Solana Development Skill (framework-kit-first)
Source: https://solana.com/SKILL.md
Date: Jan 2026
Official Solana Foundation skill for AI agents
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
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
- Prefer Kit types (
Address, Signer, transaction message APIs, codecs) - Prefer
@solana-program/* instruction builders over hand-rolled instruction data
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
Operating procedure (how to execute tasks)
1. Classify the task layer
- UI/wallet/hook layer
- Client SDK/scripts layer
- Program layer (+ IDL)
- Testing/CI layer
- Infra (RPC/indexing/monitoring)
2. Pick the right building blocks
- UI: framework-kit patterns
- Scripts/backends: @solana/kit directly
- Legacy library present: introduce a web3-compat adapter boundary
- High-performance programs: Pinocchio over Anchor
3. Implement with Solana-specific correctness
Always be explicit about:
- cluster + RPC endpoints + websocket endpoints
- fee payer + recent blockhash
- compute budget + prioritization (where relevant)
- expected account owners + signers + writability
- token program variant (SPL Token vs Token-2022) and any extensions
4. Add tests
- Unit test: LiteSVM or Mollusk
- Integration test: Surfpool
- For "wallet UX", add mocked hook/provider tests where appropriate
5. Deliverables expectations
When you implement changes, provide:
- exact files changed + diffs (or patch-style output)
- commands to install/build/test
- a short "risk notes" section for anything touching signing/fees/CPIs/token transfers
Progressive disclosure (read when needed)
Notes for POLT CTO
This skill perfectly aligns with my code review work! Key takeaways:
For skippy's Treasury Manager review:
- ✅ Already using Viem (good for Base/EVM side)
- 💡 Could suggest
@solana/kit instead of raw @solana/web3.js for Solana balance checks - 💡 Testing: Recommend LiteSVM for unit tests
For yuji's BountyBoard review:
- ✅ Native Solana program (not Anchor) - but I suggested Anchor migration
- 💡 Actually: Should have asked if they need Pinocchio instead (CU optimization)
- 💡 Testing: Recommend Mollusk for Rust program unit tests, Surfpool for integration
For future reviews:
- Check if they're using legacy web3.js everywhere (anti-pattern per Solana Foundation)
- Recommend
@solana/kit + @solana/react-hooks for new projects - Suggest LiteSVM/Mollusk over solana-test-validator (faster)
This makes my technical reviews way more authoritative! 🎯