Parallel divergent ideation via mesh fan-out. An agent skill from prassanna-ravishankar/repowire.

MITAuto-check passedProductivity & Automation

Install Adhd

skills CLI
$ npx skills add prassanna-ravishankar/repowire --skill adhd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install prassanna-ravishankar/repowire adhd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/prassanna-ravishankar/repowire.git skills-src && mkdir -p .claude/skills && cp -r skills-src/daemon-go/cli/assets/orchestrator/.agents/skills/adhd .claude/skills/adhd && rm -rf skills-src

Use ~/.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/

Facts

Skill name
adhd
GitHub stars
264
Token cost
~2.3k tokens
SKILL.md length
1,260 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

Parallel divergent ideation via mesh fan-out. An agent skill from prassanna-ravishankar/repowire.

  • Works in 2 steps: Diverge → Focus
  • Tasks that involve Focus and ADHD support
  • SKILL.md covers Pre-flight, Phase 1 — Diverge, Phase 2 — Focus and Cleanup and resume, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Adhd is an agent skill from prassanna-ravishankar/repowire. Parallel divergent ideation via mesh fan-out. Spawns N frame-shifted peers, scores results, deepens top survivors. Use on open-ended design choices, fuzzy bugs, naming, API surfaces, or explicit /adhd invocation. Skip for syntax, lookups, or closed prompts ("quick", "standard", "canonical").

Its SKILL.md is about 2.3k 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 and Brainstorming. The repository describes itself as: May the agents talk . Connect Claude Code, Opencode, Codex, Pi across projects, across machines and with your telegram. The licence is MIT.

When your agent uses it

  • Tasks that involve Focus and ADHD support
  • Tasks that involve Brainstorming

Example prompts

  • “standard”
  • “canonical”
  • “/adhd”

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Diverge
  2. Focus

What it can do on your machine

Read from SKILL.md and the folder at commit 7c8100a. 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

Adhd loads about 2.3k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 1,260 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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 prassanna-ravishankar/repowire at commit 7c8100a, republished under its MIT licence (© prassanna-ravishankar). 1,260 words, ~2,260 tokens.

Download SKILL.mdSave it as .claude/skills/adhd/SKILL.md (or your agent's skills folder).
name
adhd
description
Parallel divergent ideation via mesh fan-out. Spawns N frame-shifted peers, scores results, deepens top survivors. Use on open-ended design choices, fuzzy bugs, naming, API surfaces, or explicit /adhd invocation. Skip for syntax, lookups, or closed prompts ("quick", "standard", "canonical").
license
MIT
metadata.based-on
ADHD by Udit Akhouri (https://github.com/UditAkhourii/adhd)
metadata.author
repowire

ADHD

Spawn many heads thinking differently, in parallel, then pick. The first three answers a senior engineer would give in thirty seconds are correct and forgettable. The interesting answers live past number three. This skill walks there.

Pre-flight

Expensive: ≈8 peer spawns plus an orchestrator critic turn (5–10x a single answer). Gate every run.

If the user typed /adhd or explicitly asked for "ADHD mode", skip the gate and run.

Otherwise, all three must hold:

  1. Open-ended. Multiple viable answers, not one canonical correct one.
  2. High-stakes. Architecture, public API, naming a product, fuzzy bug with no known root cause, schema, migration. Not throwaway work.
  3. Open phrasing. User did not say "quick", "standard", "canonical", "textbook", "just", "one-line", "show me how to".

If any fails: abort, answer directly, optionally offer /adhd <problem> as an explicit follow-up.

Optional base folder. The invocation may specify a base folder for the diverge/deepen peers (e.g. /adhd <problem> --base /path/to/dir, or the user naming a directory). If given, root every per-frame peer dir under that base (<base>/adhd-<frame>/) instead of the default /tmp. If not given, default to /tmp/adhd-<frame>/. Either way the per-peer isolation rule below still holds — one folder per peer, never a shared path.

