Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI agent developers, AI coders, designers, founders, and product teams who use Claude Code / Codex / Cursor to generate UI and need a design-judgment layer that prevents the 'AI UI that looks generated' trap (default indigo gradient text, sparkle badge, placeholder mock, rainbow lists, missing empty/error states). The 15 slash-command skills are installable via `npx skills add bitjaru/s
Who should use it
Who should skip it
Pass on bitjaru/styleseed if its scope or audience does not match what your team is building right now.
About this signal
bitjaru/styleseed is tracked by RepoRadar as a design engine in the AI Coding section. It was first seen on 2026-07-03 and last updated on 2026-07-03. The current verdict is 'try now' with a Gold tier and easy setup difficulty. The standout signals for bitjaru/styleseed are workflow potential (9.1) and setup ease (8.8), while maturity (6.3) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned bitjaru/styleseed a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.
Risk explanation
The Quality Gate's >=80/100 threshold is a heuristic — review the agent's interpretation of 'one accent', 'grey normal states', 'real empty / error states' on the first few projects before locking it as the team-wide default, because the agent may interpret 'one accent' too strictly for design systems that legitimately need a primary + a secondary + an error color; The 7 brand skins (Toss, Stripe, Linear, Notion, Raycast, Arc, Vercel) cover the realistic starting points for most product teams, but a project with a genuinely custom design language (e.g. a non-listed enterprise brand or a research / academic UI) will need the agent to compose a custom skin via `/ss-setup` rather than picking a default — review the README's 'How StyleSeed differs from... generic design tokens' section before promoting to multi-team deployment; The `STYLESEED.md` lock writes the project's skin, key color, radius, and motion once and makes every agent re-read and obey them on every prompt — review the locked values before merging across branches, because the lock persists across `git pull` and a stale lock from a previous product direction will block the new direction's skin change until the lock is regenerated via `/ss-setup`.