# Flashlight

> Use this tool when you need to quickly find specific code snippets across large projects using natural language queries. It solves the problem of tedious manual searching by leveraging advanced search capabilities and caching for efficient repeated searches. Ideal for developers working on complex, large-scale codebases who require fast and accurate code discovery.

Canonical page: https://skillsregistry.net/skills/1percentsync-flashlight  
JSON: https://api.skillsregistry.net/v1/skills/1percentsync-flashlight

## Description

Enables whole-codebase code search using natural language queries by leveraging DeepSeek's 1M context window. Automatically shards large projects and utilizes prefix caching for cost-effective repeated searches.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/zocbs89x1e)
- **Repository:** <https://github.com/1PercentSync/flashlight>

## 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": "1percentsync-flashlight"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/1percentsync-flashlight` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/1percentsync-flashlight/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