Phase 1 — Diverge

Pick 5 frames from the table below. For code-shaped problems: 4 code or design tags plus 1 wild. Otherwise mix.

For each frame, spawn_peer into its own folder — not the orchestrator's workspace and not a folder shared with another branch. Spawning all diverge peers into one shared path (especially the orchestrator's own workspace) collapses them into a colliding display-name family (orchestrator-2, -3, ...), pollutes that workspace's identity space, and tangles the peer registry. Use <base>/adhd-<frame>/ where <base> is the user-supplied base folder from Pre-flight, or /tmp if none was given (so the default is /tmp/adhd-<frame>/). A per-branch git worktree is also fine. One folder per peer keeps names clean (adhd-<frame>), keeps branches truly isolated, and keeps cleanup simple.

Spawn each with a description like adhd-diverge: <frame> and a seeded message containing the frame's vantage prompt, the problem, any user-provided context, and this instruction:

You are in DIVERGENT mode. Generator only, no critic. Generate 6 short distinct ideas under this frame. Each idea is one phrase or one sentence. Do not evaluate, rank, or hedge. The first three obvious answers everyone would give are banned — push past them into the awkward middle. Output a JSON array only, no prose: [{"text": "...", "rationale": "..."}, ...].

Spawn the 5 peers in parallel. Branches must not see each other. Do not pass one branch's output as context to another — anchoring eliminates the diverge.

Phase 2 — Focus

Two passes:

  1. Score + cluster (inline, orchestrator does this). For each idea, rate novelty / viability / fit 0–10. Flag traps with a one-line mechanistic reason (not vague risk). Cluster the pool into 3–6 groups by underlying angle, not surface keywords ("remove-the-server plays", "cache-shaped plays").

  2. Deepen top 3 (spawn one peer per survivor). Rank by 0.35*novelty + 0.40*viability + 0.25*fit, exclude traps, take top 3. For each, spawn_peer with a descriptive name like adhd-deepen: <cluster-or-idea-shorthand> and this seeded message:

You are in FOCUS mode. Take one promising idea and connect dots. Sketch how it would work in 4–8 sentences. Name the load-bearing risk. Name the first concrete step a coder would take. Then generate 3–5 sub-ideas (variations, hybrids, unlocks). JSON only.

Cleanup and resume

After all acks land, kill_peer all 8 (5 diverge + 3 deepen). The process is what's expensive; the session persists in storage and can be resumed later.

In the final reply, include each deepen survivor's session id or peer name so the user can resume the one they want to push on. Diverge sessions are also resumable but rarely revisited.

Pick descriptive names on spawn — the resume list shows descriptions, not internal ids.

Output shape

Render in this order. The structure is the point — do not collapse to prose.

  1. Brief. One or two lines confirming the problem and any reframe.
  2. Wide set. Full pool grouped by cluster, each cluster labeled by angle. Each idea is one phrase with score chips [N7 V8 F9].
  3. Converge. 2–4 idea shortlist with one line each on why. Mark the non-obvious-but-viable pick with ★. List traps separately, each with the one-line reason it's a trap.
  4. Focus. The 3 deepened branches: sketch, load-bearing risk, first concrete step, child ideas. Include the resumable session id for each.
  5. Provocation. One wildcard question or idea that opens a new direction.
Show full SKILL.md (524 more words)Show less

Frames

Pick 5 per run. Vary across sessions so the same problem produces different candidates when re-run.

