About QED
QED is a Claude Code plugin for evaluating and improving content against scoring models on u22a8.ai. It offers trait-level scores and a separate editing workflow that measures changes after targeted revisions.
Key features
- 01Score content by individual traits
- 02Report composite scores
- 03Improve content through targeted edits
- 04Re-evaluate and report score changes
- 05Score Markdown files in GitHub Actions
Use cases
- 01Assess a draft against a scoring model
- 02Revise documentation based on weak traits
- 03Score Markdown files on pull requests
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://qed.systems/mcpclaude mcp add --transport http qed-plugins https://qed.systems/mcp{"mcpServers":{"qed-plugins":{"type":"http","url":"https://qed.systems/mcp"}}}Open in Cursor{"servers":{"qed-plugins":{"type":"http","url":"https://qed.systems/mcp"}}}Open in VS Code{"mcpServers":{"qed-plugins":{"type":"http","url":"https://qed.systems/mcp"}}}{"mcpServers":{"qed-plugins":{"serverUrl":"https://qed.systems/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEU+22A8 plugins
Claude Code plugin marketplace for u22a8.ai — score and improve content with scoring models.
A scoring model is a standard of judgment, learned from examples, that can score any content — turning subjective quality into something measurable.
Quick start █░░
# Add the marketplace
/plugin marketplace add u22a8/plugins
# Install the u22a8 plugin
/plugin install u22a8@u22a8-plugins
Plugins ██░
u22a8
Score and improve content against scoring models on u22a8.ai.
Two skills:
/u22a8:evaluate— Measure how content performs on specific traits. Scores each trait 0–100 with a composite. Measurement only, no edits./u22a8:improve— Full editing loop: baseline score, diagnose weaknesses, make targeted edits, re-evaluate, report deltas. Iterates until you're satisfied.
# Score a file
/u22a8:evaluate my-draft.md
# Improve a file against model traits
/u22a8:improve my-draft.md
No setup required — the plugin connects to the hosted API at u22a8.ai.
GitHub Actions
score-docs
Score markdown files on every PR. See actions/score-docs for setup and configuration.
License ███
Apache-2.0
∎
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.