by stevembarclay · Claude Skill · ★ 50
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/stevembarclay/pencilplaybook ~/.claude/skills/PencilPlaybook
git clone https://github.com/stevembarclay/pencilplaybook .claude/skills/PencilPlaybookTaken 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 | 50 |
| Forks | 3 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 63/100 |
| Last Updated | 2026-03-25 |
| Created | 2026-03-24 |
| Platforms | claude-code, python |
| Est. Tokens | ~16k |
PencilPlaybook Install once. Claude now knows why disabled buttons are 40% opacity, not 50%. That specificity — defensible, tested, perceptually grounded — is what separates production UI from AI slop. PencilPlaybook embeds those rules directly into Claude Code, so every Pencil.dev session automatically gets the values a senior designer carries in their head.
Looking for a pencilplaybook alternative? If you're comparing pencilplaybook 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.
Design intelligence engine for AI coding tools (Claude Code, Cursor, Windsurf). Deterministic anti-AI-slop lin
Audits AI-generated frontend and rewrites it so it stops looking AI-made: purple-gradient slop and the "tastef
The elite design intelligence layer for AI agents, synthesized from 10+ legendary design books. It primes your
🎨 Open-source design MCP server + shadcn/ui registry — AI design systems for Claude Code, Cursor, Codex, GitH
World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociatio
人間にも、AIにも、読めるデザインシステム — AI-Ready Design System for Claude Code & Cursor
Explore other popular claude skill 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: