i-have-adhd

Formats AI responses with action-first structure, numbered steps, and concrete time estimates for ADHD readers.

2|Updated Jul 28, 2026
One-click install
npx skills add https://github.com/mbadali25/useful-claude-add-ons --skill i-have-adhd-mbadali25
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: i-have-adhd
Source: https://github.com/mbadali25/useful-claude-add-ons/tree/main/skills/i-have-adhd
Command: npx skills add https://github.com/mbadali25/useful-claude-add-ons --skill i-have-adhd-mbadali25

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Standard AI responses bury the actionable answer under preamble, tangents, and vague estimates, which makes them hard to act on for readers with ADHD who have limited working memory and struggle with task initiation. This Skill reshapes every response so the next action is always obvious, small, and immediately doable. ## Core Features & Use Cases - Action-first formatting: Leads every response with a runnable command, path, or snippet, numbers multi-step work, and ends with one concrete next action doable in under two minutes. - State restatement and visible progress: Restates position in multi-step work every turn, gives time estimates in concrete units, and surfaces completed wins in concrete terms. - Session persistence with escape hatches: Stays active until the reader says "stop adhd mode", and overrides its own rules for explanations, destructive actions, debug spirals, and genuine ambiguity. - Use Case: A developer with ADHD asks for help fixing a failing auth test. Instead of a prose walkthrough, they get the exact command to run first, a numbered 3-step fix, a specific time estimate, and one clear next action. ## Quick Start Invoke /i-have-adhd to make every response for the rest of the session action-first and easy to execute, then say "stop adhd mode" when you want normal formatting back.

Frequently Asked Questions about i-have-adhd

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make AI responses easier to act on with ADHD?

Invoke /i-have-adhd at the start of a session. Every response then leads with the next runnable action, numbers multi-step work, restates progress each turn, and ends with one concrete step doable in under two minutes.

How do I turn off ADHD output mode once it is active?

Say "stop adhd mode" or "normal mode" in the chat. The assistant confirms in one line and returns to its default response style for the rest of the session.

Does the ADHD formatting apply to long explanations and walkthroughs?

Yes, but asking to "explain" or "walk me through" overrides the brevity rules. The body runs as long as the topic needs with skimmable headers, while preamble and closing pleasantries are still removed.

Can I use this ADHD output style with Gemini CLI or other agents?

Yes. The skill ships a Gemini CLI custom command (agents/gemini.toml) you copy to ~/.gemini/commands/, plus an OpenAI-compatible agent definition (agents/openai.yaml) for cross-platform use.

When does the skill break its own formatting rules?

It overrides defaults for destructive actions (confirms first), debug spirals (names the suspect assumption), genuine ambiguity (asks one clarifying question), and when the host harness's system prompt conflicts with a rule.