redesign-skill
Skill1 starsChanged 11 days agoMITView on GitHub
Improve existing codebases systematically: scan the UI, diagnose issues across 8 categories, fix in priority order. Never breaks existing functionality. Do NOT use for greenfield projects.
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Use when: upgrading visual design of existing codebase.
- Very specific: line 39
Before scanning, run bash scripts/design-upgrade.sh to extract existing tokens from the codebase into DESIGN.md.
- Very specific: line 43
Before touching code, run the full audit from frontend-web/REDESIGN-GUIDE.md:
- Distinctive: line 77
Do not break existing functionality — visual changes only unless data is wrong.
- Very specific: line 78
Check package.json before adding dependencies.
- Very specific: line 80
Update DESIGN.md and DESIGN-LOCK.md after approval.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Redesign Skill
Scope: Existing projects that need a visual upgrade. Not for greenfield builds.
When to Use
Use when: upgrading visual design of existing codebase. Not for greenfield projects.
When NOT to Use
- Greenfield projects (use build skills instead)
- Framework migrations or stack changes
- Performance optimization without visual changes
Output Contract
| Artifact | Format | Location | Quality Criteria |
| Visually redesigned source code (font swap, color system, interactive states, layout, components, missing states, typography) | Modified source files (CSS, markup, component files) — same framework, same structure | Existing source tree | All 87 checks across 8 categories scanned from REDESIGN-GUIDE.md, severity-diagnosed (🔴🟡🔵⚪), 7-step priority order applied, no existing functionality broken, same framework preserved, one fix category per commit, post-redesign visual verification performed, DESIGN.md + DESIGN-LOCK.md updated |
Process: Extract → Scan → Diagnose → Fix
Phase 0: Extract Existing Design System
Before scanning, run bash scripts/design-upgrade.sh to extract existing tokens from the codebase into DESIGN.md. This ensures the redesign builds on the actual design system, not a guessed one.
Phase 1: Scan
Before touching code, run the full audit from frontend-web/REDESIGN-GUIDE.md:
- Typography (12 checks)
- Color & Surfaces (15 checks)
- Layout (14 checks)
- Interactivity & States (10 checks)
- Content (12 checks)
- Component Patterns (10 checks)
- Iconography (7 checks)
- Code Quality (7 checks)
Phase 2: Diagnose
Categorize findings:
| Severity | Definition | Action |
| 🔴 Critical | Accessibility failure, broken layout, unreadable text | Fix immediately |
| 🟡 High | AI tells, banned defaults, missing states | Fix in this pass |
| 🔵 Medium | Suboptimal spacing, inconsistent tokens | Fix if time allows |
| ⚪ Low | Nice-to-have polish | Document for future |
Phase 3: Fix (Priority Order)
- Font swap — Replace Inter/Roboto with Geist, Satoshi, Outfit
- Color palette — Replace AI defaults with intentional system, add CSS variables
- Hover/active/focus states — Add to all interactive elements
- Layout & spacing — Hero overflow, nav wrapping, section consistency
- Component replacement — Card grids, spec sheets, eyebrow overuse
- States — Add loading (skeleton), empty, error states
- Typography polish — Line-height, max-width, italic clearance, eyebrow count
Rules
- Work with existing stack. Do not switch frameworks.
- Do not break existing functionality — visual changes only unless data is wrong.
- Check
package.jsonbefore adding dependencies. - One fix category per commit. Keep changes reviewable.
- Update
DESIGN.mdandDESIGN-LOCK.mdafter approval.
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- PIXARTSeu/Synapse★ 9same name
- HarambeeAI/bayes-ship★ 1same 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 repository59 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/CLAUDE.mdCLAUDE.md
- adapt-skillSkill
- api-and-interface-designSkill
- architecture-analysisSkill
- audit-skillSkill
- backend-api-masterySkill
- browser-testing-with-devtoolsSkill
- ci-cd-and-automationSkill
- clarify-skillSkill
- cli-toolsSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- context-engineeringSkill
- critique-skillSkill
- customize-opencodeSkill
- debugging-and-error-recoverySkill
- debugging-three-strikesSkill
- delight-skillSkill
- deprecation-and-migrationSkill
- dev-environment-auditSkill
- documentation-and-adrsSkill
- doubt-driven-developmentSkill
- engineering-fundamentalsSkill
- frontend-desktopSkill
- frontend-mobileSkill
- frontend-pwaSkill
- frontend-ui-engineeringSkill
- frontend-webSkill
- fullstack-shippingSkill
- gateSkill
- git-init-and-versioningSkill
- git-workflow-and-versioningSkill
- hard-skillSkill
- idea-refineSkill
- incremental-implementationSkill
- industrial-brutalist-uiSkill
- interview-meSkill
- minimalist-uiSkill
- multi-agent-orchestrationSkill
- observability-and-instrumentationSkill
- optimize-skillSkill
- output-skillSkill
- performance-optimizationSkill
- planning-and-task-breakdownSkill
- polish-skillSkill
- project-health-checkSkill
- project-metricsSkill
- security-and-hardeningSkill
- self-improvementSkill
- shipping-and-launchSkill
- skill-creatorSkill
- skill-improverSkill
- soft-premium-uiSkill
- source-driven-developmentSkill
- spec-driven-developmentSkill
- test-driven-developmentSkill
- typeset-skillSkill
- user-onboardingSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

