A comprehensive AI skill for modern Stellar development with current best practices. https://skills.stellar.org/
Inspired by solana-foundation/solana-dev-skill and cloudflare/skills.
Note
This skill was AI-generated using Claude Code and is currently under manual review. We welcome contributions! Please submit PRs, open issues, or provide feedback to help improve this resource for the Stellar ecosystem.
This skill provides AI assistants with deep knowledge of the current Stellar development ecosystem:
- Smart Contracts: Stellar smart contracts (Rust soroban-sdk, WebAssembly)
- Client SDKs: stellar-sdk (JavaScript), Python, Go, Rust
- APIs: Stellar RPC (preferred), Horizon (legacy)
- Assets: Stellar Assets, Stellar Asset Contract (SAC)
- Wallets: Freighter, Stellar Wallets Kit, Smart Accounts (passkeys)
- Testing: Local Quickstart, Testnet, Unit tests
- Security: Smart contract security patterns, audit checklists
- Ecosystem: DeFi protocols, developer tools, community projects
These skills give your agent durable Stellar context, baked in. Raven is a complementary remote Model Context Protocol (MCP) server for on-demand lookups: connect an agent and it searches Stellar docs and live ecosystem data, cross-referenced into single answers. Its catalog also includes these skills, so Raven is a live delivery gateway for them. Use both: skills for durable best practices, Raven for current lookups.
Raven is open source at kalepail/stellar-raven. Connect it in Claude Code:
claude mcp add --transport http stellar-raven "https://raven.stellar.buzz/mcp"You can also try Raven in the browser at the playground, a hosted chat UI for asking Raven questions (sign-in required).
These skills work with any agent that supports the Agent Skills standard.
# Add this repo as a marketplace
/plugin marketplace add stellar/stellar-dev-skill
# Then install the skill
/plugin install stellar-dev@stellar-devgit clone https://github.com/stellar/stellar-dev-skill ~/.codex/skills/stellar-dev-skillnpx skills add https://github.com/stellar/stellar-dev-skillgit clone https://github.com/stellar/stellar-dev-skillCopy the skills/ directory contents to your assistant's skills location.
| Agent | Skill Directory | Docs |
|---|---|---|
| Claude Code | ~/.claude/skills/ |
docs |
| OpenCode | ~/.config/opencode/skill/ |
docs |
| OpenAI Codex | ~/.codex/skills/ |
docs |
| Pi | ~/.pi/agent/skills/ |
docs |
skills/
├── smart-contracts/ # Stellar smart contracts — SKILL.md router + development/testing/security files
├── dapp/ # Frontend — SKILL.md router + react / data-fetching / smart-accounts files
├── assets/SKILL.md # Stellar Assets, trustlines, SAC bridge
├── data/ # Stellar RPC (preferred) — SKILL.md router + horizon (legacy) file
├── agentic-payments/ # AI/machine payments — SKILL.md router + x402 / mpp files
├── zk-proofs/SKILL.md # ZK verification (BLS12-381/BN254 Groth16, UltraHonk), Circom/Noir/RISC Zero
├── standards/ # SEPs & CAPs — SKILL.md router + ecosystem / resources files
└── cross-chain/ # Cross-chain — SKILL.md router + cctp file
Each sub-skill is a self-contained Agent Skill with its own frontmatter. Larger skills follow Anthropic's progressive-disclosure guidance: a sub-500-line SKILL.md router with a task-to-file table, plus companion files (one level deep) that load only when the task needs them. Cross-references link related skills (e.g., the agentic-payments skill points to smart-contracts for the SACs the protocols call, and to assets for USDC). The AI reads only the files relevant to the task at hand.
"Help me write a Stellar smart contract for a token"
"Set up a Next.js app with Freighter wallet connection"
"How do I deploy a contract to Stellar Testnet?"
"Create unit tests for my smart contract"
"Review this contract for security issues"
Contributions are welcome! Please ensure any updates reflect current Stellar ecosystem best practices.
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
- Keep information current (check stellar.org/developers for updates)
- Focus on practical, actionable guidance
- Include code examples where helpful
- Cite official documentation when possible
- Keep each
SKILL.mdbody under ~500 lines — move deep dives into companion files routed by the task table - When a change touches what a skill teaches, update or add the matching scenario under
evals/in the same PR
evals/ holds ~3 task scenarios for each of seven skills (plus cross-skill routing checks and a negative control), each encoding a mistake agents actually make without the skill. Three grading tiers: machine-checkable compile checks, LLM-judged behavior assertions, and skill-trigger checks. Two gaps are open: cross-chain has no scenarios yet, and no baseline transcripts are committed, so the set is still unvalidated. See evals/README.md for the format, how to run them, and what the missing baselines mean.
Apache-2.0 License - see LICENSE for details.
Note: This repository is not in scope for the Stellar Development Foundation bug bounty program. Vulnerabilities found in this repo are not eligible for rewards.