by jdevalk · MCP Server · ★ 923
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
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 | 923 |
| Forks | 53 |
| Language | TypeScript |
| Category | MCP Server |
| Quality Score | 60/100 |
| Open Issues | 2 |
| Last Updated | 2026-11-04 |
| Created | 2026-05-29 |
| Platforms | browser, mcp, node |
| Est. Tokens | ~15k |
The Website Specification The website specification — from to , from WCAG contrast to . Platform-agnostic, sourced on every page, written for humans and agents. MIT licensed, open for pull requests. Live site:
These tools work well together with specification.website for enhanced workflows:
Looking for a specification.website alternative? If you're comparing specification.website with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
GEO Optimizer, the open-source engine behind GeoReady (geoready.dev): audit whether ChatGPT, Perplexity, Gemin
The website QA tool for your coding agent. 310+ audit rules across SEO, performance, security, accessibility a
⚒️ Open-source game wiki template. Astro + Cloudflare Pages. Free, fast, beginner-friendly. Static-first, zero
A search-first, profile-aware reverse-engineering workspace for AI agents — 735 tools across 36 domains in one
Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required.
Claude Code skill for improving website AEO (AI Engine Optimization) and GEO (Generative Engine Optimization)
Explore other popular mcp server 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: