i-have-adhd  by ayghri

LLM output enhancement for directness and actionability

Created 1 month ago
363 stars

Top 77.2% on SourcePulse

GitHubView on GitHub
Project Summary

<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> This project provides a Claude Code skill designed to reformat large language model (LLM) outputs for improved clarity and actionability, specifically targeting users who benefit from ADHD-friendly communication styles. It addresses the common LLM tendency to bury crucial information within verbose conversational text, offering a direct, step-by-step approach to answers. The primary benefit is enabling users to quickly grasp and act upon LLM-generated information without sifting through extraneous content.

How It Works

The skill operates by intercepting and transforming LLM responses according to a strict set of rules defined in SKILL.md. These rules prioritize leading with the immediate next action, numbering multi-step tasks, providing concrete next steps, suppressing tangents, restating relevant state, offering specific time estimates, making progress visible, and presenting errors factually. This structured output aims to mimic the directness and clarity beneficial for individuals with ADHD, ensuring key information is immediately accessible.

Quick Start & Requirements

  • Installation involves cloning the repository and adding it as a Claude plugin:
    git clone https://github.com/ayghri/i-have-adhd ./i-have-adhd
    claude plugin marketplace add ./i-have-adhd
    claude plugin install i-have-adhd@i-have-adhd
    
  • Requires Claude Code environment.
  • No other non-default prerequisites are listed.
  • Setup is expected to be quick, involving standard Git and plugin management commands.
  • Relevant pages: GitHub repository (implied).

Highlighted Details

  • Implements a strict 10-rule output format for LLM responses.
  • Transforms verbose, conversational LLM outputs into concise, actionable steps.
  • Directly addresses usability challenges for users with ADHD.
  • "Before" and "After" examples clearly demonstrate the transformation.

Maintenance & Community

  • The project is hosted on GitHub. No specific details on active contributors, sponsorships, or community channels (like Discord/Slack) are provided in the README.

Licensing & Compatibility

  • License: MIT.
  • The MIT license is permissive and generally compatible with commercial use and closed-source linking, allowing broad adoption.

Limitations & Caveats

  • The skill is specific to the Claude Code environment and its plugin system.
  • Effectiveness is subjective and depends on user preference for direct, rule-based communication.
  • The README does not detail potential edge cases or limitations in transforming complex LLM outputs.
Health Check
Last Commit

1 month ago

Responsiveness

Inactive

Pull Requests (30d)
1
Issues (30d)
1
Star History
146 stars in the last 30 days

Explore Similar Projects

Starred by Eric Zhu Eric Zhu(Coauthor of AutoGen; Research Scientist at Microsoft Research) and Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems").

PromptWizard by microsoft

0.1%
4k
Agent-driven framework for task-aware prompt optimization
Created 2 years ago
Updated 9 months ago
Feedback? Help us improve.