// 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").
| 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)","author":"repowire"} |
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.
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:
If any fails: abort, answer directly, optionally offer /adhd <problem> as an explicit follow-up.
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 in the user's workspace 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.
Two passes:
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").
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.
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.
Render in this order. The structure is the point — do not collapse to prose.
[N7 V8 F9].Pick 5 per run. Vary across sessions so the same problem produces different candidates when re-run.
| Frame | Vantage prompt | Tags |
|---|---|---|
| hardware engineer | You 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 |
| regulator | You audit systems for compliance and failure modes. What must be provable, traceable, or refusable here? | design, general |
| 10-year-old | You are a curious 10 year old who has never seen software. Describe naive but unencumbered approaches. Ignore convention. | general, wild |
| competitor trying to break it | You are a hostile competitor or attacker. Generate approaches that exploit, fail, or sabotage the obvious solution. Then invert into ideas. | code, design |
| biology | Transplant a mechanism from biology (immune systems, neural plasticity, cell signaling, evolution, gut flora). Force-fit it onto this engineering problem. | code, wild |
| logistics | Steal mechanisms from logistics: queues, batching, just-in-time, hub-and-spoke, returns, last-mile. Apply them literally. | code, design |
| game design | Approach this as a game designer. What are the loops, rewards, friction, save-states, speedrun tricks? Treat the user as a player. | design, general |
| markets | Treat the problem as a market. Buyers, sellers, market-makers. What does an auction, a futures contract, a clearing house look like here? | design, wild |
| inversion | Ask the OPPOSITE question. If goal is X, brainstorm how to guarantee NOT X. Then negate each answer back. | code, design, general |
| $0 budget, 1 hour | No money, no team, one hour. What is the crudest version that still does the load-bearing thing? | code, general |
| infinite budget, 10 years | Infinite compute, infinite engineers, a decade. What is the maximalist version? | design, wild |
| remove the load-bearing assumption | Name the thing everyone treats as fixed (framework, database, request-response model, network). Imagine it is gone. What is possible? | code, design, wild |
| speedrunner | You are a speedrunner. Find glitches, skips, out-of-bounds tricks, frame-perfect shortcuts. What is the abusive-but-legal path? | code, wild |
| ant colony | No central planner. Many dumb agents, local rules, pheromone trails. How does the problem solve itself emergently? | code, wild |
| 3am on-call | You are the on-call engineer woken at 3am when this breaks. What design would let you not get paged? | code, design |
spawn_peer fan-out — each spawned peer is a fresh context.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.
Use when orchestrating complex or multi-lane work, decomposing tasks across peers, choosing status/board surfaces, running mesh roundups, or keeping high-level progress visible.
Use when creating, updating, or explaining a standing Repowire agent folder, worker folder, durable-job executor context, or reusable agent-specific AGENTS.md guidance.
Use when adding, updating, splitting, or reviewing local orchestrator skills for reusable procedures, including controlled self-improvement of the orchestrator.
Use when transferring orchestrator responsibility, summarizing current state for a new peer, recovering after a closed session, or preparing takeover notes.
Use when coordinating PR review, CI triage, second-peer critique, requested-changes loops, merge readiness, or deciding whether implementation needs independent verification.
Use when splitting work across peers, creating or selecting feature worktrees, preventing overlapping edits, or deciding whether to reroute implementation out of the main worktree.