i-have-adhd

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

1|Updated Sep 13, 2026
One-click install
npx skills add https://github.com/silentFellow/public-dotfiles --skill i-have-adhd-silentfellow
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: i-have-adhd
Source: https://github.com/silentFellow/public-dotfiles/tree/main/agents/skills/i-have-adhd
Command: npx skills add https://github.com/silentFellow/public-dotfiles --skill i-have-adhd-silentfellow

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 & Visible Wins: Restates progress every turn ("Step 3 of 5 done"), gives time estimates in concrete units, and surfaces completed work in concrete terms. - Session-Wide Persistence with Toggle: Applies to all responses from session start, toggled off with "normal mode" and back on with "adhd mode" or /i-have-adhd. - 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 matter-of-fact error diagnosis, and one two-minute next step. ## Quick Start Say "adhd mode" or invoke /i-have-adhd at the start of your session to make every response action-first and easy to execute.

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?▼

Activate this Skill at session start and every response leads with the next action, numbers multi-step work, and ends with one concrete next step. It stays active for the whole session until you say "normal mode" or "stop adhd mode".

How do I turn ADHD output mode on and off?▼

Say "adhd mode" or invoke /i-have-adhd to turn it on, and say "normal mode" or "stop adhd mode" to turn it off. The Skill confirms the change in one line and then returns to the requested style.

Does this output style work with Gemini CLI and OpenAI-compatible agents?▼

Yes. The Skill ships a gemini.toml custom command installable to ~/.gemini/commands for Gemini CLI, plus an openai.yaml interface definition with display name and default prompt for OpenAI-compatible harnesses.

When does the Skill break its own formatting 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 agent harness system prompt conflicts. Safety and task completeness always win over brevity.

Does capping lists at 5 items lose information?▼

No. The cap shapes presentation only: extra items are retained internally and shown when asked or when they become the next items to address. Analysis, search results, and candidate generation are never truncated.