i-have-adhd (ADHD-Friendly Output Mode)
An output-style skill that reshapes Claude's answers around the next action, numbered steps, and per-turn state restatement so you can actually start.
UtilitiesBeginner★ 20,813⑂ 1,295AI score 10/10Last updated: Aug 10, 2026
What it does
- Forces the first line to be an action you can take right now (command, file path, snippet) — no context-setting preamble.
- Turns multi-step work into numbered lists, one bounded action per step, capped at five items.
- Restates progress every turn: "Step 3 of 5 done: schema updated. Next: backfill the column."
- Suppresses tangents; side issues become a separate one-line offer after the main task is finished.
- Requires specific time estimates ("about 15 minutes if tests cover this, an afternoon if not").
- Makes finished work visible in concrete terms instead of burying it in a recap.
- Bans openers, closers, and recaps, with a pre-send checklist that deletes hedging adverbs and idioms.
- Includes sane override rules: full explanations on request, confirmation before destructive actions (
rm -rf, force push, schema migration), a break-the-loop rule after three failed debug turns, and deference to the agent harness's system prompt.
Who it's for
- Anyone with ADHD who loses the thread in long, prose-heavy AI answers.
- Busy engineers, writers, and PMs who just want the decision and the next step.
- People running multi-step workflows who keep losing track of where they are.
- Stack-agnostic: useful in any Claude Code session.
Examples
- Bug fix: "Login returns 401" → first line gives the edit at
src/auth.ts:42plusnpm test -- auth.spec.ts; cause and fix in one line below. - Project setup: you get five numbered steps, and after each one Claude reports "3/5 done, next: connect the DB."
- Comparing options: "What are my deployment options?" → recommendation first, then 2–4 ranked options with one-line trade-offs.
- Turning it off: say "stop adhd mode" when you want a long, teaching-style explanation.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/ayghri/i-have-adhd/HEAD/skills/i-have-adhd/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/i-have-adhd folder from the GitHub repo ayghri/i-have-adhd into my ~/.claude/skills/ayghri-i-have-adhd/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/ayghri/i-have-adhd.git /tmp/i-have-adhd && mkdir -p ~/.claude/skills && cp -r /tmp/i-have-adhd/skills/i-have-adhd ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open your terminal.
- Clone the repo:
git clone https://github.com/ayghri/i-have-adhd.git - Create the skills directory if needed:
mkdir -p ~/.claude/skills - Copy the skill:
cp -r i-have-adhd/skills/i-have-adhd ~/.claude/skills/ - Restart Claude Code.
- Type
/i-have-adhdin chat to turn the mode on (the skill setsdisable-model-invocation: true, so it only runs when you invoke it). - Say "stop adhd mode" or "normal mode" to return to the default style.
View source on GitHub ↗License: MIT