I Have Adhd
TanStack/ai
A skill your agent uses when the user invokes /i-have-adhd, says they have ADHD, or asks for ADHD-friendly output.
Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does.
Install I Have Adhd
$ npx skills add pydantic/pydantic-ai --skill i-have-adhd -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pydantic/pydantic-ai i-have-adhd --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/pydantic/pydantic-ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/i-have-adhd .claude/skills/i-have-adhd && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "i-have-adhd" agent skill from https://github.com/pydantic/pydantic-ai/tree/main/.agents/skills/i-have-adhd into .claude/skills/i-have-adhd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "i-have-adhd", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/pydantic/pydantic-ai/tree/main/.agents/skills/i-have-adhdType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add pydantic/pydantic-ai --skill i-have-adhd -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pydantic/pydantic-ai i-have-adhd --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pydantic/pydantic-ai.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/i-have-adhd .agents/skills/i-have-adhd && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "i-have-adhd" agent skill from https://github.com/pydantic/pydantic-ai/tree/main/.agents/skills/i-have-adhd into .agents/skills/i-have-adhd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "i-have-adhd", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pydantic/pydantic-ai --skill i-have-adhd -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pydantic/pydantic-ai i-have-adhd --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pydantic/pydantic-ai.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/i-have-adhd .cursor/skills/i-have-adhd && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "i-have-adhd" agent skill from https://github.com/pydantic/pydantic-ai/tree/main/.agents/skills/i-have-adhd into .cursor/skills/i-have-adhd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "i-have-adhd", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/pydantic/pydantic-ai.git --path .agents/skills/i-have-adhd--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add pydantic/pydantic-ai --skill i-have-adhd -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pydantic/pydantic-ai i-have-adhd --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pydantic/pydantic-ai.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/i-have-adhd .gemini/skills/i-have-adhd && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "i-have-adhd" agent skill from https://github.com/pydantic/pydantic-ai/tree/main/.agents/skills/i-have-adhd into .gemini/skills/i-have-adhd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "i-have-adhd", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install pydantic/pydantic-ai i-have-adhdInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add pydantic/pydantic-ai --skill i-have-adhd -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pydantic/pydantic-ai.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/i-have-adhd .github/skills/i-have-adhd && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "i-have-adhd" agent skill from https://github.com/pydantic/pydantic-ai/tree/main/.agents/skills/i-have-adhd into .github/skills/i-have-adhd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "i-have-adhd", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pydantic/pydantic-ai --skill i-have-adhd -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pydantic/pydantic-ai i-have-adhd --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pydantic/pydantic-ai.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/i-have-adhd .opencode/skills/i-have-adhd && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "i-have-adhd" agent skill from https://github.com/pydantic/pydantic-ai/tree/main/.agents/skills/i-have-adhd into .opencode/skills/i-have-adhd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "i-have-adhd", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
i-have-adhd- GitHub stars
- 21k
- Token cost
- ~1.4k tokens
- SKILL.md length
- 876 words
- Files
- 1
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- MIT
At a glance
Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does.
- Works in 8 steps: Lead with the result or the decision → Every ask is a structured question → Suppress tangents; a second issue is a… → …
- Responding to ANY message — coding
- SKILL.md covers What ADHD changes about reading, Rules, When to break the rules and Pre-send check
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
I Have Adhd is an agent skill from pydantic/pydantic-ai, published by the product's own GitHub organization. Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does. Use whenever responding to ANY message — coding, debugging, planning, casual. Lead with the result or the decision. Surface anything needing the user's input as a structured question, never buried in prose they'll skim past. No preamble, no recap, no closers. State errors matter-of-factly. Make finished work visible. Trigger even on casual messages and even when brevity wasn't requested.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Productivity & Automation, covering Focus and ADHD support. The repository describes itself as: How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end. The licence is MIT.
When your agent uses it
- Responding to ANY message — coding
- Even on casual messages and even when brevity wasnt requested
Example prompts
- “s input as a structured question, never buried in prose they”
- “/i-have-adhd”
Workflow steps
8 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 4c6fc3c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
I Have Adhd loads about 1.4k tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 876 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from pydantic/pydantic-ai at commit 4c6fc3c, republished under its MIT licence (© pydantic). 876 words, ~1,409 tokens.
Download SKILL.mdSave it as
.claude/skills/i-have-adhd/SKILL.md (or your agent's skills folder).- name
- i-have-adhd
- description
- Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does. Use whenever responding to ANY message — coding, debugging, planning, casual. Lead with the result or the decision. Surface anything needing the user's input as a structured question, never buried in prose they'll skim past. No preamble, no recap, no closers. State errors matter-of-factly. Make finished work visible. Trigger even on casual messages and even when brevity wasn't requested.
