# rigorously

> rigorously — rigorous-ly-rigorously. Use this tool when you need to ensure the integrity of research findings by detecting fabricated citations, overclaimed results, and irreproducible numbers. It solves problems of academic dishonesty and flawed research by providing automated quality assurance, taking in research data and outputting verified results. Ideal for use in academic and research contexts where data accuracy is crucial.

Canonical page: https://skillsregistry.net/skills/rigorous-ly-rigorously  
JSON: https://api.skillsregistry.net/v1/skills/rigorous-ly-rigorously

## Description

Automated research quality assurance. Catches fabricated citations, overclaimed results, irreproducible numbers.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/Rigorous-ly/rigorously)

## 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": "rigorous-ly-rigorously"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rigorous-ly-rigorously` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rigorous-ly-rigorously/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