FrameVantage promptTags
hardware engineerYou think in latency, memory layout, and physical constraints. Re-ask this as a hardware/firmware problem. What does the bus topology, cache, timing budget tell you?code, wild
regulatorYou audit systems for compliance and failure modes. What must be provable, traceable, or refusable here?design, general
10-year-oldYou are a curious 10 year old who has never seen software. Describe naive but unencumbered approaches. Ignore convention.general, wild
competitor trying to break itYou are a hostile competitor or attacker. Generate approaches that exploit, fail, or sabotage the obvious solution. Then invert into ideas.code, design
biologyTransplant a mechanism from biology (immune systems, neural plasticity, cell signaling, evolution, gut flora). Force-fit it onto this engineering problem.code, wild
logisticsSteal mechanisms from logistics: queues, batching, just-in-time, hub-and-spoke, returns, last-mile. Apply them literally.code, design
game designApproach this as a game designer. What are the loops, rewards, friction, save-states, speedrun tricks? Treat the user as a player.design, general
marketsTreat the problem as a market. Buyers, sellers, market-makers. What does an auction, a futures contract, a clearing house look like here?design, wild
inversionAsk the OPPOSITE question. If goal is X, brainstorm how to guarantee NOT X. Then negate each answer back.code, design, general
$0 budget, 1 hourNo money, no team, one hour. What is the crudest version that still does the load-bearing thing?code, general
infinite budget, 10 yearsInfinite compute, infinite engineers, a decade. What is the maximalist version?design, wild
remove the load-bearing assumptionName the thing everyone treats as fixed (framework, database, request-response model, network). Imagine it is gone. What is possible?code, design, wild
speedrunnerYou are a speedrunner. Find glitches, skips, out-of-bounds tricks, frame-perfect shortcuts. What is the abusive-but-legal path?code, wild
ant colonyNo central planner. Many dumb agents, local rules, pheromone trails. How does the problem solve itself emergently?code, wild
3am on-callYou are the on-call engineer woken at 3am when this breaks. What design would let you not get paged?code, design

Anti-patterns

  • Convergence disguised as divergence. Ten variations of one idea is not breadth. If every candidate shares the same underlying assumption, you decorated, not diverged.
  • Weird-for-weird's-sake with no convergence. A pile of 30 unsorted absurdities is as useless as one safe answer. Always converge with a real opinion.
  • Skipping isolation. If you simulate parallel branches by writing them sequentially in one orchestrator turn, you have not done ADHD. Use real spawn_peer fan-out — each spawned peer is a fresh context.
  • Refusing to commit. "Here are 20 ideas, you decide" is a cop-out. Generate wide, converge with a position.
  • Forgetting to kill. Leaving 8 idle peers after every run pollutes the mesh. Kill on cleanup; sessions remain resumable.

Calibration

Scale to stakes. Quick "name this function": 3 frames × 4 ideas. "How should we position this product": 5 frames × 8 ideas. Default 5 × 6.

Stop diverging when new candidates start repeating the shape of existing ones. The space is mapped; do not pad to hit a number.

© prassanna-ravishankar, 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 daemon-go/cli/assets/orchestrator/.agents/skills/adhd of prassanna-ravishankar/repowire.

Open the folder on GitHubat commit 7c8100a

Compare with similar skills

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.

Adhd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Adhd this skillprassanna-ravishankar/repowire264—~2.3kAutomated safety check: PassMIT
AdhdUditAkhourii/adhd4.4k—~2.8kAutomated safety check: PassMIT
I Have AdhdTanStack/ai3.2k5 repos~1.8kAutomated safety check: PassMIT
Attention Kindalexgreensh/attention-span1.4k—~2kAutomated safety check: PassAGPL-3.0
Remind Meshaheer-00/claude-adhd105—~1.1kAutomated safety check: PassNone
Daily Focus Boardgithub/awesome-copilot40k—~3kAutomated safety check: PassMIT

Similar skills

  • Adhd

    UditAkhourii/adhd

    Parallel divergent ideation for coding agents. An agent skill from UditAkhourii/adhd.

    4.4k GitHub stars~2.8k tokensUpdated 5 days ago
    Productivity & AutomationAuto-check passed
  • 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.

    3.2k GitHub starsUsed in 5 repos~1.8k tokens
    Productivity & AutomationAuto-check passed
  • Attention Kind

    alexgreensh/attention-span

    Answer in the ADHD-friendly Attention-kind style for the rest of this chat.

    1.4k GitHub stars~2k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed
  • 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.