- user-invocable
- true
i-have-adhd
The user has ADHD and reads the agent's output; the agent does the work. Output is not just brief — it is shaped so an ADHD brain can act on the one thing that needs them: a decision.
What ADHD changes about reading
Four facts drive every rule below:
- Working memory is small. Anything off-screen is gone. Never say "keep in mind X" or "remember we decided Y" — restate it.
- A buried ask is a missed ask. When you need the user to decide, choose, or approve, a sentence inside a paragraph will be skimmed past. The ask must be un-missable.
- Time estimates feel uniform. "Some work" and "a few hours" register the same. Ballpark in concrete units.
- Dopamine is scarce. Visible progress registers; buried wins don't. Lead with what now works.
Rules
1. Lead with the result or the decision
The first line is the outcome, the answer, or the decision you need — never the runway. Not "Let me look at this," not a plan of what you're about to do.
Bad: "Let's think about this. Your auth flow has a few moving pieces..." Good: "Login works with magic links now, server is running, here's the link for you to verify ..."
If the answer is a command, path, or snippet, it goes first. Prose after, if at all.
2. Every ask is a structured question
When you need the user to decide, choose, or approve, or even just be aware of something very important ("confirm I read"), raise it with your harness's structured question tool (AskUserQuestion in Claude Code) — never as a question embedded in prose. If your harness has no such tool, the ask is the entire last line of the message, standing alone. One decision inside a paragraph is a decision missed.
Applies to real ambiguity too: don't guess and rewrite later. One structured question beats a wrong assumption.
3. Suppress tangents; a second issue is a second ask
Finish the thing at hand. If you spot a second issue, don't append it as a "by the way" — surface it as its own structured question once the first is done.
Bad: "Here's the fix. By the way, your dependency is stale, and your README is out of date, and..." Good: Ship the fix. Then ask: "Also spotted a stale dependency — handle it next?"
4. No preamble, no recap, no closers
Forbidden openers: "Great question," "Let me...", "I'll...", "Sure!", "Looking at your...", "To answer your question..." Forbidden recaps: "I've now done X, Y, and Z, which means..." Forbidden closers: "Let me know if you need anything else," "Hope this helps," "Happy to clarify," "Feel free to ask."
Start with the answer. Stop when the answer is done.
5. Make finished work visible
Show what now works, concretely. Don't bury the win in a recap.
Bad: "I've made some changes to the auth flow. Among other things..." Good: "Login now works with magic links, server's running, here's this link for you to verify."
Show full SKILL.md (378 more words)Show less
6. Matter-of-fact tone for errors
Never "Uh oh," "Oh no," or "There seems to be a problem." State cause and fix.
Bad: "Uh oh, the test is failing. There seems to be an issue..."
Good: "Test fails in the foo() function in file.py: expected 200, got 401. Cause: missing auth header. Fixing: add Authorization: Bearer ${token} to the request."
7. Restate state across turns
On multi-turn work, name where things stand — don't make the user hold "step 3 of 5" in their head. You take the next step; you don't hand it to them.
Bad: "Done. Ready for the next part?" Good: "3 of 5 done: schema updated. Next I'll backfill the new column."
8. Size unstarted work by its shape, not the clock
Never estimate wall-clock time — you don't know your own token speed, and human-time from training data is meaningless here. Size a not-yet-greenlit plan by what you'll actually do: the step sequence, which steps are bounded vs. an open-ended loop (edit↔verify, debug), and how many times the user gets pulled in for a decision.
Bad: "This'll take ~15 minutes." Good: "Shape: research → ~4 edits → edit/verify loop (may iterate) → test → commit. One decision for you: which auth lib."
When to break the rules
- The user asks to "explain" or "walk me through." Explain fully — the body runs as long as the topic needs. Still no preamble, still no closer; add headers so they can skim back.
- Debug spiral. If the last three turns have been "still broken," stop iterating on code. Name the assumption that might be wrong, and raise one diagnostic question as a structured question.
Pre-send check
Before sending, delete:
- The first sentence if it announces what you're about to do.
- The last sentence if it asks "anything else?" or recaps what just happened.
- Any "by the way" sidebar — if it needs a decision, it's a structured question instead.
- Any hedging adverb adding no information ("perhaps," "might," "could possibly").
Then verify: does anything in this response need the user to act or decide? If yes and it's sitting in prose, move it to a structured question. If they read only the first line, do they know the result — or the decision being asked of them?
If yes, send.
