⌨️ cli toolActivePromisinghigh

clowder-ai

by zts212653

Build AI teams, not just agents. Hard rails, soft power, shared mission.

Stars

1.2k

Skill Type

🏗️ Code Scaffolding & Templates

Quality Score

94/200

License

MIT

Forks

381

Last Updated

Jun 11, 2026

Discovered

Mar 27, 2026

Validation

Passed

github.com/zts212653/clowder-ai

Quality Breakdown

94/ 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

high

Broad system access required. Carefully review permissions before installing.

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

  • Contains .claude/ directory with persistent configuration hooks (claude-settings.template.json, session-start-recall.sh, session-stop-check.sh) that modify Claude AI tool behavior and settings
  • Multiple shell scripts (.sh files) in hyperfocus-brake skill module designed to run as hooks and pre-tool checks, enabling autonomous execution without explicit user approval
  • CLAUDE.md and AGENTS.md files indicate framework for building multi-agent AI teams with orchestration capabilities
  • Bootstrap automation present (BOOTSTRAP.md, cat-cafe-skills/BOOTSTRAP.md) suggesting installation and setup scripts that modify system state
  • Manifest-driven skill system (manifest.yaml) that loads external capabilities and tools automatically
  • Hook-based architecture (hook.sh, pretool-brake-check.sh) that intercepts and modifies tool execution flow, representing autonomous operation gates