agent-ecosystem

Control twin of probe-allowed-tools with no allowed-tools field. Use when asked to probe allowed-tools control behavior.

Benchmark skill for testing the experimental allowed-tools field. Use when asked to probe allowed-tools behavior.

Benchmark skill whose name violates the consecutive-hyphen rule. Use when asked to probe double-hyphen name handling.

Benchmark skill whose compatibility field runs past the spec's 500-character limit. Use when asked to probe oversize compatibility handling.

Benchmark skill whose description deliberately runs past the spec's 1024-character limit, to test oversize field handling. Use when asked to probe oversize description handling. The head marker SANDERLING-GNEISS-1010 sits near the start of this description…

Benchmark skill whose name exceeds the 64-character limit. Use when asked to probe overlong name handling.

Benchmark skill for testing whether bundled scripts are executable. Use when asked to probe script execution behavior.

Benchmark skill for testing path traversal boundary enforcement. Use when asked to probe path traversal.

A fixture with generated and non-generated non-standard content.

A fixture with two intentionally nested asset bundles.

A skill that uses only shell and config code blocks for testing contamination.

Review a proposed Agent Skill for structural validity and content quality before publishing. Runs the skill-validator CLI to check for structural issues, scores the skill with an LLM judge, and interprets results to advise authors on what to address. Use when…

A skill with development directories that require --allow-dirs.

A skill using a flat layout with all files at the root level.

A skill that produces warnings but no errors.

A well-formed example skill for testing the validator.