# PQS - Prompt Quality Score

> Use this tool when you need to evaluate and improve the quality of language model prompts, solving issues with ineffective or inefficient prompts. The PQS tool takes a prompt as input and returns a grade, score, percentile, and dimension breakdown, helping you refine your prompts for better results. Ideal for use cases where prompt quality directly impacts model performance, such as chatbots, language translation, or text generation tasks.

Canonical page: https://skillsregistry.net/skills/onchaintel-pqs  
JSON: https://api.skillsregistry.net/v1/skills/onchaintel-pqs

## Description

The world's first named AI prompt quality score. Score any LLM prompt before it hits any model — returns grade (A-F), score out of 40, percentile, and dimension breakdown across 8 quality dimensions.

Built on PEEM, RAGAS, G-Eval, and MT-Bench frameworks.

**Tools:**
- score_prompt — Free. No API key needed.
- optimize_prompt — $0.025 USDC. Returns optimized prompt + full breakdown.
- compare_models — $0.50 USDC. Claude vs GPT-4o head-to-head.

Cheaper than one bad inference call.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/onchaintel/pqs)
- **Repository:** <https://github.com/OnChainAIIntel/pqs-mcp-server>

## 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": "onchaintel-pqs"
    }
  }
}
```

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