TacoSkill LAB
TacoSkill LAB
HomeSkillHubCreatePlaygroundSkillKit
© 2026 TacoSkill LAB
AboutPrivacyTerms
  1. Home
  2. /
  3. SkillHub
  4. /
  5. code-discovery
Improve

code-discovery

3.1

by majiayu000

52Favorites
65Upvotes
0Downvotes

"Helpers to discover, rank, and invoke repository symbols from natural language with minimal context."

code-intelligence

3.1

Rating

0

Installs

AI & LLM

Category

Quick Review

The skill addresses a valuable problem (discovering and ranking repository symbols from natural language), which is novel and would save tokens for a CLI agent. However, the SKILL.md lacks sufficient detail for a CLI agent to invoke the skill effectively. The description is too brief, providing no information about input formats, output structures, available functions, parameters, or usage examples. While the structure appropriately references CODE.md for implementation details and main.ts for the API, the SKILL.md itself should contain enough operational information for invocation without requiring an agent to read implementation files. To improve: add concrete examples, list available functions with signatures, specify input/output formats, and provide at least one end-to-end usage scenario.

LLM Signals

Description coverage2
Task knowledge2
Structure4
Novelty5

GitHub Signals

49
7
1
1
Last commit 0 days ago

Publisher

majiayu000

majiayu000

Skill Author

Related Skills

mcp-developerprompt-engineerfine-tuning-expert

Loading SKILL.md…

Try onlineView on GitHub

Publisher

majiayu000 avatar
majiayu000

Skill Author

Related Skills

mcp-developer

Jeffallan

6.4

prompt-engineer

Jeffallan

7.0

fine-tuning-expert

Jeffallan

6.4

rag-architect

Jeffallan

7.0
Try online