Submit a tool

Search iThub

Search tools, categories and collections. Type at least two characters.

Explore all tools
↑ ↓ to explore resultsEnter to open · Esc to close

i-have-adhd

A skill that shapes coding assistant responses into action-first, ADHD-friendly output.

Visit website Save

i-have-adhd is an MIT-licensed coding assistant skill that puts the next action first, numbers multi-step work and restates progress. Activation varies by host.

Pricing
Open source
60,342stars3,519forks
0views
Updated

What is i-have-adhd?

i-have-adhd is a skill for your coding assistant that stops it from burying the answer. It produces ADHD-friendly output, and the project states that no ADHD diagnosis is needed to use it.

The skill applies 10 rules, with the full text in SKILL.md. They include leading with the next action, numbering multi-step tasks, ending with one concrete next step, suppressing tangents, restating state every turn, making wins visible, reporting errors in a matter-of-fact way, capping lists at 5 items, and dropping preamble, recaps and closers.

The README says it is loosely based on The Adult ADHD Tool Kit by J. Russell Ramsay and Anthony L. Rostain, adapted for how an LLM should respond. To install, paste a prompt that asks your assistant to install the skill from the GitHub repository and follow its AGENTS.md. You can fork the repository, edit SKILL.md and swap your copy in. The license is MIT.

Key capabilities

  • A skill with 10 response rules
  • Action-first answers with numbered steps
  • One concrete next step at the end of each reply
  • Lists capped at 5 items
  • A fork-and-edit route to tune SKILL.md
  • MIT license
Advertisements

Where i-have-adhd fits

  • Lead with the next action The first line of a reply says what to do, instead of opening with background.
  • Numbered multi-step tasks Steps are numbered, and a reply ends with one concrete next step.
  • Suppressed tangents Side topics are held back so the reply stays on the task.
  • State restated every turn Each reply restates where the work stands, with specific time estimates in minutes rather than vague ones.
  • Visible wins and matter-of-fact errors Completed steps are made visible, and errors are reported plainly.
  • Capped lists Lists are limited to five items.
  • No preamble, recap or closers Replies skip openers such as "Great question" and closing phrases such as "Hope this helps".
  • Tunable rules The ten rules live in SKILL.md, which can be forked and edited.

Reviews of i-have-adhd

No reviews yet

Be the first to share your experience with i-have-adhd.

Loading review form…

Alternatives to i-have-adhd

ARAgent ReachAgent Reach installs and configures tools that let command-capable AI agents search platforms, read structured content and retrieve transcripts through a shared command-line interface.AArchifyArchify is an open-source agent skill that turns descriptions, plans and repositories into interactive diagrams delivered as self-contained HTML files.CAClaude AdsClaude Ads is an open-source Claude Code skill that analyzes ad account exports and screenshots for evidence-backed audits, campaign plans and draft changes.
Compare i-have-adhd with these tools →