from plugins”GitHub · Feb 5, 2026 · 12 reactions
- ricokahler/sanity-codegen“Feature request: Sanity v3 support”GitHub · Sep 2, 2022 · 7 reactions
- nuxt-modules/sanity“Generate query types automatically”GitHub · Jul 17, 2025 · 5 reactions
- sanity-io/next-sanity“fix(deps): update sanity monorepo to v6.11.0”GitHub · Aug 18, 2026 · 3 reactions
The biggest 5 of 29 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 29
Talked about on GitHub and Stack Overflow (29 times).
On GitHub · 24
- May 21, 2024(feat) Option to insert multiple images — sanity-io/sanity-plugin-media15 reactions · 9 comments
- Feb 5, 2026Typegen cannot generate types from plugins — nuxt-modules/sanity12 reactions · 3 comments
- Sep 2, 2022Feature request: Sanity v3 support — ricokahler/sanity-codegen7 reactions · 8 comments
- Jul 17, 2025Generate query types automatically — nuxt-modules/sanity5 reactions · 5 comments
- Aug 18, 2026fix(deps): update sanity monorepo to v6.11.0 — sanity-io/next-sanity3 reactions · 3 comments
19 more on GitHub
- Aug 1, 2023fix: bump "@sanity/schema" dependency version to resolve invalid export — sanity-io/sanity-naive-html-serializer2 reactions · 2 comments
- Oct 30, 2026build(deps-dev): bump the development-dependencies group across 1 directory with 27 updates — CloudNativeBergen/website1 reaction · 3 comments
- Oct 30, 2026build(deps): bump the production-dependencies group across 1 directory with 31 updates — CloudNativeBergen/website1 reaction · 2 comments
- Oct 11, 2026chore(deps-dev): bump the development-dependencies group across 1 directory with 24 updates — CloudNativeBergen/website1 reaction · 3 comments
- Oct 11, 2026chore(deps): bump the production-dependencies group across 1 directory with 26 updates — CloudNativeBergen/website1 reaction · 3 comments
- Oct 2, 2026chore(deps-dev): bump the development-dependencies group across 1 directory with 22 updates — CloudNativeBergen/website1 reaction · 3 comments
- Oct 1, 2026chore(deps-dev): bump the development-dependencies group with 18 updates — CloudNativeBergen/website1 reaction · 3 comments
- Oct 1, 2026chore(deps): bump the production-dependencies group with 25 updates — CloudNativeBergen/website1 reaction · 3 comments
- Sep 4, 2026chore(deps-dev): bump the development-dependencies group across 1 directory with 13 updates — CloudNativeBergen/website1 reaction · 2 comments
- Sep 1, 2026chore(deps-dev): bump the development-dependencies group with 20 updates — CloudNativeBergen/website1 reaction · 1 comment
- Aug 4, 2026chore(deps): bump the production-dependencies group across 1 directory with 3 updates — CloudNativeBergen/website1 reaction · 4 comments
- Aug 4, 2026chore(deps): bump the production-dependencies group across 1 directory with 4 updates — CloudNativeBergen/website1 reaction · 2 comments
- Aug 4, 2026chore(deps): bump the production-dependencies group across 1 directory with 5 updates — CloudNativeBergen/website1 reaction · 2 comments
- Aug 4, 2026chore(deps-dev): bump the development-dependencies group across 1 directory with 4 updates — CloudNativeBergen/website1 reaction · 2 comments
- Aug 4, 2026chore(deps-dev): bump the development-dependencies group across 1 directory with 5 updates — CloudNativeBergen/website1 reaction · 2 comments
- Aug 4, 2026chore(deps-dev): bump the development-dependencies group across 1 directory with 7 updates — CloudNativeBergen/website1 reaction · 2 comments
- Aug 4, 2026chore(deps): bump the production-dependencies group across 1 directory with 5 updates — CloudNativeBergen/website1 reaction · 2 comments
- Aug 4, 2026chore(deps): bump the production-dependencies group across 1 directory with 7 updates — CloudNativeBergen/website1 reaction · 2 comments
- May 7, 2024fix(typeEvlauator): handle rest on object splat operations — sanity-io/groq-js1 reaction · 7 comments
On Stack Overflow · 5
- Feb 17, 2020Filter query result by field value inside array of objects [Sanity.io & GROQ]3 votes
- May 8, 2022Websocket failed when first time rendering - React1 vote
- Mar 17, 2025Sanity desk error: Could not fetch list items Error: Could not establish EventSource connection0 votes
- Feb 24, 2023Can't login to Sanity via VSC terminal0 votes
- Jan 7, 2022npm run graphql-deploy command stuck in Sanity0 votes
Other versions6 projects use a version of this.
