- Home
- Skills
- Workflow Automation
- adhd-style-eval-run
Adhd Style Eval Run
Blind paired-response eval harness for measuring agent style changes with a weighted rubric and deterministic label permutation.
$12.99
Works with the AI Agents you already use
About this skill
A blind, paired-response evaluation harness for measuring how a change to an agent's rules, prompt, or style affects real behavior. Generate candidate and baseline responses to the same cases, permute labels deterministically so the judge never knows which is which, score on a 5-dimension weighted rubric (correctness, autonomy, actionability, safety, concision), and get a per-dimension verdict with a release gate you can defend. Covers trial design, judge selection (and the trap of a weak same-family judge), resume-after-crash runs, and per-trial delta analysis to separate real regressions from judge noise.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 days ago