i-have-adhd — ADHD-Friendly Output Style
Reshapes Claude's replies so the next action comes first, multi-step work is numbered, and progress is restated every turn.
UtilitiesBeginner★ 50,668⑂ 2,928AI score 10/10Last updated: Sep 19, 2026
What it does
It changes the shape of every answer so an ADHD brain can act on it, not just read it.
- Lead with the action: commands, file paths or snippets go first; prose comes later, if at all.
- Number multi-step work: one bounded action per step, trivial steps folded in, unnecessary steps cut.
- Restate state each turn: "Step 3 of 5 done: schema updated. Next: backfill the new column."
- Suppress tangents: secondary issues are surfaced once, at the end, as a separate question.
- Concrete time estimates: "about 15 minutes if tests cover this, an afternoon if not."
- Visible wins, flat error reports: no "Uh oh" — just cause and fix.
- No preamble, recap, or closing pleasantries: kills "Great question" and "Hope this helps."
- Built-in overrides: full explanations when you ask to be walked through, confirmation before destructive commands (rm -rf, force push, migrations), a diagnostic question after three failed debug turns, and one clarifying question on real ambiguity.
Turn it on with /i-have-adhd; it persists for the whole session until you say "stop adhd mode".
Who it's for
- Anyone who loses the actual instruction inside long AI answers
- Readers with ADHD who stall in the gap between "got it" and "done it"
- Developers who prefer step-by-step checklists over narrative
- Anyone who simply wants terse, filler-free output
Examples
- Bug fix: "Login returns 401" → first line is the edit at
src/auth.ts:42, then three numbered steps, ending with "Next: runnpm testand paste the first failing line." - Long refactor: an 8-step job where every reply opens with "4 of 8 done → next step", so you never lose your place in a long thread.
- Asking for options: "What are my choices?" → recommendation first, then 2–4 ranked options with one-line trade-offs.
- Risky operations: before dropping a table or force-pushing, safety beats brevity and it asks for confirmation.
· · · 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/.cursor/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 .cursor/skills/i-have-adhd folder from the GitHub repo ayghri/i-have-adhd into my ~/.claude/skills/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/.cursor/skills/i-have-adhd ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Clone the repo:
git clone https://github.com/ayghri/i-have-adhd.git /tmp/i-have-adhd - Create the skills folder:
mkdir -p ~/.claude/skills - Copy the skill in:
cp -r /tmp/i-have-adhd/.cursor/skills/i-have-adhd ~/.claude/skills/ - Verify that
~/.claude/skills/i-have-adhd/SKILL.mdexists. - Restart Claude Code.
- Type
/i-have-adhdto switch it on — model auto-invocation is disabled, so you must trigger it yourself. - Say "stop adhd mode" or "normal mode" to return to the default style.
View source on GitHub ↗License: MIT