tldr-router
Maps questions to the optimal LeIndex command
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Maps questions to the optimal LeIndex command
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | tldr-router |
| description | Maps questions to the optimal LeIndex command |
| user-invocable | false |
Maps questions to the optimal LeIndex command. Use this to pick the right layer.
leindex tree . --ext .py # File overview
leindex structure src/ --lang python # Function/class overview
Use: Starting exploration, orientation
leindex context <function> --project . --depth 2
leindex calls src/
Use: Understanding architecture, finding entry points
leindex cfg <file> <function>
Use: Identifying refactoring candidates, understanding difficulty
leindex dfg <file> <function>
Use: Debugging, understanding data flow
leindex slice <file> <function> <line>
Use: Impact analysis, safe refactoring
leindex search "pattern" src/
Use: Finding code, structural search
leindex semantic "authentication flow"
Use: Semantic code search using embeddings
START
│
├─► "What exists?" ──► tree / structure
│
├─► "How does X connect?" ──► context / calls
│
├─► "Why is X complex?" ──► cfg
│
├─► "Where does Y flow?" ──► dfg
│
├─► "What depends on Z?" ──► slice
│
├─► "Find something" ──► search
│
└─► "Describe X in plain English" ──► semantic
| Intent | Keywords | Layer |
|---|---|---|
| Navigation | "what", "where", "find", "exists" | tree, structure, search |
| Architecture | "calls", "uses", "connects", "depends" | context, calls |
| Complexity | "complex", "refactor", "branches", "paths" | cfg |
| Data Flow | "variable", "value", "assigned", "comes from" | dfg |
| Impact | "affects", "changes", "slice", "dependencies" | slice/pdg |
| Debug | "bug", "error", "investigate", "broken" | cfg + dfg + context |
| Semantic | "describe", "what does", "how works" | semantic search |
from maestro.leindex import (
get_relevant_context,
semantic_search,
ContextExtractor,
)
# Get context for an entry point
context = get_relevant_context("/path/to/project", "main")
# Semantic search
results = semantic_search("how does authentication work?", "/path/to/project")
# Full analysis with token savings
extractor = ContextExtractor()
result = extractor.extract_for_file("src/api.py")
print(f"Token savings: {result.savings_percent:.1f}%")
The leindex-context and leindex-read hooks automatically:
You don't need to manually run these commands - the hooks do it for you.
If you need a specific layer the hooks didn't provide:
from maestro.leindex import (
CFGAnalyzer,
DFGAnalyzer,
SlicingAnalyzer,
)
cfg_analyzer = CFGAnalyzer()
dfg_analyzer = DFGAnalyzer()
slicing_analyzer = SlicingAnalyzer()
# Analyze specific function
cfg = cfg_analyzer.analyze(source, "function_name", "file.py")
dfg = dfg_analyzer.analyze_function(source, "function_name", "file.py")
slice_result = slicing_analyzer.slice_backward(source, "function_name", 42, "file.py")
Maestro spec-driven development for Claude Code. Load this skill when invoking Maestro commands so workflows stay aligned with LeIndex and the Rust TUI.
Maestro spec-driven development for Gemini CLI. Load this skill when invoking Maestro commands so workflows stay aligned with LeIndex and the Rust TUI.
Maestro spec-driven development for Amp CLI. Load this skill when invoking Maestro commands so workflows stay aligned with LeIndex and the Rust TUI.
Show users how Maestro works - the opinionated setup with hooks, memory, and coordination
Full 5-layer analysis of a specific function for debugging or deep understanding
Get a token-efficient overview of any project using the TLDR stack