Juicebox V6

OrganizationPopular

BankrBot

juicebox-v6

Build, inspect, configure, and safely transact with Juicebox V6 projects, terminals, rulesets, hooks, tiered NFTs, Revnets, Croptop, Bendystraw, and omnichain deployments. Use for Juicebox protocol questions, contract addresses or ABIs, project creation, payments, cash-outs, tokenomics, hooks, NFT tiers, cross-chain bridges, loan queries, transaction decoding, and Juicebox app/UI development on Ethereum, Optimism, Base, Arbitrum, or their Sepolia testnets.

Overview

Publisher	BankrBot
Repository	`skills`
Skill name	`juicebox-v6`
Stars	1.2K
Forks	643
Bundled files	97
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
97 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by BankrBot on GitHub. Read the source before you install it.

Installation

Install the Juicebox V6 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/BankrBot/skills/tree/main/juicebox-v6
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/BankrBot/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/juicebox-v6 .claude/skills/juicebox-v6

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Juicebox V6 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Juicebox V6 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Juicebox V6 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Juicebox V6

Use this skill as the single entry point for Juicebox V6. Load the smallest applicable module from references/modules/<module>.md; modules contain the upstream protocol-specific procedures and examples. Do not load every module.

Operating rules

Resolve chain, project ID, token, and intended outcome before proposing a write.
Use references/shared/chain-config.json only for read-only discovery. For any write, read deployment verification and use references/shared/deployment-manifest.json as the sole target authority. Missing, unknown, mismatched, or non-write-enabled entries stop the action.
Use references/shared/abis/<Contract>.json for complete ABI tuple definitions when encoding or decoding calls.
For every write, also read references/modules/jb-tx-safety.md. Apply its review → re-verify → simulate → gas → send → prove pipeline without skipping steps. Abort on stale/missing quotes, failed preview/simulation, code or graph mismatch, or unavailable price-feed/hook/terminal/accounting context.
Derive every minReturnedTokens, minTokensReclaimed, and minTokensPaidOut from a fresh successful preview and the user's approved slippage tolerance. A protocol-verified zero may remain zero only where jb-tx-safety explicitly permits it; unavailable is never treated as zero.
Treat source data as versioned guidance, not live proof. Immediately before confirmation, verify the exact chain, nonempty matching runtime code, allowed selector, proxy/clone implementation pin, controller/terminal/project ownership and wiring, balances, approvals, and price-sensitive inputs.
Default to explanation, read-only inspection, or an unsigned transaction plan. Before signing or broadcasting, decode and present the exact chain, target, selector/function/arguments, asset and amount, recipient/project, native value, approvals, fees, expected effects, and partial-completion risk; require explicit user confirmation.
After mining, require receipt.status === 'success' plus operation-specific event and post-state evidence. A missing receipt is pending; missing evidence is uncertain; either state disables retry. Never report success from a bare receipt or third-party status string.
Never request, expose, or place private keys in code. Use Bankr's wallet/signing flow or the user's approved signer.

Module routing

User intent	Read this module or modules
Find contract addresses, roles, supported chains, or ABIs	`jb-contracts`, then `jb-v6-api` as needed; use `deployment-verification.md` for writes
Explain a Juicebox concept or protocol mechanics	`jb-simplify`, `jb-v6-impl`, or `jb-patterns`
Launch or configure a project or Revnet	`jb-project`, `jb-revnet-deploy`, `jb-ruleset`, `jb-fund-access-limits`, `jb-multi-currency`
Pay a project, cash out, manage terminal routing, fees, or Permit2	`jb-query`, `jb-terminal-selection`, `jb-protocol-fees`, `jb-fee-flows`, `jb-cash-out-curve`, `jb-permit2-metadata`
Build or review custom hooks	`jb-data-hook-resolution`, `jb-buyback-hook`, `jb-lp-split-hook`, `jb-pay-hook`, `jb-cash-out-hook`, `jb-split-hook`, `jb-terminal-wrapper`
Configure or mint tiered NFTs	`jb-721-per-chain-config`, `jb-721-tier-content`
Configure an omnichain project or bridge	`revnet-omnichain-default`, `jb-suckers`, `jb-omnichain-erc20-config`, `jb-omnichain-payout-limits`, `jb-omnichain-per-chain-projectids`, `jb-omnichain-tier-quantity-per-chain`
Design a Revnet or inspect/operate REVLoans	`revnet-economics`, `revnet-modeler`, `jb-revloans`, `jb-loan-queries`
Use Croptop or Bendystraw	`jb-croptop` or `jb-bendystraw`
Inspect state, decode calldata, use the SDK, or obtain docs	`jb-query`, `jb-decode`, `jb-sdk`, or `jb-docs`
Build a Juicebox frontend	Choose the relevant `*-ui` module: `jb-deploy-ui`, `jb-interact-ui`, `jb-explorer-ui`, `jb-event-explorer-ui`, `jb-ruleset-timeline-ui`, `jb-nft-gallery-ui`, `jb-hook-deploy-ui`, or `jb-omnichain-ui`
Resolve currency or reserved-rate questions	`jb-currency-types` or `jb-reserved-rate-offchain-revenue`
Relay transactions or execute through a Safe	`jb-relayr` and `jb-safe-and-relayr-execution`
Construct, audit, or execute any write	`jb-tx-safety` plus the domain module and `deployment-verification.md`

For a named module, read references/modules/<module>.md. Combine modules only when the requested workflow actually crosses domains.

Frontend dependency boundary

Before generating or modifying a wallet-connected UI, read frontend security. Obtain approval before installing exact local dependencies (viem@2.55.19, or ethers@6.15.0 only for the explorer), preserve the lockfile integrity pins, import only from local packages, move scripts out of inline HTML, and apply the restrictive CSP. Never dynamically import wallet-adjacent JavaScript from a CDN.

UI module adaptation

The UI modules include upstream fragments, not deployable pages. Copy only required assets into the generated app, update module paths, and enforce the frontend and transaction boundaries above. Copy deployment-manifest.json with the ABI and chain references; never assume a Bankr skill directory is served by the generated app.

Attribution

This bundle adapts the Juicebox V6 skill library from mejango/juicebox-skills at commit 783b11ab163fdc60fd68db8b690ee1ebc26dc2fa, licensed MIT. Preserve the included LICENSE when redistributing the bundle or derived content.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 37 more files.

Frequently asked questions

What does the Juicebox V6 AI skill do?

Why use Juicebox V6 on TypingMind?

Because you install it once and use it with any model. Juicebox V6 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Juicebox V6 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/BankrBot/skills/tree/main/juicebox-v6. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Juicebox V6?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Juicebox V6?

As many as you like. As long as a model supports skills, you can use Juicebox V6 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Juicebox V6 AI skill free?

It is published on GitHub by BankrBot. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Agent Agentic Payments

ruvnet

CommunityPopular

Agent skill for agentic-payments - invoke with $agent-agentic-payments

Agent Payments

Agent skill for payments - invoke with $agent-payments

Canopy Part Title

Leaves sweep through the frame and part to reveal the headline. HyperFrames block, 1920×1080, 12s, 11 variables.

Module Regression

Govern cross-module regression in large repositories with a REGRESSION.md ledger that records each module's downstream consumers and executable acceptance command. After a change, run the changed…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Juicebox V6

Operating rules

Module routing

Frontend dependency boundary

UI module adaptation

Attribution

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now