This is a decision tree for choosing the right search tool when working with code. It breaks down four options: LEANN for semantic queries like "how does authentication work", AST-grep for structural patterns like finding all function calls, Morph for fast text search across the codebase, and the built-in Grep for literal patterns. The skill includes a PreToolUse hook that auto-redirects semantic Grep queries to LEANN, which is smart since developers often grep for concepts when they really want semantic search. Think of this as a cheat sheet that saves you from using grep when you should be using embeddings, or vice versa.

skills.sh installs
491
GitHub stars
3.9K
last updated
Aug 21, 2026

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill search-tools --agent claude-code

Installs into .claude/skills of the current project.

Files

Search Tool Hierarchy

When searching code, use this decision tree:

Decision Tree

Need CONCEPTUAL/SEMANTIC search?
  (how does X work, find patterns, understand architecture)
  → Use LEANN (/leann-search) - embedding-based semantic search
  → PreToolUse hook auto-redirects semantic Grep queries

Need to understand code STRUCTURE?
  (find function calls, class usages, refactor patterns)
  → Use AST-grep (/ast-grep-find)

Need to find TEXT in code?
  → Use Morph (/morph-search) - 20x faster
  → If no Morph API key: fall back to Grep tool

Simple one-off search?
  → Use built-in Grep tool directly

Tool Comparison

ToolBest ForRequires
LEANNSemantic search: "how does caching work", "error handling patterns", conceptual queriesIndex built
AST-grepStructural patterns: "find all calls to foo()", refactoring, find usages by typeMCP server
MorphFast text search: "find files mentioning error", grep across codebaseAPI key
GrepLiteral patterns, class/function names, regexNothing (built-in)

Examples

Sponsors

Details

Repository
github.com/parcadei/continuous-claude-v3
First seen
Jun 3, 2026

More from parcadei/continuous-claude-v3

All 108

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs