i-have-adhd

Formats AI responses for ADHD readers with action-first structure and numbered steps.

1|Updated Aug 11, 2026
One-click install
npx skills add https://github.com/Chia1104/agent-air --skill i-have-adhd-chia1104
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: i-have-adhd
Source: https://github.com/Chia1104/agent-air/tree/main/skills/shared/i-have-adhd
Command: npx skills add https://github.com/Chia1104/agent-air --skill i-have-adhd-chia1104

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Standard AI responses bury the actionable answer under preamble, tangents, and vague recaps, 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 instead of context, and ends with one concrete next step doable in under two minutes. - Persistent Session Rules: Applies ten output rules (numbered steps, state restating, specific time estimates, capped lists, no preamble or closers) across the entire session until the user says "stop adhd mode". - Sensible Overrides: Breaks its own rules when safety or clarity demands it, such as confirming destructive actions, escaping debug spirals, or honoring harness system prompts. - Use Case: A developer with ADHD asks for help fixing a failing auth test. Instead of a long explanation, they get: the exact command to run first, a numbered fix sequence, a concrete time estimate, and one clear next action. ## Quick Start Invoke the skill with /i-have-adhd and it will shape all subsequent responses into action-first, ADHD-friendly output until you say stop adhd mode.

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 follow with ADHD?▼

Invoke the skill with /i-have-adhd and every subsequent response leads with the next runnable action, uses numbered steps for multi-step work, and ends with one concrete task doable in under two minutes. It stays active until you say "stop adhd mode".

How to get action-first answers instead of long explanations from an AI assistant?▼

This skill bans preamble, recaps, and closing pleasantries, putting the command, path, or snippet on the first line. If you want depth, ask the assistant to "explain" or "walk me through" and it will go long while keeping the clean structure.

Does the ADHD formatting mode persist across the whole conversation?▼

Yes, the rules apply to every response for the rest of the session and do not expire when the topic changes. They turn off only when you explicitly say "stop adhd mode" or "normal mode".

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

Yes, the skill ships an agents/gemini.toml custom command you copy to ~/.gemini/commands/ and an agents/openai.yaml interface definition. Both deliver the same ten formatting rules as a self-contained global command.

When does the skill break its own brevity rules?▼

It overrides defaults for explicit explanation requests, destructive actions requiring confirmation, debug spirals needing a diagnostic question, genuine ambiguity, and conflicts with the host harness's system prompt. Safety and task correctness always win over brevity.