# Where Is the Canonical Ruleset for the i‑have‑adhd Skill Located?

> Find the canonical ruleset for the i-have-adhd skill in the ayghri/i-have-adhd repository. This SKILL.md file is your single source of truth for ADHD-friendly responses.

- Repository: [Ayoub Ghriss/i-have-adhd](https://github.com/ayghri/i-have-adhd)
- Tags: api-reference
- Published: 2026-08-28

---

**The canonical ruleset for the i‑have‑adhd skill is located at [`skills/i-have-adhd/SKILL.md`](https://github.com/ayghri/i-have-adhd/blob/main/skills/i-have-adhd/SKILL.md) in the ayghri/i-have-adhd repository, which serves as the single source of truth for all ADHD‑friendly response behaviors.**

The ayghri/i-have-adhd repository provides an AI skill designed to shape responses according to ADHD‑friendly communication patterns. Understanding the location of the canonical ruleset ensures that developers and contributors modify the correct files when customizing behavior or integrating the skill into external agents.

## Locating the Canonical Skill Definition

The authoritative definition of the *i‑have‑adhd* skill resides in a dedicated skill file within the repository root.

**[`skills/i-have-adhd/SKILL.md`](https://github.com/ayghri/i-have-adhd/blob/main/skills/i-have-adhd/SKILL.md)** – This Markdown document contains the complete canonical ruleset, including all 10 ADHD‑friendly response rules, persistence behavior specifications, and usage guidelines. As the single source of truth, any modifications to the skill's behavior must originate in this file to maintain consistency across implementations.

When integrating the skill into custom agents or plugins, reference this exact path to ensure you are loading the most current and authoritative rule definitions.

## Understanding the Cursor Mirror File

A secondary copy exists specifically for Cursor IDE compatibility, but it is not the authoritative source.

**[`.cursor/skills/i-have-adhd/SKILL.md`](https://github.com/ayghri/i-have-adhd/blob/main/.cursor/skills/i-have-adhd/SKILL.md)** – This file serves as a generated mirror used by the Cursor IDE for local development. While functional for IDE users, changes made directly to this location will not persist or propagate to other environments. Contributors must treat this as a read-only copy that requires manual synchronization with the canonical file.

To maintain consistency across the codebase, always apply edits to [`skills/i-have-adhd/SKILL.md`](https://github.com/ayghri/i-have-adhd/blob/main/skills/i-have-adhd/SKILL.md) first, then synchronize the changes to the Cursor mirror location.

## Loading and Using the Skill Programmatically

Developers can reference the canonical ruleset in plugin manifests or load it dynamically at runtime.

To register the skill in a plugin configuration, specify the canonical path in the manifest:

```json
{
  "name": "i-have-adhd",
  "description": "ADHD‑aware response shaping",
  "skillPath": "skills/i-have-adhd/SKILL.md"
}

```

For runtime integration, import the skill loader and apply the rules to raw output:

```javascript
import { loadSkill } from 'opencode';

// Load the canonical skill definition
const adhdSkill = loadSkill('skills/i-have-adhd/SKILL.md');

// Apply the skill to a response
const response = adhdSkill.apply(rawOutput);

```

## Synchronizing Mirror Files

When updating the canonical ruleset, contributors must manually sync the changes to support Cursor IDE users.

Execute the following command from the repository root to update the mirror:

```bash
cp skills/i-have-adhd/SKILL.md .cursor/skills/i-have-adhd/SKILL.md

```

This synchronization ensures that both the authoritative source and the IDE‑compatible mirror remain aligned, preventing behavioral drift between different usage contexts.

## Summary

- The **canonical ruleset for the i‑have‑adhd skill** is located at [`skills/i-have-adhd/SKILL.md`](https://github.com/ayghri/i-have-adhd/blob/main/skills/i-have-adhd/SKILL.md) in the ayghri/i-have-adhd repository.
- This file contains **10 ADHD‑friendly response rules** and defines persistence behavior as the single source of truth.
- A **Cursor IDE mirror** exists at [`.cursor/skills/i-have-adhd/SKILL.md`](https://github.com/ayghri/i-have-adhd/blob/main/.cursor/skills/i-have-adhd/SKILL.md) but must be synchronized manually from the canonical source.
- Developers load the skill by referencing the canonical path in **JSON manifests** or **JavaScript runtime calls**.
- The [`AGENTS.md`](https://github.com/ayghri/i-have-adhd/blob/main/AGENTS.md) file provides additional repository mapping and agent guidance for navigating the codebase.

## Frequently Asked Questions

### What file contains the official i-have-adhd skill rules?

The official rules reside in [`skills/i-have-adhd/SKILL.md`](https://github.com/ayghri/i-have-adhd/blob/main/skills/i-have-adhd/SKILL.md) at the repository root. This Markdown file serves as the single source of truth, containing the complete set of 10 ADHD‑friendly response rules and behavioral guidelines that define how the skill shapes AI outputs.

### How do I sync changes between the canonical file and the Cursor mirror?

After editing [`skills/i-have-adhd/SKILL.md`](https://github.com/ayghri/i-have-adhd/blob/main/skills/i-have-adhd/SKILL.md), run `cp skills/i-have-adhd/SKILL.md .cursor/skills/i-have-adhd/SKILL.md` from the repository root. This manual copy operation updates the Cursor IDE mirror, ensuring IDE users receive the same behavioral updates defined in the canonical ruleset.

### What rules are defined in the SKILL.md file?

The canonical [`SKILL.md`](https://github.com/ayghri/i-have-adhd/blob/main/SKILL.md) defines **10 specific ADHD‑friendly response rules** that govern how AI agents format and structure outputs for neurodivergent users, along with specifications for persistence behavior and usage guidelines that maintain consistent communication patterns.

### Can I load the i-have-adhd skill in custom AI agents?

Yes. Import the skill loader from your runtime environment—such as `opencode`—and invoke `loadSkill('skills/i-have-adhd/SKILL.md')` to instantiate the skill object. You can then apply the loaded rules to raw model outputs using the `.apply()` method to generate ADHD‑aware responses.