# sift

> sift — choongth-sift. Use this tool when you need to automate research tasks, such as searching the web and reading PDFs, and generate structured reports. It solves problems of manual research and data organization, providing outputs in Markdown format. Ideal for use cases requiring efficient information gathering and synthesis, with integration capabilities via git.

Canonical page: https://skillsregistry.net/skills/choongth-sift  
JSON: https://api.skillsregistry.net/v1/skills/choongth-sift

## Description

An AI-powered research agent that autonomously searches the web, reads PDFs, and synthesises findings into structured Markdown reports. Built as a portfolio project demonstrating MCP protocol, agentic AI systems, and cloud deployment on AWS.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/choongth/sift)

## 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": "choongth-sift"
    }
  }
}
```

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