Verifies relationships between a source text (e.g. Episode, Task) and existing Knowledge Graph lessons. Runs KNN/Hybrid search to find candidates, then uses LLM (scillm) to verify "verifies", "contradicts", or "related" stances with strict rationales.
4.9
Rating
0
Installs
Testing & Quality
Category
The skill provides a clear overview of KNN+LLM verification for knowledge graph edges with good structural organization. The description adequately explains the three-phase process (Recall, Verify, Link) and includes practical usage examples with bash commands and mom scheduling integration. However, taskKnowledge is moderate because the actual implementation details (run.sh script, verification logic, search parameters) are not present, though this is acceptable given the concise SKILL.md format. Novelty is moderate - while the combination of KNN search + LLM verification is useful, similar graph verification patterns are common in knowledge management systems. The mom integration and scheduling template add practical value. Confidence is high that this skill would function as described if the referenced run.sh exists.
Loading SKILL.md…

Skill Author