10 rules that reshape AI output for ADHD-friendly reading. Action first. Numbered steps. No preamble, no recap, no "Hope this helps!"
Every response shaped so an ADHD brain can act on it.
First line is something the reader can do. Not context. Not a plan. The action.
Each step is one bounded action. No step contains "and then" twice.
Name ONE thing the reader can do in under two minutes. Even "open the file" counts.
Finish the first issue, then offer the second as a separate question.
The reader cannot hold "we are on step 3 of 5" between messages.
"About 15 minutes" not "some work." Concrete units or nothing.
Show what now works, in concrete terms. Do not bury wins in a recap.
State cause and fix. Never "Uh oh," "Oh no," or "There seems to be a problem."
Split into "do now" vs "later." Five items ranked beats ten unranked.
Forbidden: "Great question," "Hope this helps," "Let me know if..."
Examples tuned for the work you actually do.
Media swaps, flow rates, regeneration cycles. Lead with the exact change, not the theory.
Email flows, approval digests, cron schedules. Command first, explanation after.
Underwriter logic, deal status flows, KV configs. Exact file and line, not vague references.
Parallel task orchestration, state rollups, enrichment pipelines. Restate state every turn.
One skill. One price. MIT-licensed — fork it if you want.
Download, drop in your agent's skills folder, restart. Done.
git clone https://github.com/lifecycleResearch/i-have-adhd-skill.git
cd i-have-adhd-skill && ./install.sh
# Type /i-have-adhd to activate