i-have-adhd: output shaped for ADHD readers
A persistent output style for ADHD readers — lead with the next action, number steps, give time estimates
Curated by Skill Harbor — @ayghri's session-persistent output style that reshapes every agent answer so an ADHD reader can act on it: lead with the one next action (not context), number multi-step work in single bounded steps, end with one concrete under-two-minutes action, suppress tangents, restate state every turn ("Step 3 of 5 done: schema updated"), give specific time estimates ("about 15 minutes if tests already cover this"), make wins visible in concrete terms, use a matter-of-fact error tone (cause and fix, never "Uh oh"), cap lists at five, and strip preamble, recaps and closing pleasantries — with when-to-break-the-rules overrides (explain requests, destructive actions, debug spirals, real ambiguity, a rule that would delete the answer itself) and a pre-send checklist that deletes announcement sentences, "anything else?" closers, hedges and idioms, ending on a first-line/last-line test: does the reader know what to do next and what just happened? Invoke with /i-have-adhd; it stays on until "stop adhd mode". Honest caveats: it shapes presentation only and never limits the analysis itself; MIT-licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
i-have-adhd is a session-persistent output style that reshapes an agent's answers so an ADHD reader can act on them: lead with the one next action, number steps, give specific time estimates, end with one concrete action of under two minutes. It shapes presentation only — the listing is explicit that it never limits the analysis itself. It is a formatting style, not a diagnosis or a treatment, and it makes no therapeutic claim.
At a glance
| What it is | A persistent answer format: the next action first instead of context, multi-step work numbered in single bounded steps, state restated every turn (Step 3 of 5 done), lists capped at five, tangents suppressed, no preamble, recaps or closing pleasantries — with a pre-send checklist and defined overrides for when the rules should break (explanation requests, destructive actions, debug spirals, real ambiguity). |
|---|---|
| Who it's for | Readers with ADHD who find long, context-first agent answers hard to act on, and who want answers restructured around the next action. |
| What you give it | Your normal requests, unchanged. You invoke the style with /i-have-adhd, and it stays on until you say stop adhd mode. |
| What you get | The same analysis, presented differently: one clear next action at the top, numbered bounded steps, specific time estimates, visible wins stated in concrete terms, and a matter-of-fact error tone (cause and fix). Presentation changes; the underlying work does not. |
| Works with | Installed from this listing with the copy-paste install prompt into Muse; once invoked it persists for the session until you stop it. The listing documents formatting behaviour only — nothing medical. |
| Cost | Free |
| Time | A few minutes to install. No extra time per answer — the style applies as the agent writes, and turning it off is one phrase. |
Example — the same answer, reshaped
An example of a typical use, showing only the output format the skill documents — not a reported result, and not a claim about anyone's condition.
- You ask how to fix a failing deployment and invoke /i-have-adhd; instead of background first, the answer opens with the one next action to take.
- The steps come numbered and bounded, with the state restated as it goes (Step 2 of 4 done) and a specific time estimate for the remaining step.
- The answer ends with one concrete action of under two minutes, and no closing pleasantries — you say stop adhd mode whenever you want the normal style back.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 723af7dStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: none — the skill is guidance only, no accounts, keys or tools required Install "i-have-adhd: output shaped for ADHD readers" for me. A session-persistent output style for agents: lead every response with the next action, number multi-step work, restate state every turn, suppress tangents, give specific time estimates, make wins visible, use a matter-of-fact error tone, cap lists at five, strip preamble/recaps/pleasantries — with documented overrides for explanations, destructive actions, debug spirals and ambiguity, plus a pre-send checklist. Invoked with /i-have-adhd, stays on until "stop adhd mode". Repository: https://raw.githubusercontent.com/ayghri/i-have-adhd/723af7d9afaf43eb871dbcce6129e2bf80de90d5/.cursor/skills/i-have-adhd/SKILL.md Pinned version: install the code at commit 723af7d9afaf43eb871dbcce6129e2bf80de90d5 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "i-have-adhd". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. nothing — invoke with /i-have-adhd when I want the style on, or "stop adhd mode" to turn it off). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 723af7d · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.