A new skill, 'i-have-adhd', has been introduced for coding assistants. This skill is designed to modify the output style of AI tools, making responses more concise and action-oriented. It is intended to help users quickly identify the next steps without sifting through extraneous information.
The 'i-have-adhd' skill operates based on ten specific rules. These rules include leading with the next action, numbering multi-step tasks, ending with a concrete next step, suppressing tangents, and restating the state in each turn. It also emphasizes specific time estimates, visible wins, matter-of-fact error reporting, and capping lists at five items.
The skill also dictates no preamble, no recap, and no closers in the AI's responses, aiming for direct communication.
Users can install the 'i-have-adhd' skill by copying a command into their CLI prompt, with specific instructions available in the project's AGENTS.md file. The skill is also customizable; users can fork the repository, edit the SKILL.md file, and then swap in their modified version using provided Claude plugin commands. This allows for personalized adjustments to the output rules.
The skill's design is loosely based on principles from 'The Adult ADHD Tool Kit' by J. Russell Ramsay and Anthony L. Rostain, adapted for how an LLM should respond. The project is released under the MIT license.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
A new skill named 'i-have-adhd' has been released for coding assistants, designed to provide more direct and actionable responses. It aims to prevent AI from burying answers by leading with actions, numbering steps, and avoiding conversational filler.