code_tools
Code Tools Skill
You have loaded the Code Tools Skill - The unified entry point for all code operations.
Primary Command
code_search - Unified Search Interface
This is the ONLY search tool you should use.
# Structure search (finds class/function definitions)
code_search("class User")
code_search("def authenticate")
# Semantic search (finds conceptually related code)
code_search("how does authentication work")
code_search("user validation logic")
# Text search (finds exact matches)
code_search("TODO: fix")
code_search("FIXME: memory leak")
Returns XML-formatted results optimized for LLM consumption.
Search Strategy Selection
The tool automatically selects the best strategy:
| Query Type | Strategy | Example |
|---|---|---|
class Foo |
AST | Structural definition search |
def foo() |
AST | Function signature search |
| Questions | Vector | Semantic/conceptual search |
TODO, FIXME |
Grep | Exact text match |
Workflow
1. SEARCH
code_search("...") # Unified entry point
↓
2. INTERPRET XML RESULTS
- <item> for focused results
- <search_interaction> for refinement suggestions
↓
3. REFINE (if needed)
code_search("class ClassName") # More specific
↓
4. READ FILE (for implementation details)
read_file("path/to/file.py")
Best Practices
- Always use
code_searchfor all code discovery tasks - Be specific:
code_search("class UserAuth")>code_search("auth") - Check XML guidance: If results are too broad, the XML will suggest refinements
- Read files for details: Use
read_fileafter finding the right file
Search Engines
| Engine | Use Case | Examples |
|---|---|---|
| AST | Class/function definitions | class Foo, def bar |
| Vector | Conceptual queries | "how does auth work" |
| Grep | Exact text | TODO, "error message" |
More from tao3k/omni-dev-fusion
crawl4ai
Use when crawling web pages, extracting markdown content, or scraping website data with intelligent chunking and skeleton planning. Use when the user provides a URL or link to fetch or crawl.
50software_engineering
Use when analyzing project architecture, exploring codebase structure, understanding system design, reviewing code patterns, or navigating modular components.
18python_engineering
Use when linting Python code, formatting with ruff/black, running pytest tests, type checking with pyright, or modernizing Python 3.12+ standards.
18rust_engineering
Use when analyzing Rust project structure, managing Cargo dependencies, building and testing Rust projects, or generating Rust code.
16git
Use when committing code, managing branches, pushing to remote, creating pull requests, or performing version control operations. Conforms to docs/reference/skill-routing-value-standard.md.
15researcher
Use when analyzing repositories, conducting deep research on codebases, performing architecture reviews, or exploring large projects from a git URL.
15