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.

Merge remote-tracking branch 'origin/main' into naren/rollout-benchmark-pr25

Narendran Raghavan862b71d8bcb2
diff --cc src/skillevaluator/evaluation/tier3_report.py
index 09540fca,0fdf2bf7..2b2bd718
--- a/src/skillevaluator/evaluation/tier3_report.py
+++ b/src/skillevaluator/evaluation/tier3_report.py
@@@ -32,12 -31,8 +32,12 @@@ from skillevaluator.constants import
AGENT_EVAL_SCORE_DEFINITION,
DIMENSION_HINTS,
DIMENSION_MAPPING,
+ DIMENSION_VERDICT_NEUTRAL_THRESHOLD,
+ DIMENSION_VERDICT_PASS_THRESHOLD,
+ TIER3_LIFT_FAIL_THRESHOLD,
+ TIER3_LIFT_PASS_THRESHOLD,
)
- from skillevaluator.models.result import ValidationResult
+ from skillevaluator.models.result import Finding, Severity, ValidationResult
# Verdict labels mirror SkillEvaluator's AGENT_EVAL_VERDICT_* values so the ported
# reporters classify the overall outcome identically.
diff --cc src/skillevaluator/reporting/cli.py
index 3a3b7528,80227ca5..988e78e9
--- a/src/skillevaluator/reporting/cli.py
+++ b/src/skillevaluator/reporting/cli.py
@@@ -23,11 -23,7 +23,11 @@@ from rich.markup import escape as rich_
from rich.panel import Panel
from rich.table import Table
+from skillevaluator.constants import (
+ DIMENSION_VERDICT_NEUTRAL_THRESHOLD,
+ DIMENSION_VERDICT_PASS_THRESHOLD,
+)
- from skillevaluator.reporting.base import ReporterBase
+ from skillevaluator.reporting.base import ReporterBase, passes_required_gate
from skillevaluator.reporting.harbor_viewer import (
harbor_evidence_link_text,
normalize_harbor_viewer_for_display,