QED

Name: QED
Author: onebit0fme

@onebit0fme

Repository

About QED

Scores your writing against quality profiles — per-trait breakdown, deterministic, sub-second. No auth required.

#writing-quality #documentation #developer-tools #readme #content-scoring #technical-writing

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "qed": {
      "type": "http",
      "url": "https://qed.systems/mcp"
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is QED?

QED is a deterministic scoring tool that evaluates text against quality profiles built from example documents. It returns a composite score and a per-trait breakdown, identifying weak areas and their magnitude. Designed for developers and technical writers, it works with profiles for READMEs, landing pages, technical writing, and more.

How to use QED?

Add QED to Claude Code via claude mcp add --transport http qed https://qed.systems/mcp. Then use the commands /qed:score, /qed:improve, or /qed:profile directly in Claude Code. No signup or authentication is required.

Key features of QED

Deterministic scoring – same content, same profile, same result every time.
Multiple quality profiles for different document types.
Per-trait breakdown showing exact weaknesses.
No LLM at inference – scores work in CI, scripts, or interactively.
No auth, no signup required.

Use cases of QED

Scoring a README against the qed.compelling-readme profile.
Evaluating landing page copy with qed.developer-landing-page.
Checking technical documentation against qed.technical-writing.
Testing content quality in CI pipelines without nondeterminism.

FAQ from QED

How does QED differ from using an LLM to score content?

QED is fully deterministic – same content and profile always produce the same score, with no LLM at inference time. This makes it suitable for CI scripts, automated checks, and reproducible evaluations.