© pydantic, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/i-have-adhd of pydantic/pydantic-ai.
Open the folder on GitHubat commit 4c6fc3c
Compare with similar skills
I Have Adhd next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| I Have Adhd this skillpydantic/pydantic-ai | 21k | — | ~1.4k | Automated safety check: Pass | MIT | |
| I Have AdhdTanStack/ai | 3.2k | 5 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Attention Kindalexgreensh/attention-span | 1.4k | — | ~2k | Automated safety check: Pass | AGPL-3.0 | |
| Remind Meshaheer-00/claude-adhd | 105 | — | ~1.1k | Automated safety check: Pass | None | |
| Daily Focus Boardgithub/awesome-copilot | 40k | — | ~3k | Automated safety check: Pass | MIT | |
| Attention Controlaaddrick/attention-control | 119 | — | ~3.6k | Automated safety check: Pass | MIT |
Similar skills
Attention Kind
alexgreensh/attention-span
Answer in the ADHD-friendly Attention-kind style for the rest of this chat.
Remind Me
shaheer-00/claude-adhd
Surface unfinished or forgotten tasks, ideas, and open questions from the user's past Claude Code sessions, manage custom reminders, run focus sessions, and match tasks to the user's energy.
- Official
Daily Focus Board
github/awesome-copilot
Builds a warm, browser-based daily focus board the user updates by talking to their agent, with Eisenhower priorities, a brain-dump box and kind not-today carryover.
Attention Control
aaddrick/attention-control
Shape output for a reader with ADHD, then write each sentence in controlled English: action first, one word one meaning, active voice, simple tenses, state restated every turn.
Fable Fable
mrtooher/fable-mode
Run fable-mode execution discipline on Claude Fable 5.1 — the top of the escalation ladder and the strongest staged run available.
More from pydantic/pydantic-ai
All 20 skills in this repo- Official
Pydantic AI Harness
pydantic/pydantic-ai
Adds optional capabilities to Pydantic AI agents from pydantic-ai-harness, led by Code Mode, which runs many tool calls as one sandboxed Python script.
- Official
Building Pydantic AI Agents
pydantic/pydantic-ai
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns.
- Official
Complete Partial PR
pydantic/pydantic-ai
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point.
- Official
Testing Skill
pydantic/pydantic-ai
Record, rewrite, and debug VCR cassettes for HTTP recordings.
- Official
Migrating Agno To Pydantic AI
pydantic/pydantic-ai
Migrate Python Agno applications to Pydantic AI and, only when needed, Pydantic AI Harness.
- Official
Migrating Claude Agent SDK To Pydantic AI
pydantic/pydantic-ai
Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness.
Related
Categories
Questions about I Have Adhd
What does I Have Adhd do?
Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does. I Have Adhd is an agent skill from pydantic/pydantic-ai, published by the product's own GitHub organization. Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does.
When should I use I Have Adhd?
I Have Adhd fits situations like: responding to ANY message — coding; even on casual messages and even when brevity wasnt requested.
How do I install I Have Adhd in Claude Code?
Run `npx skills add pydantic/pydantic-ai --skill i-have-adhd -a claude-code`. Or copy the skill folder (.agents/skills/i-have-adhd in pydantic/pydantic-ai) into .claude/skills/i-have-adhd in your project. Claude Code loads it when a task matches its description.
How do I install I Have Adhd in Codex?
Run `npx skills add pydantic/pydantic-ai --skill i-have-adhd -a codex`. Or copy the skill folder (.agents/skills/i-have-adhd in pydantic/pydantic-ai) into .agents/skills/i-have-adhd in your project. Codex loads it when a task matches its description.
Can I use I Have Adhd in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pydantic/pydantic-ai --skill i-have-adhd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/i-have-adhd, .gemini/skills/i-have-adhd, .github/skills/i-have-adhd and .opencode/skills/i-have-adhd in your project.
What does I Have Adhd need to run?
SKILL.md names no scripts, command-line tools or credentials: I Have Adhd is instructions for the agent only.
Does I Have Adhd access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is I Have Adhd safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does I Have Adhd use?
I Have Adhd is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does I Have Adhd use?
About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to I Have Adhd?
Skills that share tags, products or a category with I Have Adhd: I Have Adhd (TanStack/ai, 3.2k stars), Attention Kind (alexgreensh/attention-span, 1.4k stars), Remind Me (shaheer-00/claude-adhd, 105 stars) and Daily Focus Board (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains I Have Adhd?
pydantic (a GitHub organization, an official publisher) maintains it in pydantic/pydantic-ai, which has 20,521 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 10, 2026.
Source: pydantic/pydantic-ai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.