Word for word · 3
- emilkowalski/skills★ 57k100% same
- boraoztunc/skills★ 473100% same
- atpaawej/opencode-skillpack★ 0100% same
Edited · 2
- anis-dr/skills★ 499% same
- christofferbergj/agent-skills★ 197% same
Wrote their own version · 1
- malinskibeniamin/skills★ 4same 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 repository54 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- animateSkill
- animation-performanceSkill
- animation-vocabularySkill
- apple-designSkill
- ask-emilSkill
- ask-sonnerSkill
- before-and-afterSkill
- break-uiSkill
- choreographSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- deslopSkill
- emil-design-engSkill
- find-animation-opportunitiesSkill
- find-skillsSkill
- gesturesSkill
- grill-meSkill
- improve-animationsSkill
- improve-codebase-architectureSkill
- migrate-styled-components-to-panda-cssSkill
- mobile-nativeSkill
- modern-web-guidanceSkill
- performance-optimizationSkill
- pick-ui-librarySkill
- playwright-best-practicesSkill
- playwright-cliSkill
- pr-descriptionSkill
- prototypeSkill
- react-devtoolsSkill
- react-rx-hook-auditSkill
- remove-animationsSkill
- review-animationsSkill
- rxjs-like-a-proSkill
- sanity-benchSkill
- sanity-config-reducersSkill
- sanity-default-pluginsSkill
- sanity-i18n-translateSkill
- sanity-plugin-authoringSkill
- sanity-radar-investigateSkill
- sanity-radarSkill
- sanity-tsdown-configSkill
- sanity-ui-migration-progressSkill
- sanity-visual-coverageSkill
- sanity-visual-regressionSkill
- storiesSkill
- storybook-initSkill
- storybook-setupSkill
- storybook-upgradeSkill
- tddSkill
- vercel-react-best-practicesSkill
- write-a-skillSkill
The file
We split this skill into the rules it gives an agent
10 rules. 8 are common, 1 is distinctive, and 1 is very specific to this project.
8
Common
Most of the 3 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
- Common: line 15
Only the user's taste: Every rule traces back to something the user said, edited, or confirmed.
- Common: line 16
Never invent a why: If the user gave no reason, propose one marked *inferred* and get it confirmed before writing.
- Very specific: line 25
Read the current conversation from the first turn.
- Common: line 41
Completion criterion: every turn has been read, and every correction is listed with its source quote or diff.
- Common: line 62
Completion criterion: every Phase 1 correction ends as Skipped, Rewrite, Conflict, Check candidate, or a rule to generalize.
- Common: line 74
If the same correction came up on two or more different components, that's evidence for the class level.
- Common: line 76
Write the rule strictly: values and token names from this codebase, "always" or "never", no "prefer" or "try to".
- Common: line 82
Completion criterion: every kept rule has a level and a why marked as the user's or *inferred*.
- Distinctive: line 97
Create DESIGN.md or the section if it's missing.
- Common: line 148
If the session had no taste corrections, say so in one line.
“Common” is measured: kept by at least 6 in 10 of the 3 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.
Files
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 |
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:
| Level | Example | Verdict |
| 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 · CopyCreate 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 said | Rule | Why | Where |
| 1 | "no, semi-transparent shadow, not a border" | Raised surfaces use shadow-raised, never a solid border | Solid borders look flat and heavy; shadows adapt to both themes | DESIGN.md › Surfaces |
| 2 | Changed duration: 400 → 200 in Dropdown.tsx | Dropdowns open in 200ms | inferred: 400ms felt sluggish on a surface opened many times a day | DESIGN.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
| Invocation | Behavior |
/learn-taste | Current session, full workflow, stop at the report |
/learn-taste <sessions> | Also read the named or most recent N session transcripts |
write all / write 1, 3 | Write the approved items from the last report |
/learn-taste prune | Read DESIGN.md and propose merges for duplicates, fixes for contradictions, and stricter wording for vague rules. Same propose-then-stop rule |
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.

