📄 skillActivePromisingmedium

trailblaze

AI-driven UI testing framework.

Supported Platforms

🤖 Claude Code

Stars

236

Skill Type

🧪 Product Verification

Quality Score

117/200

License

Apache-2.0

Forks

Last Updated

Jun 11, 2026

Discovered

Apr 17, 2026

Validation

Passed

github.com/block/trailblaze

Quality Breakdown

117/ 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.

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.

Install script present (install.sh via curl | bash pattern in README) - potential for elevated privilege execution
GitHub Actions workflows (.github/workflows/) with PR and release automation that execute build and test scripts
Shell scripts in .github directory (.github/pr_*.sh) that execute potentially complex operations
Gradle build configuration with custom plugins that execute code during build (build-logic/ directory with Kotlin plugins)
DevLog documentation references 'agent loop implementation' and 'agentic dev loop' suggesting autonomous operation capabilities
.claude/ directory with SKILL.md indicating Claude agent integration/extensibility