Skill of Skills
📄 skillActivePromisingmedium

novuhq/novu

by novuhq

The open-source communication infrastructure for agents and products

Supported Platforms

🤖 Claude Code🖱️ Cursor🧠 Codex

Stars

39.1k

Skill Type

📖 Library & API Reference

Quality Score

87/200

License

Not specified

Forks

4.3k

Last Updated

Jul 13, 2026

Discovered

Jun 12, 2026

Validation

Passed

github.com/novuhq/novu

Quality Breakdown

87/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
○Verification/Safety+20
○Code Examples+15
○Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Repository contains .cursor/ and .claude/ configuration directories with custom agent definitions and scripts that could modify AI tool behavior
  • .cursor/scripts/ directory contains shell scripts (install.sh, start.sh, scan.sh) that execute arbitrary commands
  • Multi-agent spawning capability evidenced by .cursor/agents/ and .agents/ directories with agent definitions (impact-checker.md, verifier.md, openai.yaml)
  • Persistent configuration modification vectors through .cursor/settings.json and .claude/ configuration persistence
  • .cursor/scripts/dead-code/scan.sh is a bash script that could execute during repository operations
  • Agent skill definitions in .agents/skills/ and .cursor/skills/ directories enable extended autonomous capabilities