namesreallyblank

search-router

2
0
# Install this skill:
npx skills add namesreallyblank/Clorch --skill "search-router"

Install specific skill from multi-skill repository

# Description

Choose the right search tool for each query type

# SKILL.md


name: search-router
description: Choose the right search tool for each query type
user-invocable: false


Search Tool Router

Use the most token-efficient search tool for each query type.

When to Use

  • Searching for code patterns
  • Finding where something is implemented
  • Looking for specific identifiers
  • Understanding how code works

Decision Tree

Query Type?
β”œβ”€β”€ CODE EXPLORATION (symbols, call chains, data flow)
β”‚   β†’ TLDR Search - 95% token savings
β”‚   DEFAULT FOR ALL CODE SEARCH - use instead of Grep
β”‚   Examples: "spawn_agent", "DataPoller", "redis usage"
β”‚   Command: cd opc/packages/tldr-code && uv run python scripts/tldr_search.py "query"
β”‚
β”œβ”€β”€ STRUCTURAL (AST patterns)
β”‚   β†’ AST-grep (/ast-grep-find) - ~50 tokens output
β”‚   Examples: "def foo", "class Bar", "import X", "@decorator"
β”‚
β”œβ”€β”€ SEMANTIC (conceptual questions)
β”‚   β†’ TLDR Semantic - 5-layer embeddings (P6)
β”‚   Examples: "how does auth work", "find error handling patterns"
β”‚   Command: tldr semantic search "query"
β”‚
β”œβ”€β”€ LITERAL (exact text, regex)
β”‚   β†’ Grep tool - LAST RESORT
β”‚   Only when TLDR/AST-grep don't apply
β”‚   Examples: error messages, config values, non-code text
β”‚
└── FULL CONTEXT (need complete understanding)
    β†’ Read tool - 1500+ tokens
    Last resort after finding the right file

Token Efficiency Comparison

Tool Output Size Best For
TLDR ~50-500 DEFAULT: Code symbols, call graphs, data flow
TLDR Semantic ~100-300 Conceptual queries (P6, embedding-based)
AST-grep ~50 tokens Function/class definitions, imports, decorators
Grep ~200-2000 LAST RESORT: Non-code text, regex
Read ~1500+ Full understanding after finding the file

Examples

# CODE EXPLORATION β†’ TLDR (DEFAULT)
cd opc/packages/tldr-code && uv run python scripts/tldr_search.py "spawn_agent"
cd opc/packages/tldr-code && uv run python scripts/tldr_search.py "redis" --layer call_graph

# STRUCTURAL β†’ AST-grep
/ast-grep-find "async def $FUNC($$$):" --lang python

# SEMANTIC β†’ TLDR Semantic
tldr semantic search "how does authentication work"

# LITERAL β†’ Grep (LAST RESORT - prefer TLDR)
Grep pattern="check_evocation" path=opc/scripts

# FULL CONTEXT β†’ Read (after finding file)
Read file_path=opc/scripts/z3_erotetic.py

Optimal Flow

1. AST-grep: "Find async functions" β†’ 3 file:line matches
2. Read: Top match only β†’ Full understanding
3. Skip: 4 irrelevant files β†’ 6000 tokens saved
  • /tldr-search - DEFAULT - Code exploration with 95% token savings
  • /ast-grep-find - Structural code search
  • /morph-search - Fast text search

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.