i-have-adhd

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

3|Updated Jul 28, 2026
One-click install
npx skills add https://github.com/marcmarti9/agentit --skill i-have-adhd-marcmarti9
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: i-have-adhd
Source: https://github.com/marcmarti9/agentit/tree/main/skills/i-have-adhd
Command: npx skills add https://github.com/marcmarti9/agentit --skill i-have-adhd-marcmarti9

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. This Skill reshapes every response so the next action is obvious, progress is visible, and working memory is never overloaded. ## Core Features & Use Cases - Action-First Formatting: Leads every response with a runnable command, path, or snippet instead of context or plans. - Persistent Session Mode: Applies ten output rules (numbered steps, state restatement, concrete time estimates, capped lists, no preamble or closers) across the whole session until the user says "stop adhd mode". - Sensible Overrides: Breaks its own rules for explanations, destructive actions, debug spirals, and genuine ambiguity so safety and completeness always win. - 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, and one concrete next step at the end. ## Quick Start Invoke /i-have-adhd and ask your question to receive action-first, numbered responses for the rest of the session.

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 /i-have-adhd to activate a persistent output mode that leads with the next action, numbers multi-step work, and removes preamble and closers. The rules stay active for the whole session until you say "stop adhd mode" or "normal mode".

How to turn off ADHD output mode once enabled?▼

Say "stop adhd mode" or "normal mode" and the assistant confirms in one line, then returns to its default style. The mode otherwise persists across turns and topic changes for the rest of the session.

Does i-have-adhd work with Gemini CLI and OpenAI agents?▼

Yes, the skill ships a Gemini CLI custom command file (agents/gemini.toml) installable to ~/.gemini/commands, and an OpenAI agent manifest (agents/openai.yaml) with implicit invocation disabled. Both wrap the same ten formatting rules.

When does ADHD formatting mode break its own rules?▼

Rules are overridden when you ask for a full explanation, when a destructive action needs confirmation, during debug spirals, when the request is ambiguous, or when the host harness system prompt conflicts. Safety and task completeness always take priority over brevity.

Does the 5-item list cap hide relevant information?▼

No, the cap shapes presentation only. Additional relevant items are retained internally and shown when you ask or when they become the next items to address; analysis, search, and completeness are never limited.