i-have-adhd

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

2|Updated Jul 11, 2026
One-click install
npx skills add https://github.com/MoofonLi/dev-ready --skill i-have-adhd-moofonli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: i-have-adhd
Source: https://github.com/MoofonLi/dev-ready/tree/main/src/dev_ready/templates/claude/skills/i-have-adhd
Command: npx skills add https://github.com/MoofonLi/dev-ready --skill i-have-adhd-moofonli

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 doable immediately. ## 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. - State Restatement & Time Estimates: Restates progress every turn ("Step 3 of 5 done") and gives estimates in concrete units instead of vague phrases. - Session Persistence: Rules apply to every response until the user says "stop adhd mode", with explicit overrides for explanations, destructive actions, and debug spirals. - 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, the cause of the error stated plainly, and one two-minute next step. ## Quick Start Invoke /i-have-adhd and then ask your coding 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 at the start of your session. Every response then leads with the next action, numbers multi-step work, restates progress each turn, and ends with one concrete step you can do in under two minutes.

How do I turn off ADHD output mode?

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

Does ADHD formatting work for long explanations?

Yes. Asking to "explain" or "walk me through" overrides brevity: the body runs as long as the topic needs with skimmable headers, while preamble and closing pleasantries stay removed.

Can I use this ADHD output style with Gemini CLI?

Yes. Copy the included agents/gemini.toml file to ~/.gemini/commands/i-have-adhd.toml, then type /i-have-adhd in Gemini CLI. The command is self-contained and works from any directory.

When does the skill break its own formatting rules?

Rules yield for destructive actions (confirmation first), debug spirals (one diagnostic question), genuine ambiguity (one clarifying question), explicit explanation requests, and conflicts with the host harness's system prompt.