other / skill
i-have-adhd
Make your coding assistant lead with the next action, number the steps and skip the filler in its replies.
At a glance
- Purpose
- Make your coding assistant lead with the next action, number the steps and skip the filler in its replies.
- Runs in
- Local agent with shell
- Operating systems
- Not stated
- Needs
- Runtime: Not stated; Needs internet: Not stated; Needs accounts or API keys beyond your agent: Not stated
- Files and data
- Reads files: Not stated; Writes files: Not stated; Sends data to other services: Not stated
- Tool type
- Skill
- Delivery
- From GitHub
- Version
- Latest on the main branch
- Access
- Code on GitHub
- Compatibility
- The README describes it as a skill for your coding assistant and gives Claude Code plugin commands for swapping in your own copy. It does not list supported assistants. The repository's file list has entries named for Codex, Cursor, OpenCode, Gemini, Kimi and Qwen, which the README does not describe.
- External costs
- The repository is MIT-licensed and states no pricing. Your coding agent or model provider may charge for usage.
- Permissions
- The skill acts through your coding agent with the access you give it. According to the README, its rules change how your assistant writes its replies. Your assistant installs it when you paste the README's prompt, and swapping in your own fork uses Claude Code plugin commands.
- Usage terms
- MIT License, as stated in the repository. See its LICENSE file for the exact terms.
Code on GitHub
ayghri/i-have-adhd
MITA skill to stop your coding agent from burying the answer. ADHD-friendly output.
Topics: adhd claude- claude-code-plugin claude-skills developer-tools productivity
Public GitHub data fetched · 0 days old
Skill folders in this repository (2)
Folders that contain a SKILL.md file, from GitHub's file list on .
What it does
i-have-adhd is a skill for coding assistants. According to the README, it stops the assistant from burying the answer: it puts the action first, numbers the steps and drops filler such as "Hope this helps!". The README presents the result as ADHD-friendly output and says no ADHD diagnosis is needed.The README lists 10 rules. The first five are: lead with the next action, number multi-step tasks, end with one concrete next step, suppress tangents and restate state every turn. The last five are: give specific time estimates in minutes, make wins visible, state errors matter-of-factly, cap lists at 5 items, and use no preamble, recap or closers. The full text is in the skill's SKILL.md file.
The README shows a before and after example of a reply about an authentication fix. It says the skill is loosely based on a book about adult ADHD, adapted for how an AI model should respond, not for how a person should organize their day.
Who it is for
Developers who use a coding assistant and want its replies to put the next action first, which the README describes as ADHD-friendly output.Example tasks
Ask a coding question and get the next action first.Get numbered steps for a multi-step change.
Read an error explained in a matter-of-fact way, with one concrete next step.
Get time estimates in minutes instead of vague phrases.
Fork the repository and edit the skill's SKILL.md to tune the rules.