Test skills before using or publishing. Trial, compare, evaluate in isolation without affecting your environment.
Real data. Real impact.
Growing
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
Two use cases:
Key principle: Test in isolation. Never affect user's environment.
References:
sandbox.mdcompare.mdevaluate.mdTrial a skill:
sessions_spawn( task="Test skill X: Load ONLY its SKILL.md, run [sample task], report quality", model="anthropic/claude-haiku" )
Compare two skills:
Trial Mode — Before installing
Evaluation Mode — Before publishing
evaluate.md⚠️ Never load test skill into your main context.
Sub-agent approach (recommended):
sessions_spawn( task="You have ONE skill loaded: [skill content]. Test by doing: [task]", model="anthropic/claude-haiku" )
What to check:
Skill requires credentials: Ask user for test credentials or skip auth-dependent features.
Skill not found: Verify slug with
npx clawhub info <slug>Test fails mid-way: Sub-agent terminates cleanly. Review logs, adjust test task, retry.
Skill has many auxiliary files: Load SKILL.md first, reference others only if needed during test.
Test thoroughly. Install only after explicit user approval.
No automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions
1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.