content-design
Skill9 starsChanged 2 months agoMITView on GitHub
Write and repair UI copy: labels, CTAs, errors, empty states, confirmations, onboarding, product voice, localization-ready strings, and AI-sounding prose. Trigger for “copy terasa AI”, “tulisan AI”, “pesan error”, “teks tombol”, “empty state”, “tulisan generik”, or docs/changelog that read like filler. Visual slop stays on anti-slop-design; this skill owns words.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- memi-design/design-skillstheir own version, first seen Nov 8, 2026
- phant0um/claude-skillstheir own version, first seen Oct 15, 2026
- HugoLopes45/design-skillstheir own version, first seen Aug 26, 2026
- mgifford/accessibility-skillstheir own version, first seen Jul 27, 2026
- miovrag/claude-skillstheir own version, first seen Jun 12, 2026
- nalalou/daedalustheir own version, first seen Mar 24, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- mgifford/accessibility-skills★ 48same name
- memi-design/design-skills★ 7same name
- HugoLopes45/design-skills★ 1same name
- miovrag/claude-skills★ 1same name
- nalalou/daedalus★ 1same name
- phant0um/claude-skills★ 0same 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 repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/design-system-enforcer.mdcCursor rule
- frontend-expertSkill
- accessibilitySkill
- anti-slop-codeSkill
- anti-slop-designSkill
- app-shellSkill
- architectureSkill
- componentsSkill
- data-fetchingSkill
- design-colorSkill
- design-directionSkill
- design-foundationsSkill
- design-surfacesSkill
- design-typographySkill
- design-vocabularySkill
- devtoolsSkill
- engineering-vocabularySkill
- fidelitySkill
- formsSkill
- frontend-expertSkill
- marketingSkill
- monitoringSkill
- motion-inspectionSkill
- motionSkill
- performanceSkill
- polishSkill
- prototypeSkill
- quality-loopSkill
- responsiveSkill
- seoSkill
- skill-authoringSkill
- testingSkill
- tokensSkill
- webglSkill
The file
Files
Content Design
Overview
Copy helps someone understand, act, and recover. Product facts beat generic enthusiasm. AI-sounding prose is a content defect, not a separate pack domain.
When to use
- Labels, buttons, help, empty/error/success, confirmations, onboarding
- “Tulisan AI” / copy that sounds generated
- Terminology, voice, or localization-ready strings
- README, changelog, docs, or marketing sentences that read like filler
When to skip
- Visual rendering, wrapping, truncation →
design-typography - Validation mechanics →
forms - Landing section stack / IA →
marketing - Purple/gradients/Lorem-as-layout →
anti-slop-design(then replace Lorem here) - Generated hooks/
any/empty wrappers →anti-slop-code
MUST
| Rule | Detail |
| Preserve facts | Never invent capabilities, metrics, quotes, logos, or guarantees |
| Unknown ≠ fiction | If retry, reversibility, or scope is unknown, ask or say so |
| Action-led | Buttons name the action; errors name what happened and the next step |
| Consequence-first | Destructive copy names object, outcome, and whether it can be undone |
| One term | One concept keeps one name across the flow |
| Localization-ready | Whole sentences; no concatenated fragments; don’t depend on layout direction |
| Before/after | Review work shows concrete rewrites, not vibe notes |
AI-writing scan
| Pattern | Fix |
| Unlock / elevate / seamless / next-gen | Name the actual job |
| “Something went wrong.” | What failed + retained state + recovery |
| “Are you sure?” | Named object + consequence |
| Stacked adjectives | One concrete noun phrase |
| Fake metrics or testimonials | Delete, or use a real sourced fact |
| Throat-clearing intros | Start at the action |
| Repeated summary conclusions | Cut the echo |
Workflow
- Inventory — audience, task, known facts, terms, tone, states.
- Scan — hype, missing recovery, inconsistency, translation risk.
- Rewrite — meaning, action, consequence, or recovery first.
- Fit — realistic length and expansion; don’t truncate away meaning.
- Verify — before/after; no invented facts; flow still complete.
Boundaries
- May decide: concise wording in the product’s existing voice.
- Must not: fabricate proof, hide consequences, or treat visual truncation as a copy fix.
Checklist
- Facts inventoried; unknowns labeled
- CTA / error / empty / destructive copy is specific
- AI-writing scan clean
- Before/after shown for review work
- Strings survive expansion
Depth
Full guide: references/content-design.md.
Visual slop catalog: references/anti-patterns.md.
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.