Add PQS (Prompt Quality Score) to Prompt Management and Testing

[OnChainAIIntel]

What this adds

PQS (Prompt Quality Score) — a pre-inference prompt scoring system, added as a row in the Prompt Management and Testing table.

Why it fits

PQS is complementary to existing entries in this section. Quick differentiation:

• Promptfoo tests outputs against assertions (post-inference QA)
• PQS scores inputs before inference runs (pre-flight quality gate)
• DSPy / TextGrad optimize prompts via LLM calls; PQS scores them on structured dimensions without requiring optimization loops

PQS scores any prompt on 8 dimensions using 5 established frameworks (PEEM, RAGAS, MT-Bench, G-Eval, ROUGE). Published on GitHub Marketplace as "PQS Check" for CI-based gating.

Ecosystem

• GitHub Action: OnChainAIIntel/pqs-action (GitHub Marketplace listed)
• Python SDK: prompt-quality-score on PyPI (CrewAI, LangChain, AutoGen integrations)
• MCP server: pqs-mcp-server on npm (Smithery 88/100, Glama Official)
• REST API: pqs.onchainintel.net — free tier, no signup required

MIT licensed. Happy to rework the description or move to a different section if a better fit exists.