Skip to content

Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior. Ships reusable CI templates that bring every check to any repository.

NameLast commit date
..
config
deduplication
embedding
evaluation
harness
inference
models
reporting
tier1
tier2
tier3
utils
validators
__init__.py
_ci_onboarding_all_tiers.py
_ci_onboarding_git.py
_ci_onboarding_pages.py
_ci_onboarding_workflows.py
ci_onboarding.py
ci-release-all-tiers.json
ci-release.json
cli_core.py
cli_help.py
cli.py
constants.py
doctor.py
evidence.py
finding_verification_policy.py
logging_config.py
model_catalog.py
model_commands.py
plugin_component_risk.py
plugin_config_risk.py
plugin_context_cost.py
plugin_dependencies.py
plugin_dependency_audit.py
plugin_dependency_records.py
plugin_discovery.py
plugin_format_schema.py
plugin_formats.py
plugin_inventory.py
plugin_manifest.py
plugin_markdown.py
plugin_mcp.py
plugin_member_paths.py
plugin_paths.py
plugin_permissions.py
plugin_refs.py
plugin_skills.py
plugin_states.py
precommit.py
provider_config.py
publication_evidence.py
publication_identity.py
publication_text.py
quality_config.py
skillspector_diagnostics.py
skillspector_provenance.py
skillspector_reference_caveats.py
skillspector_references.py
source_identity.py
spdx.py
tier_group.py
tier_workflows.py
tier3_environments.py