Score any URL against a quality profile with one curl command

Name: Score any URL against a quality profile with one curl command
Availability: InStock
Author: onebit0fme

by onebit0fme·Mar 14, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainShip ItNiche Gem

Deterministic writing quality scores without LLMs, plus MCP server integration for AI workflows.

Strengths

•No auth or rate limits makes it instantly usable for CI pipelines and scripts.
•Ground truth example training beats vague LLM rubrics for consistent scoring.
•MCP server integration brings quality checks directly into AI coding assistants.

Weaknesses

•Subjective quality metrics may not generalize well beyond the trained profiles.
•Limited profile selection right now; custom profiles require manual request to author.

Post Description

I've been building a quality scoring API for text content. The idea: instead of writing rules for what good looks like, each profile is trained from examples of great and not-so-great writing. The profile then scores anything you throw at it, with per-trait scores.

Two profiles live right now — compelling READMEs and technical writing. Happy to train more profiles on request. Try it:

curl -s https://qed.systems/p/qed.compelling-readme -H "Content-Type: application/json" -H "Accept: text/plain" -d '{"content":"https://github.com/astral-sh/uv"}'

Works with any public URL or raw text. No auth, no account. Also ships as an MCP server (claude mcp add --transport http qed https://qed.systems/mcp).