📄 skillActiveCuratedhigh

microsoft/waza

CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness

Supported Platforms

🤖 Claude Code🧠 Codex

Stars

991

Skill Type

🔍 Code Quality & Review

Quality Score

120/200

License

MIT

Forks

Last Updated

Jun 11, 2026

Discovered

May 10, 2026

Validation

Passed

github.com/microsoft/waza

Quality Breakdown

120/ 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.

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.

Install script execution via curl pipe to bash (install.sh) - requests shell execution without user review of script contents
Git LFS artifacts embedded in repository - potentially includes compiled binaries (copilot binaries mentioned) that cannot be easily audited
Multi-agent orchestration framework (.squad-templates, .github/agents/squad.agent.md) - evidence of autonomous agent spawning and coordination capabilities
Copilot integration (.copilot/ directory with session state and MCP configuration) - external AI model integration with persistent state
Automated GitHub workflows with elevated permissions (auto-merge, release, triage, promote workflows) - autonomous operations without explicit approval gates
Command execution examples in codebase (command-execution/main.go, exec_stream_session.go) - demonstrates remote command execution capabilities