Ss restyle
Open-source design-method engine for Claude Code, Codex & Cursor. Gives coding agents fixed design judgment—not one fixed aesthetic—then selects or derives the right grammar from references, locks project decisions, and verifies UI, carousels, decks & docs. 20 skills · MIT.
npx -y skills add bitjaru/styleseed --skill ss-restyleAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Apply one optional StyleSeed aesthetic profile without changing the selected output grammar, product job, or core design judgment.
SKILL.md
1.8 KB, as published. Nobody here has run it
Apply an aesthetic profile
Read PRODUCT-PRINCIPLES.md, RULESETS.md, PRESETS.md, and STYLESEED.md. Profiles are
coordinated visual axes; output grammars organize attention, information, and action. Keep them
separate.
Workflow
- Validate that the lock has one output grammar. If not, run
/ss-setupfirst. - Select exactly one profile from
PRESETS.md, ornone. Never stack profiles. - Apply its coordinated radius, density, type, palette temperature, elevation, motion, composition accent, and signature move inside the output grammar's allowed ranges.
- Preserve deliberate brand values and required fonts when compatible. If incompatible, the output grammar and core invariants win; explain the conflict.
- Update
Aesthetic profileand affected bounded values inSTYLESEED.md. Do not rewrite the output grammar or a reference-compiled rule set. - Run
/ss-scoreto ≥80 and/ss-verifyif renderable. Report the complete effective rule set, not just the profile name.
Rules
- A profile is optional appearance coordination, not a design-method exemption.
technicalprofile does not turn a commerce page into an observability console.editorialprofile does not justify unreadable serif body in a transaction workflow.brutalist-litestill requires coherent states, contrast, and one border language.- Use
/ss-dialfor one-axis changes and/ss-referencefor a new evidence-derived language.