by bstaruk · Claude Skill · ★ 84
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
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 | 12 |
| Language | TypeScript |
| Category | Claude Skill |
| Quality Score | 57/100 |
| Last Updated | 2026-04-25 |
| Created | 2017-03-18 |
| Platforms | claude-code, node |
| Est. Tokens | ~193k |
Starbase A Claude-first front-end launchpad. Starbase is an opinionated front-end starter kit built on Vite, TypeScript, React, and Tailwind CSS. Claude Code sits in the co-pilot seat by design. Every convention, component, and architectural decision is shaped to make Claude generate code that actually looks like yours. Liftoff Open http://localhost:3000. You're in orbit.
These tools work well together with starbase for enhanced workflows:
Looking for a starbase alternative? If you're comparing starbase 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.
An opinionated, AI-native development workflow for Java Enterprise — reusable Skills, Agents, Commands, and MC
Claude Conductor - a simple Claude Code framework
Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligen
simple web ui to manage mcp (model context protocol) servers in the claude app
Universal development automation for ANY project. Claude Code implements features, runs tests, creates PRs aut
Admin foundation on FastAPI + React 19 + shadcn/ui — row-level permissions, multi-tab that keeps state, approv
Explore other popular claude skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: