TacoSkill LABTacoSkill LAB

The full-lifecycle AI skills platform.

Product

  • SkillHub
  • Playground
  • Skill Create
  • SkillKit

Resources

  • Privacy
  • Terms
  • About

Platforms

  • Claude Code
  • Cursor
  • Codex CLI
  • Gemini CLI
  • OpenCode

© 2026 TacoSkill LAB. All rights reserved.

TacoSkill LAB
TacoSkill LAB
HomeSkillHubCreatePlaygroundSkillKit
  1. Home
  2. /
  3. SkillHub
  4. /
  5. edge-verifier
Improve

edge-verifier

4.9

by majiayu000

61Favorites
136Upvotes
0Downvotes

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.

verification

4.9

Rating

0

Installs

Testing & Quality

Category

Quick Review

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.

LLM Signals

Description coverage7
Task knowledge6
Structure8
Novelty5

GitHub Signals

49
7
1
1
Last commit 0 days ago

Publisher

majiayu000

majiayu000

Skill Author

Related Skills

code-reviewerdebugging-wizardtest-master

Loading SKILL.md…

Try onlineView on GitHub

Publisher

majiayu000 avatar
majiayu000

Skill Author

Related Skills

code-reviewer

Jeffallan

6.4

debugging-wizard

Jeffallan

6.4

test-master

Jeffallan

6.4

playwright-expert

Jeffallan

6.4
Try online