Attention-kind (ADHD-friendly reply style)
A conversation-style skill that makes Claude lead with the bottom line, break replies into scannable blocks, and never trim warnings or exact numbers.
UtilitiesBeginner★ 1,025⑂ 30AI score 9/10Last updated: Sep 6, 2026
What it does
- Changes only how Claude talks for the rest of the chat, not how it codes or how much work it does.
- Bottom line in sentence one, so a reader who stops there still has the answer.
- No silent omission: risks, preconditions, exact numbers, thresholds and scoped conditions ("only workspaces under 14 days") must be stated precisely, never rounded off for brevity.
- When there's genuinely too much: it neither dumps everything nor drops it, it names what's held back and offers it ("three more areas, want them?").
- When you say "really explain it" or "walk me through it", the brevity rules are suspended and you get the full picture, still broken into scannable blocks.
- Format rules: each point as a
**→ Lead-in.**paragraph, bold carrying the whole gist, 1-3 sentence paragraphs, tables under 5 rows, no filler openers, no em-dashes.
Who it's for
- Anyone who bounces off walls of text and loses the one thing that mattered (ADHD included).
- Developers running Claude Code in a terminal who are tired of scrolling long reports.
- Reviewers and decision-makers who want "conclusion first, caveats intact".
- Non-native English readers who prefer plain, direct wording.
Examples
- Invoke
/attention-kindat the start of a session; every later reply opens with the takeaway and is split into scannable blocks. - Hand off a large refactor: instead of a long report you get a one-line headline, the first move, and a clear next action, with the rest available on request.
- Ask "explain the full reasoning behind this migration": brevity is suspended and every threshold, scoped condition and risk is delivered in full.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/alexgreensh/attention-span/HEAD/skills/attention-kind/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/attention-kind folder from the GitHub repo alexgreensh/attention-span into my ~/.claude/skills/attention-kind/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/alexgreensh/attention-span.git /tmp/attention-span && mkdir -p ~/.claude/skills && cp -r /tmp/attention-span/skills/attention-kind ~/.claude/skills/ && rm -rf /tmp/attention-span⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Create the skills folder:
mkdir -p ~/.claude/skills - Clone the repo:
git clone https://github.com/alexgreensh/attention-span.git /tmp/attention-span - Copy the skill:
cp -r /tmp/attention-span/skills/attention-kind ~/.claude/skills/ - Clean up:
rm -rf /tmp/attention-span - Restart Claude Code and invoke it manually, e.g.
/attention-kind. It setsdisable-model-invocation: true, so it will never auto-trigger. - For a single project only, copy the folder into that project's
.claude/skills/instead of your home directory.
View source on GitHub ↗License: AGPL-3.0