spellbook
Standardizes reusable skill definitions across multiple AI code execution environments, reducing duplication and enabling consistent behavior in multi-agent …
A library of 101 reusable skills and 7 Claude Code agents that installs from one source tree into Claude Code (~/.claude/skills) and Codex (~/.agents/skills). Covers engineering, ops, product, UI, content, and agent workflows, with a validated registry, searchable tags, and selective installs by workflow bundle. Formerly known as Claude Arsenal.
- Automate repetitive coding tasks across Claude Code and Codex environments simultaneously
- Build reusable skill components for multi-agent AI workflow systems
- Execute consistent operations without rewriting logic for different runtime platforms
Standardizes reusable skill definitions across multiple AI code execution environments, reducing duplication and enabling consistent behavior in multi-agent systems where different runtimes handle distinct tasks.
Teams deploying Claude Code alongside other AI agents and requiring unified skill APIs across heterogeneous runtime environments.
https://github.com/majiayu000/spellbook
By majiayu000
How to Get It
curl -fsSL https://raw.githubusercontent.com/majiayu000/spellbook/main/install.sh | bash -s -- --target all
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me automate repetitive coding tasks across Claude Code and Codex environments simultaneously
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- Show HN: I made an esoteric programming language that's read like a spellbook — Hacker News · 176 pts
- The Open Sourcerer's Magic Spell Book — Hacker News · 90 pts
- MIT 6.001 Spellbook (1992) — Hacker News · 73 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 186 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 186 GitHub stars; contributors unknown; last commit 0d ago; license MIT.