# crucible

> crucible — harperz9-crucible. Use this tool when you need to test and verify claims against evidence, and track outcomes such as MATCH, DRIFT, or UNVERIFIABLE results. It solves problems of claim validation and evidence-based decision making by providing a structured testing framework. The crucible tool accepts claims and evidence as inputs and outputs verified outcomes, ideal for use in data-driven projects managed through git.

Canonical page: https://skillsregistry.net/skills/harperz9-crucible  
JSON: https://api.skillsregistry.net/v1/skills/harperz9-crucible

## Description

Python and MCP tools for testing falsifiable claims and recording MATCH, DRIFT, or UNVERIFIABLE outcomes against supplied evidence.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **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/HarperZ9/crucible)

## 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": "harperz9-crucible"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/harperz9-crucible` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/harperz9-crucible/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