Skip to content
mcp/skillhub

Agent Skill

I Have Adhd skill

i-have-adhdayghri/i-have-adhd.cursor/skills/i-have-adhd/SKILL.md

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

58kMIT

always on

62 tokname + description

once used

1,638 tokSKILL.md body

bundled files

0

repo stars

58kGitHub

Install the I Have Adhd skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/ayghri/i-have-adhd --skill i-have-adhd

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/ayghri/i-have-adhd.git /tmp/i-have-adhd
mkdir -p ~/.claude/skills
cp -R /tmp/i-have-adhd/.cursor/skills/i-have-adhd ~/.claude/skills/i-have-adhd

For one project only, copy the folder into .claude/skills/ in that project instead. It is marked disable-model-invocation, so the agent won't pick it on its own: you run it as /i-have-adhd.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description62 tok
When the agent uses itThe SKILL.md instructions1,638 tok
Only if openedNo bundled files—

Until it is used, i-have-adhd costs about 22× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 2 skills from ayghri/i-have-adhd would load 124 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • i-have-adhd
  • Persistence
  • What ADHD changes about reading
  • Rules
  • 1. Lead with the next action
  • 2. Number multi-step tasks
  • 3. End with one concrete next action
  • 4. Suppress tangents
  • 5. Restate state every turn
  • 6. Give specific time estimates
  • 7. Make completed work visible
  • 8. Matter-of-fact tone for errors
  • 9. Cap lists to 5 items
  • 10. No preamble, no recap, no closing pleasantries
  • When to break the rules
  • Pre-send check