# PCQ

> Use this tool when you need to manage and control experiment evidence for AI agents, allowing for seamless integration with existing training code. PCQ solves problems related to experiment reproducibility, data tracking, and model validation, providing a standardized interface for inputting experiment parameters and outputting actionable insights. It is ideal for use cases where agent-operable experiment evidence and control are crucial, such as in machine learning model development and deployment.

Canonical page: https://skillsregistry.net/skills/playidea-lab-pcq  
JSON: https://api.skillsregistry.net/v1/skills/playidea-lab-pcq

## Description

Python library for agent-operable experiment evidence and control. Bring any training code

## Trust

- **Trust score (0–1):** 0.75
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gc0u7mu8j1)
- **Repository:** <https://github.com/playidea-lab/pcq>

## 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": "playidea-lab-pcq"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/playidea-lab-pcq` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/playidea-lab-pcq/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