# scry

> Use this tool when you need to quickly search and find specific files or symbols in your codebase, solving problems of slow search and navigation in large projects. It takes in file directories and search queries as input and outputs relevant results, ranked by frecency. Ideal for use in code editors, Neovim, and AI agents like Claude, particularly in git-based projects.

Canonical page: https://skillsregistry.net/skills/quangdang46-scry  
JSON: https://api.skillsregistry.net/v1/skills/quangdang46-scry

## Description

Ultra-fast file search toolkit for AI agents, Neovim, and code editors. MCP server for Claude Code/Cursor/Codex, frecency-ranked search, symbol indexing via tree-sitter, and a Rust core that outperforms ripgrep and fzf in long-running processes.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-05-13

## Source

- **Source listing:** [GitHub](https://github.com/quangdang46/scry)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "quangdang46-scry"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/quangdang46-scry` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/quangdang46-scry/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt