No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Ilm-Alan · Claude Skill · ★ 126
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is frontend-design safe to install? View the security audit →
frontend-design Frontend design skill for Claude Code, Codex, and Gemini CLI. Eight aesthetic anchors, each locking palette, typography, and texture to specific CSS tokens. Pick one per brief. Install Claude Code Codex Gemini CLI Enable experimental skills in : Then: Verify with . How it works Each anchor locks specific palette, typefaces, and texture tokens. Picking an anchor commits to those tokens, not to a vibe. Before any code, the skill asks for: An anchor, picked with a bias toward unexpected pairings. A memorable anchor-internal move. CSS that matches the chosen anchor's tokens. If the rendered tokens drift outside the anchor's range, the anchor didn't hold. The eight anchors Pure primary colors, system fonts (Times, Helvetica, Courier), hard offset shadows Xpx
| Stars | 126 |
| Forks | 18 |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 67.1486103614872/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-26 |
| Created | 2026-01-11 |
| Platforms | claude-code, cli, codex, gemini |
| Est. Tokens | ~12k |
These tools work well together with frontend-design for enhanced workflows:
Looking for a frontend-design alternative? If you're comparing frontend-design with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
偏执型设计顾问：反 AI 味设计 + 风格试衣间 + 58 站设计系统库的 Claude Code Skill | Opinionated design advisor for Claude Code: anti-gen
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor
Complete Kaggle integration plugin/skill for AI coding agents — competition reports, dataset/model downloads,
Audits AI-generated frontend and rewrites it so it stops looking AI-made: purple-gradient slop and the "tastef
👁️ The visual layer for CLI coding agents. Pipe JSON → interactive native UI → modified JSON back. Like fzf,
Explore other popular claude skill tools:
frontend-design is Frontend design skill for Claude Code, Codex, and Gemini CLI. Eight aesthetic anchors, each locking palette, typography, and texture to specific CSS tokens. Pick one per brief.. It is categorized as a Claude Skill with 126 GitHub stars.
You can find installation instructions and usage details in the frontend-design GitHub repository at github.com/Ilm-Alan/frontend-design. The project has 126 stars and 18 forks, indicating an active community.
frontend-design is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to frontend-design on Agent Skills Hub include qiaomu-design, compose-skill, agent-designer. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: