/pick-my-sui-track

name: pick-my-sui-track
description: Pick a Sui Overflow 2026 track (Agentic Web, DeFi, Walrus, DeepBook). Use when the user wants a track recommendation for Sui Overflow.

Preamble (run first)

# Suiperpower telemetry. Routes through the CLI so projects.json + Convex stay in sync.
# Silent on failure so the skill never blocks. Opt out: SUIPERPOWER_TELEMETRY=off.
#
# AGENT NOTE: when this skill finishes, run the matching completion command:
#   suiperpower track pick-my-sui-track ship completed
# Or use "failed" / "aborted" if it ended that way.
command -v suiperpower >/dev/null 2>&1 && suiperpower track pick-my-sui-track ship started >/dev/null 2>&1 &
true

If `TEL_PROMPTED` is `no`, before doing real work, ask the user:

> Help suiperpower get better. We track which skills get used and how long they take. No code, no file paths, no PII. Change anytime in `~/.suiperpower/config.json`. > > A) Sure, anonymous > B) No thanks

Write the answer to `~/.suiperpower/config.json` `telemetryTier` field and create `~/.suiperpower/.telemetry-prompted`. Then continue.

What this skill does

Walks the project's actual code and demo flow, scores depth of fit against all eleven official Sui Overflow 2026 tracks on a 0 to 3 scale, and recommends a single primary track only if a track scores 3 (load-bearing).

The eleven official tracks:

**Core tracks ($62.5K each)**:

• **Agentic Web**: autonomous AI agents that act, transact, and coordinate using Sui's object model.
• **DeFi & Payments**: financial primitives or payment rails on Sui.
• **Infra & DevX**: developer tools, SDKs, indexers, and infrastructure that make Sui easier to build on.

**Specialized tracks**:

• **Walrus** ($70K): applications built on Walrus decentralized storage.
• **DeepBook** ($70K): trading or liquidity applications powered by DeepBook's on-chain orderbook.
• **ONE Championship** ($70K): consumer apps in sports, entertainment, fan engagement, gaming, NFTs.
• **EVE Frontier** ($50K): Smart Assembly mods, tools, or experiences for EVE Frontier.
• **Degen** (TBD): meme launches, gamified trading, bonding curves, viral degen culture.
• **Payments & Wallets** (TBD): wallet UX, payment rails, sponsored transactions.
• **Entertainment & Culture** (TBD): NFTs, gaming, social, consumer culture apps.
• **Explorations** (TBD): RWA, DePIN, multi-chain, novel experiments.

If overflow.sui.io ever changes its track list mid-cycle, this skill should be re-verified against the current page before recommending.

Official policy

Per overflow.sui.io: "You must select the one track that best represents your project."

Per the Overflow 2026 organizers (Telegram, paraphrased): track choice is the team's prerogative. Teams pick where the project aligns most strongly.

This skill stays opinionated within that policy. It will not bless a track recommendation where the fit is aspirational, because judges score against what they see in the demo, not what is claimed in the description.

When to use it

• After the project compiles and at least one demo flow runs end to end.
• Before drafting the submission, so the right track is locked in early.
• When the user is torn between two plausible tracks and wants a tie-breaker.

When NOT to use it

• Pre-build, when fit cannot be measured against real code.
• For special award eligibility (OpenZeppelin, OtterSec, Scallop, Hippo). Those are prize partners or special awards, not tracks themselves; see "Special awards and prize sponsors" below.
• For grant track decisions. Route to `apply-grant`.

If you activated this and the user actually wants something else, consult `skills/SKILL_ROUTER.md` and hand off.

Inputs

• `.suiperpower/idea-context.md`: project intent and target user.
• `.suiperpower/build-context.md`: stack, package id, modules used.
• Move package source and any frontend code (for static evidence of integrations).
• Optional: a recording of the load-bearing demo flow.

Outputs

Append to `.suiperpower/track-pick.md`:

## Track pick, <timestamp>

### Track fit scores (core)
- Agentic Web: <0 | 1 | 2 | 3>, evidence: <one sentence>
- DeFi & Payments: <0 | 1 | 2 | 3>, evidence: <one sentence>
- Infra & DevX: <0 | 1 | 2 | 3>, evidence: <one sentence>

### Track fit scores (specialized)
- Walrus: <0 | 1 | 2 | 3>, evidence: <one sentence>
- DeepBook: <0 | 1 | 2 | 3>, evidence: <one sentence>
- ONE Championship: <0 | 1 | 2 | 3>, evidence: <one sentence>
- EVE Frontier: <0 | 1 | 2 | 3>, evidence: <one sentence>
- Degen: <0 | 1 | 2 | 3>, evidence: <one sentence>
- Payments & Wallets: <0 | 1 | 2 | 3>, evidence: <one sentence>
- Entertainment & Culture: <0 | 1 | 2 | 3>, evidence: <one sentence>
- Explorations: <0 | 1 | 2 | 3>, evidence: <one sentence>

### Primary track
- recommended: <track name | none of the eleven>
- reasoning: <one paragraph>
- caveats: <one paragraph if any>

### What is needed to upgrade a 2 to a 3
- <if any track sits at 2, what would tip it to load-bearing>

### Special awards and prize sponsor eligibility (informational, not tracks)
- OpenZeppelin (1st place DeFi & Payments sponsor): <yes | no>, evidence: ...
- OtterSec (3rd place DeFi & Payments sponsor): <yes | no>, evidence: ...
- Scallop University Award ($2.5K x 10 teams): <yes | no>, evidence: ...
- Hippo Community Award ($25K): <eligible by default, community-voted>

### Verdict
- ready to submit to one of the eleven tracks: <yes | no>
- if no: which track to deepen, with the concrete change needed to get there

Workflow

1. **Read project state**

• Open `idea-context.md` and `build-context.md`.
• Walk the Move package and frontend for integration evidence.
• Walk the user-visible demo flow end to end.

2. **Score each of the eleven tracks on 0 to 3**

• 0: no real fit.
• 1: thematic adjacency only (a mention in docs, an aspirational claim in the description).
• 2: real code or theme present, but the project still works as something else if you remove