Domains
Forms
Mechanism
Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.
When understanding how PluginEval measures plugin/skill quality, interpreting a low dimension score, deciding how to improve a skill's triggering accuracy or orchestration fitness, calibrating marketplace scoring thresholds, or explaining quality badges to partners.
A clear methodology reference enabling users to measure, interpret, and improve plugin quality, set badge thresholds, and communicate quality standing to external partners.
Use Cases
A plugin marketplace operator receives a skill scored D on triggering_accuracy. Using this skill, they read the dimension weights and blend table, understand that Layer 3 Monte Carlo contributes 60% to that dimension, and realize the skill fires incorrectly on real prompts. They then follow improvement tips to rewrite the description with explicit 'Use when' triggers, raising the score and badge tier.
A partner like Neon asks why a skill has a Gold badge. The user opens this methodology, explains the composite threshold (≥80) and Elo threshold (≥1500), shows the anti-pattern penalty formula and Monte Carlo consistency metrics, and demonstrates that the skill passed all static and judge checks. This transparently communicates quality standing and builds partner trust.
Skill Relationships
Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.
Tier 1 · These Skills Use Me
Tier 2 · Current Skill
Tier 3 · I Use These Skills
Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.
Skill File
