# AutoResearch

> Use this tool when you need to streamline experiment management and automate the research process. AutoResearch solves problems related to experiment tracking, technique composition, and result analysis by providing a structured workflow and a catalog of composable techniques. It takes in experiment configurations and outputs tracked results, best used in contexts where iterative research and evaluation are crucial, such as scientific research, data analysis, and machine learning model development.

Canonical page: https://skillsregistry.net/skills/shreemulay-autoresearch  
JSON: https://api.skillsregistry.net/v1/skills/shreemulay-autoresearch

## Description

Implements a structured experiment management workflow following the "edit artifact, run evaluator, score improved, keep or revert, repeat" pattern. Provides a 30-item composable technique catalog spanning search strategies, evaluators, execution patterns, and recipes. Tracks experiments with SQLite and FTS5-backed persistence, including cost and token tracking across iterations. Supports experiment scaffolding, technique discovery, and result logging through 11 tools.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/shreemulay-autoresearch)
- **Repository:** <https://github.com/shreemulay/autoresearch-mcp>

## 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": "shreemulay-autoresearch"
    }
  }
}
```

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