Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
.claude/skills/moizibnyousaf-browse-and-evaluate/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -54% | 0% |
Find the right skill for a task without flooding the context window or installing blindly.
--fields on list/search/info to keep output small. Default: --fields name,tier,workArea,description.--dry-run before installing anything.--format json in non-interactive pipelines. The CLI defaults to JSON when stdout is not a TTY.--limit when browsing large catalogs. Start with --limit 10.bashnpx ai-agent-skills search <query> --fields name,tier,workArea,description --limit 10
bashnpx ai-agent-skills info <skill-name> --fields name,description,tags,collections,installCommands
bashnpx ai-agent-skills preview <skill-name>
bashnpx ai-agent-skills install <skill-name> --dry-run
bashnpx ai-agent-skills install <skill-name>
preview command sanitizes skill content to strip prompt injection patterns. If content looks truncated, check if suspicious patterns were removed.--list or --dry-run a collection before installing.--dry-run to verify the source is reachable.Other measured skills in the registry, with their headline benchmark lift.