PluginEval Core 🔬#

Self-contained quality evaluation for AI agent skills. Measures quality across 6 dimensions, detects anti-patterns, assigns quality badges.

Use When#

• Evaluating skill quality before installation
• Checking installed skills for quality issues
• Improving skills to meet quality standards
• Publishing skills to ClawHub with quality badges

Input / Output#

Input:

• Skill directory containing SKILL.md
• Optional: --layer1, --layer2, --anti-patterns flags

Output:

json

{
  "skill": "example-skill",
  "score": 87,
  "badge": "Gold",
  "grade": "B+",
  "anti_patterns": []
}

Usage#

bash

# Layer 1: Static Analysis
python3 ~/.openclaw/skills/plugineval-core/scripts/eval.py --layer1 <skill-dir>

# Anti-Pattern Detection
python3 ~/.openclaw/skills/plugineval-core/scripts/eval.py --anti-patterns <skill-dir>

# Full Evaluation
python3 ~/.openclaw/skills/plugineval-core/scripts/eval.py <skill-dir>

Quality Dimensions#

DimensionWeightMeasuresFrontmatter Quality35%Name, description, triggerOrchestration Wiring25%Input/Output, examplesProgressive Disclosure15%ConcisenessStructural Completeness10%Headings, troubleshootingToken Efficiency6%Directives, duplicationEcosystem Coherence2%Cross-references

Quality Badges#

BadgeScorePlatinum ★★★★★≥90Gold ★★★★≥80Silver ★★★≥70Bronze ★★≥60Needs Improvement ★<60

Anti-Patterns#

PatternPenaltyOVER_CONSTRAINED10%EMPTY_DESCRIPTION10-50%MISSING_TRIGGER15%BLOATED_SKILL10%ORPHAN_REFERENCE5%DEAD_CROSS_REF5%

References#

• quality-framework.md
• anti-pattern-catalog.md

Examples#

bash

# Evaluate skill
python3 scripts/eval.py --layer1 ~/.openclaw/skills/weather-pollen

# Output:
# [1/6] Frontmatter Quality: 100/100
# [2/6] Orchestration Wiring: 100/100
# ...
# Final: 87 | Badge: Gold ★★★★

---

Version: 1.0.0 | License: MIT