
Solana Dev
Run an end-to-end Solana playbook in your agent for wallets, Anchor programs, typed clients, local tests, and devnet deploy when you build or debug a dapp.
Overview
Solana Development Skill is an agent skill most often used in Build (also Ship testing/security and Operate deploy) that provides a framework-kit-first end-to-end playbook for Solana dapps, programs, tests, and toolchain
Install
npx skills add https://github.com/solana-foundation/solana-dev-skill --skill solana-devWhat is this skill?
- framework-kit-first dApp UI with @solana/client, @solana/react-hooks, and wallet-standard / ConnectorKit flows
- Anchor and Pinocchio on-chain programs with Codama client generation
- Local test matrix: LiteSVM, Mollusk, and Surfpool
- Security hardening and audit-style review checklists
- Toolchain troubleshooting: Anchor/Solana CLI versions, GLIBC, and dependency mismatches
- Metadata version 1.1.0
- Requires Node.js 18+
- Rust toolchain, Solana CLI, and Anchor CLI
Adoption & trust: 28.4k installs on skills.sh; 514 GitHub stars; 2/3 security scanners passed (skills.sh audits); trending (+200% hot-view momentum).
What problem does it solve?
You need to ship or debug a Solana dapp but wallet wiring, Anchor versions, RPC clients, and test harnesses each follow different docs and your agent drifts across incompatible stacks.
Who is it for?
Indie builders creating Anchor or Pinocchio programs, React/Next dapp frontends, and devnet/mainnet deploy pipelines who want MCP-backed doc search and opinionated package choices.
Skip if: Teams building on non-Solana chains, pure NFT marketplace no-code setups, or environments where Rust, Solana CLI, and Anchor cannot be installed.
When should I use this skill?
User asks to build a Solana dapp, write an Anchor program, create a token, debug Solana errors, set up wallet connection, test a Solana program, deploy to devnet, explain Solana concepts, or fix toolchain and dependency
What do I get? / Deliverables
The agent follows one Solana Foundation stack—UI hooks, program layout, generated clients, local tests, and security checks—so transactions, programs, and deploy steps align with current tooling.
- Wallet-connected dapp flows with transaction build and confirm UX
- Anchor or Pinocchio program with generated typed client
- Local test runs and security review notes aligned with skill checklists
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Integrations is the canonical shelf because the skill stitches UI wallet flows, on-chain programs, RPC clients, and toolchain CLIs into one shipping stack. Solana work spans React dapp surfaces and program RPC boundaries; integrations captures that cross-boundary orchestration better than frontend-only or backend-only shelves.
Where it fits
Spin a minimal wallet-connected prototype on devnet to validate a token or program interaction before full product scope.
Wire ConnectorKit wallet signing and @solana/kit RPC calls for send-and-confirm UX in a Next.js dapp.
Author an Anchor program, generate a Codama typed client, and call it from the app layer.
Run program tests in LiteSVM or Mollusk before promoting to Surfpool or cluster integration.
Deploy to devnet and reconcile CLI, Rust, and Anchor versions after GLIBC or dependency conflicts.
How it compares
Opinionated Solana skill package with MCP doc search, not a generic Web3 snippet list or an MCP server by itself.
Common Questions / FAQ
Who is solana-dev for?
Solo developers and small teams shipping Solana dapps who need wallet flows, on-chain programs, typed clients, testing, and deploy guidance in one agent workflow.
When should I use solana-dev?
In Build when wiring wallets and transactions or writing Anchor/Pinocchio programs; in Ship when running LiteSVM/Mollusk/Surfpool tests or security checklists; in Operate when deploying to devnet or fixing CLI and GLIBC toolchain errors.
Is solana-dev safe to install?
The skill describes signing, deployment, and audit workflows that can touch real funds and secrets; review the Security Audits panel on this Prism page and never let an agent use production keys without your explicit approval.
SKILL.md
READMESKILL.md - Solana Dev
# Solana Development Skill (framework-kit-first) ## What this Skill is for Use this Skill when the user asks for: - Solana dApp UI work (React / Next.js) - Wallet connection + signing flows - Transaction building / sending / confirmation UX - On-chain program development (Anchor or Pinocchio) - Client SDK generation (typed program clients) - Local testing (LiteSVM, Mollusk, Surfpool) - Security hardening and audit-style reviews - Confidential transfers (Token-2022 ZK extension) - **Toolchain setup, version mismatches, GLIBC errors, dependency conflicts** - **Upgrading Anchor/Solana CLI versions, migration between versions** ## Default stack decisions (opinionated) 1) **UI: framework-kit first** - Use `@solana/client` + `@solana/react-hooks`. - Prefer Wallet Standard discovery/connect via the framework-kit client. 2) **SDK: @solana/kit first** - Build clients with `createClient()` from `@solana/kit`, then `.use(...)` plugins: ```ts createClient() .use(signer(mySigner)) .use(solanaRpc({ rpcUrl })); // or solanaLocalRpc / solanaDevnetRpc / solanaMainnetRpc from @solana/kit-plugin-rpc ``` - Default to `signer()` / `signerFromFile()` / `generatedSigner()` from `@solana/kit-plugin-signer` — they set both `payer` and `identity` to the same keypair (the common case). For fresh local/devnet signers, install the RPC/LiteSVM plugin after `generatedSigner()`, then fund with `airdropSigner(...)`. Reach for the role-specific variants (`payer()` + `identity()`) only when fees and authority must come from different keypairs. - Use `@solana-program/*` program plugins (e.g., `tokenProgram()`) for fluent instruction APIs. - Prefer Kit types (`Address`, `Signer`, transaction message APIs, codecs). 3) **Legacy compatibility: web3.js only at boundaries** - If you must integrate a library that expects web3.js objects (`PublicKey`, `Transaction`, `Connection`), use `@solana/web3-compat` as the boundary adapter. - Do not let web3.js types leak across the entire app; contain them to adapter modules. 4) **Programs** - Default: Anchor (fast iteration, IDL generation, mature tooling). - Performance/footprint: Pinocchio when you need CU optimization, minimal binary size, zero dependencies, or fine-grained control over parsing/allocations. 5) **Testing** - Default: LiteSVM or Mollusk for unit tests (fast feedback, runs in-process). - Use Surfpool for integration tests against realistic cluster state (mainnet/devnet) locally. - Use solana-test-validator only when you need specific RPC behaviors not emulated by LiteSVM. ## Agent safety guardrails ### Transaction review (W009) - **Never sign or send transactions without explicit user approval.** Always display the transaction summary (recipient, amount, token, fee payer, cluster) and wait for confirmation before proceeding. - **Never ask for or store private keys, seed phrases, or keypair files.** Use wallet-standard signing flows where the wallet holds the keys. - **Default to devnet/localnet.** Never target mainnet unless the user explicitly requests it and confirms the cluster. - *