by educlopez · Agent Tool · ★ 84
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npx design-bites add linear.app
npx design-bites listTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 84 |
| Forks | 11 |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 72/100 |
| Last Updated | 2026-10-02 |
| Created | 2026-04-10 |
| Platforms | browser |
| Est. Tokens | ~17k |
design-bites Design systems decoded for AI agents. Curated DESIGN.md files auto-extracted from the world's best-designed websites. Browse on sparkbites.dev • Get started • CLI • How it works • Twitter What is
Looking for a design-bites alternative? If you're comparing design-bites with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Figma plugin that extracts local style guidelines and generates DESIGN.md and SKILL.md files for AI tools such
Stop Claude Code/Cursor from guessing UI. Extract any website's design system into a spec-valid DESIGN.md that
Generate Google Stitch compatible DESIGN.md files from any website using AI vision. Bring your own Gemini, Ope
Claude Code skills for the work that keeps a design system alive
Extract design tokens (colors, typography, spacing, border radius, shadows) from any public website. Generates
Audits AI-generated frontend and rewrites it so it stops looking AI-made: purple-gradient slop and the "tastef
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: