agentleFS
0xvikram0xvikram/backboard-skills/skills/track-arc/SKILL.md

track-arc

Skill1 starsChanged 25 days agoMITView on GitHub

Use when building for the Arc prize track at ETHGlobal Mumbai (Apps built in Arc Studio: DeFi, payments and consumer agents). Lists the tools on Backboard that fit the track, past winning projects for ideas, and where the official rules are.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read each tool's own docs for AI before writing code, and build the smallest demo that clearly uses Arc's product.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- backboard:generated -->

Arc track at ETHGlobal Mumbai

Arc's track, in its own words: Apps built in Arc Studio: DeFi, payments and consumer agents.

The rules, requirements and prizes are only on ETHGlobal's official page: https://ethglobal.com/events/mumbai/prizes. Read the Arc section there before planning, and check it again before you submit. This skill never restates them.

How to help the user

  1. Open the official prize page above and confirm what Arc asks for (which product to use, what to submit).
  2. Suggest one or two tools from the list below that fit what the user is building, and install their skills.
  3. Read each tool's own docs for AI before writing code, and build the smallest demo that clearly uses Arc's product.
  4. The project likely deploys on Arc: for chain IDs, RPCs and faucets, install npx skills add 0xvikram/backboard-skills --skill sponsor-chains.

Tools on Backboard that fit this track

  • Biconomy: Gasless, one-click transactions across chains (Backboard's suggestion) Skill: npx skills add 0xvikram/backboard-skills --skill biconomy
  • Pimlico: Gasless transactions with permissionless.js, a bundler and a paymaster (Backboard's suggestion) Skill: npx skills add 0xvikram/backboard-skills --skill pimlico
  • Safe: Smart accounts with shared control and spending limits, good for agents and treasuries (Backboard's suggestion) Skill: npx skills add 0xvikram/backboard-skills --skill safe
  • Superfluid: Streaming payments for subscriptions, salaries and rewards (Backboard's suggestion) Skill: npx skills add 0xvikram/backboard-skills --skill superfluid
  • Tenderly: Simulate and debug transactions, and test on virtual testnets (Backboard's suggestion) Skill: npx skills add 0xvikram/backboard-skills --skill tenderly
  • ZeroDev: Smart accounts with session keys and gas sponsorship (Backboard's suggestion) Skill: npx skills add 0xvikram/backboard-skills --skill zerodev

Ranked by hacker upvotes on https://backboard.0xvikram.me on 2026-10-19. "Backboard's suggestion" means the tool's team hasn't confirmed the fit.

What has won before (for ideas)

Past prizes from other ETHGlobal events. This year's prizes may differ: check the official page.

About this skill

Generated by Backboard on 2026-10-19. Backboard is an independent project, not affiliated with ETHGlobal or Arc.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.