by spacecake-labs · Claude Skill · ★ 373
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.
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 | 373 |
| Forks | 16 |
| Language | TypeScript |
| Category | Claude Skill |
| License | AGPL-3.0 |
| Quality Score | 54/100 |
| Last Updated | 2026-05-06 |
| Created | 2025-07-17 |
| Platforms | claude-code, node |
| Est. Tokens | ~3496k |
spacecake is an open-source desktop app for Claude Code. It combines an integrated terminal, visual markdown editor, and live task tracking. You can run agents, write specs, and see what's happening in one place. For full documentation, visit spacecake.ai. ℹ️ is in public alpha. If you find any bugs, please open an issue in this repo or join us on Discord.
Looking for a spacecake alternative? If you're comparing spacecake 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.
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
A verification-first engineering toolkit for Claude Code. Built for senior ICs and tech leads who already know
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Transform your Claude Code terminal with atomic precision statusline. Features flexible layouts, real-time cos
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: