Skill of Skills
🔌 pluginActivePromisingcritical

genie

by automagik-dev

Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.

Stars

323

Skill Type

🚀 CI/CD & Deployment

Quality Score

107/200

License

MIT

Forks

52

Last Updated

Jun 11, 2026

Discovered

Mar 27, 2026

Validation

Passed

github.com/automagik-dev/genie

Quality Breakdown

107/ 200

Content Signals

â—‹Gotchas/Edge Cases+40
✓Progressive Disclosure+30
â—‹Trigger Description+20
â—‹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

critical

Manual security review required. Use with extreme caution.

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

  • Autonomous multi-agent spawning system: Described as 'dispatches parallel agents in isolated worktrees' with no explicit human approval gates shown
  • Shell script execution capability: Contains .genie/agents/metrics-updater/tools with bash scripts (backfill.sh, collect-stats.sh, run-metrics.sh) that execute autonomously
  • Persistent configuration storage: .claude/ and .genie/ directories indicate persistent config modification and agent state management
  • Bootstrap/install automation: README explicitly mentions curl-based installer (curl -fsSL https://get.automagik.dev/genie | bash) that downloads and executes code from external CDN
  • Complex agent orchestration: Multi-agent architecture with isolated worktrees, messaging system (NATS streaming references), and autonomous decision-making
  • Code review bypass potential: 'reviews code before you see it' indicates autonomous code modification and PR generation without guaranteed human review