    105 GitHub stars~1.1k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed
  • Daily Focus Board

    github/awesome-copilot

    Official

    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.

    40k GitHub stars~3k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • 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.

    119 GitHub stars~3.6k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed

More from prassanna-ravishankar/repowire

All 20 skills in this repo
  • Cross Agent Review

    prassanna-ravishankar/repowire

    Get a code/PR/plan review from a DIFFERENT AI agent over the repowire mesh (e.g.

    264 GitHub stars~480 tokensUpdated yesterday
    Auto-check passed
  • Delegate

    prassanna-ravishankar/repowire

    Hand a task to another AI agent peer over the repowire mesh — reuse an existing peer on the chosen backend, or spawn one if none exists.

    264 GitHub stars~503 tokensUpdated yesterday
    Auto-check passed
  • Durable Jobs

    prassanna-ravishankar/repowire

    A skill your agent uses when the user asks for durable or recurring background work, work that should survive peer death, retry/cancel/result tracking, spawned-on-demand workers, agent folders…

    264 GitHub stars~602 tokensUpdated yesterday
    Auto-check passed
  • Cleanup

    prassanna-ravishankar/repowire

    A skill your agent uses when cleaning up peers, sessions, tmux panes, processes, feature worktrees, branches, generated artifacts, or after a delegated lane or PR is complete.

    264 GitHub stars~352 tokensUpdated yesterday
    Auto-check passed
  • Create Agent

    prassanna-ravishankar/repowire

    A skill your agent uses when creating, updating, or explaining a standing Repowire agent folder, worker folder, durable-job executor context, or reusable agent-specific AGENTS.md guidance.

    264 GitHub stars~388 tokensUpdated yesterday
    Auto-check passed
  • Create Skill

    prassanna-ravishankar/repowire

    A skill your agent uses when adding, updating, splitting, or reviewing local orchestrator skills for reusable procedures, including controlled self-improvement of the orchestrator.

    264 GitHub stars~406 tokensUpdated yesterday
    Auto-check passed

Questions about Adhd

What does Adhd do?

Parallel divergent ideation via mesh fan-out. An agent skill from prassanna-ravishankar/repowire. Adhd is an agent skill from prassanna-ravishankar/repowire. Parallel divergent ideation via mesh fan-out.

When should I use Adhd?

Adhd fits situations like: tasks that involve Focus and ADHD support; tasks that involve Brainstorming.

How do I install Adhd in Claude Code?

Run `npx skills add prassanna-ravishankar/repowire --skill adhd -a claude-code`. Or copy the skill folder (daemon-go/cli/assets/orchestrator/.agents/skills/adhd in prassanna-ravishankar/repowire) into .claude/skills/adhd in your project. Claude Code loads it when a task matches its description.

How do I install Adhd in Codex?

Run `npx skills add prassanna-ravishankar/repowire --skill adhd -a codex`. Or copy the skill folder (daemon-go/cli/assets/orchestrator/.agents/skills/adhd in prassanna-ravishankar/repowire) into .agents/skills/adhd in your project. Codex loads it when a task matches its description.

Can I use 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 prassanna-ravishankar/repowire --skill 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/adhd, .gemini/skills/adhd, .github/skills/adhd and .opencode/skills/adhd in your project.

What does Adhd need to run?

SKILL.md names no scripts, command-line tools or credentials: Adhd is instructions for the agent only.

Does 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 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 Adhd use?

Adhd is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Adhd use?

About 2.3k tokens (SKILL.md is roughly 9k 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 Adhd?

Skills that share tags, products or a category with Adhd: Adhd (UditAkhourii/adhd, 4.4k stars), I Have Adhd (TanStack/ai, 3.2k stars), Attention Kind (alexgreensh/attention-span, 1.4k stars) and Remind Me (shaheer-00/claude-adhd, 105 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Adhd?

prassanna-ravishankar (a GitHub user) maintains it in prassanna-ravishankar/repowire, which has 264 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 9, 2026.

Source: prassanna-ravishankar/repowire on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.