Build and deploy Cardano dApps with guided skills for smart contracts (Aiken/Plutus), transactions, governance, wallet integration, debugging, security reviews, and local dev environment setup.
Security review for Cardano smart contracts written in Aiken, Plutus, or OpShin. Trigger: "review contract", "audit validator", "check security", "find vulnerabilities", "security review", "smart contract audit", "check for exploits".
Build Cardano transaction, send ADA, mint NFT, mint token, interact with smart contract, delegate stake, register DRep, vote on-chain using Mesh SDK, Evolution SDK, PyCardano, or cardano-client-lib.
Enable durable Cardano development context in the current project by writing a delimited directive block into CLAUDE.md. Tells Claude to consult the cardano-dev-skills skill set and bundled docs before relying on training data. Trigger phrases: "enable cardano context", "set up cardano for this project", "tell claude this is a cardano project", "mark this as a cardano project", "/cardano-context".
Guides integrating a Cardano wallet into a web dApp using CIP-30. Triggers: "connect wallet", "CIP-30", "wallet integration", "browser wallet", "sign transaction", "wallet connector", "dApp wallet", "Nami", "Eternl", "Lace".
Debug failing Cardano transaction, fix transaction error, diagnose ValueNotConservedUTxO, InsufficientCollateral, script failure, budget exceeded, datum mismatch, missing signer, min-UTxO error.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Community-curated Cardano developer knowledge โ bundled skills, documentation, and tooling for AI coding agents.
Works as a Claude Code plugin, Codex skill set, or standalone reference.
๐ Website: https://cardano-foundation.github.io/cardano-dev-skills/
Training data on Cardano drifts fast. Conway era changed governance, Aiken syntax evolves, SDK APIs ship breaking changes monthly. An AI agent answering "how do I write a vesting validator in Aiken?" from training data alone gets it wrong more often than right.
This plugin solves that by shipping:
End result: the agent answers from current, project-authoritative sources instead of memorized snapshots.
docs/sources/, auto-refreshed weekly via GitHub ActionsSessionStart reports doc freshness; a UserPromptSubmit auto-consultation hook is in development| Skill | What it does |
|---|---|
cardano-context | Install a per-project Cardano directive into CLAUDE.md so the agent reliably consults bundled skills and docs |
scaffold-project | Bootstrap a new Cardano project across Aiken + 4 off-chain stacks |
write-validator | Guide writing a validator from spec (default Aiken) |
review-contract | Security review of a validator |
optimize-validator | Lower CPU / memory / script-size costs |
build-transaction | Build & submit transactions across SDKs |
design-token | Design native tokens, NFTs, CIP-25/68/113 metadata |
debug-transaction | Diagnose failing transactions |
query-chain | Pick the right query strategy (Blockfrost / Ogmios / indexer) |
setup-devnet | Local devnet with Yaci DevKit or testnet setup |
connect-wallet | CIP-30 wallet integration for dApps |
governance-guide | CIP-1694 governance, DRep, voting, treasury |
explain-eutxo | Cardano's UTxO model for newcomers |
explain-cip | Walk through a specific CIP |
suggest-tooling | Recommend an SDK / framework given the use case |
In scope: generic developer building blocks โ SDKs, frameworks, validator libraries, design patterns, language tooling, infrastructure, protocol/standard specs, reference implementations of patterns.
Out of scope: product docs for specific deployed dApps (SundaeSwap, Minswap, Liqwid, Indigo, JPG Store, etc.). This repo teaches how to build a DEX, a lending protocol, an NFT marketplace โ not how a particular branded product works. If users want product-specific integration help, their agent can search externally.
Borderline rule: if the upstream repo's primary purpose is "use OUR product", it's out. If it's "here's how X pattern works, here's the reference code", it's in.
See docs/CONTRIBUTING.md for the full policy and the maintenance bar for source vetting.
In any Claude Code session:
/plugin marketplace add cardano-foundation/cardano-dev-skills
/plugin install cardano-dev-skills@cardano-dev-skills
Installed once, active in every Claude Code session in any directory. Verify with /plugin list.
git clone https://github.com/cardano-foundation/cardano-dev-skills.git
cd your-project
ln -s ../cardano-dev-skills/skills .agents/skills
Skills are pure Markdown โ read skills/*/SKILL.md directly or with grep.
Three complementary mechanisms, listed from most reliable to least:
/cardano-contextEven with the plugin installed globally, Claude sometimes answers Cardano questions from training data instead of consulting these skills and bundled docs. Run the cardano-context skill once per project to install a durable directive:
/cardano-context
What it does:
npx claudepluginhub cardano-foundation/cardano-dev-skills --plugin cardano-dev-skillsBlockchain development agents providing expertise in blockchain architecture, smart contracts, and Web3
Specialized agents for blockchain development, smart contracts, and Web3 applications
Ethereum development skills โ corrects LLM blind spots on gas costs, L2s, CROPS trust review (Censorship Resistance, Open Source and Free, Privacy, Security), DeFi protocols, security, and the current tool landscape.
Blockchain development with Solidity security, DeFi protocols, NFT standards, and Web3 testing
Full dev lifecycle for OP_NET Bitcoin L1 projects: idea โ challenge โ spec โ build โ review โ ship. Self-learning across sessions with pattern extraction, agent performance scoring, score-based finding routing, project-type profiles, cross-layer validation, and starter templates. Includes shell-enforced E2E testing gates, frontend runtime smoke checks, PUA problem-solving methodology, the OP_NET Bible (2000+ lines), cross-agent critique, adversarial auditing, adversarial E2E testing, ABI-lock checkpoints, findings ledger with regression tracking, acceptance test generation, chain probe, hard gate enforcement, incremental audits, dry-run mode, execution tracing, dynamic re-planning from learned patterns, dynamic knowledge slice loading, property-based fuzz testing, stale pattern pruning, mutation testing as loop exit gate, structured repair phases (R1/R2/R3), goal-oriented build evaluation, hierarchical repo map, autoresearch optimize mode, and TLA+ formal specification verification as a pre-codegen phase. Agents get smarter with every project.
Domain-specific technology experts - blockchain, fintech, gaming, IoT, payments