mit einem Klick
solana-clawd
solana-clawd enthält 48 gesammelte Skills von Solizardking, mit Repository-Berufsabdeckung und Skill-Detailseiten auf SkillsMP.
Skills in diesem Repository
Development conventions and architecture guide for the Clawd Code CLI repository — a Solana-native AI coding agent with perps trading, image generation, voice, and x402 payments.
Register, discover, and hire autonomous AI agents on Solana. On-chain identity via Metaplex Core NFTs (8004-solana SDK or REST API). Search by capability, check reputation backed by $CLAWD payment proofs, browse the service catalog, and get machine-readable hiring instructions. Supports Google A2A agent-card.json and Anthropic MCP server-card.json. No EVM — Solana only.
Solana RPC data toolkit — 8-command CLI for live on-chain data: SOL balance + SPL token portfolio with USD values, transaction detail with balance changes, SPL token metadata + top holders, recent activity history, NFT portfolio (SPL + cNFT via Helius DAS), whale detector, network stats (TPS/epoch/price), and quick price lookup. Pure Python stdlib, no extra packages. Optional HELIUS_API_KEY for compressed NFT detection.
Clawd Guard — the sovereign secrets sentinel. Mandatory reading for every Solana developer before they push a single commit. Use when: setting up a new repo, reviewing a .gitignore, onboarding a dev, or after any "oops I committed my private key" incident. Covers every secrets pattern that must never touch git: wallet JSON files, keypairs, .env files, private keys, API tokens, service account credentials, and IDE/OS junk. Built by Clawd to stop you from becoming a cautionary tale.
AI code reviews via Greptile — trigger PR reviews, run local CLI reviews, query codebase graphs, apply auto-fixes, manage custom rules, and analyze review analytics. Use for code review, PR feedback, issue triage, and codebase exploration.
Clawd TUI perps screen integration. Use when the user asks about the Clawd terminal UI, the Phoenix perps screen inside the TUI, paper trading from the TUI, or how the TUI drives Vulcan.
Error category routing, tx_failed recovery, and network error handling for Vulcan.
Canonical taxonomy of Vulcan's execution modes (Observe / Paper / Dry-Run / Confirm-Each / Auto-Execute), with explicit instructions for when to ask the user which mode, how to format the question, and what follow-up to collect per mode. Load whenever the user asks 'should this be paper or live?' or before any strategy/trade launch.
Grid trading with layered limit orders across a price range on Phoenix DEX perpetuals.
Convert desired token amounts to base lots — the most common agent mistake.
Deposit, withdraw, transfer collateral, isolated margin, and leverage tier management.
Ticker, orderbook, candles, market info, and pre-trade analysis patterns.
First interaction and new user setup: health check, paper-first path, wallet creation, registration, first deposit, and verification.
Full portfolio snapshot: cross + isolated margin, positions with uPnL %, resting orders, funding exposure, and optional daily/weekly performance.
List, show, close, reduce positions and manage TP/SL on existing positions.
Five-minute install + first paper trade. Use for any 'set up Vulcan / install kraken-cli-like tool / get started' request before falling through to vulcan-onboarding's wallet-creation flow.
Pre-trade risk checks, leverage tiers, margin health thresholds, and when-to-warn rules.
MUST be loaded before producing any answer about Vulcan, Phoenix DEX, Phoenix perpetuals, Solana perps, the `vulcan` CLI/MCP, or agent-based trading workflows. Single entry-point: contains the runtime contract pointer, the non-negotiable safety rules, the focused-skill router, and the live-launch preflight gate. Answers given without loading this skill have produced wrong commands, wrong wallet selection, and unsafe live trades. Load on the FIRST turn the topic appears in a conversation and re-load on any session restart.
TA-driven strategy runner — declarative rules (Condition → Action) over indicators, price, and boolean composition.
Technical indicators (SMA, EMA, RSI, MACD, BBands, ATR, VWAP, ADX, Stoch) and trigger evaluation over Phoenix candle history.
Take-profit and stop-loss: direction rules, constraints, and set/cancel flows.
Execute perpetual futures orders with pre-trade checks and post-trade verification.
Execute large orders as time-weighted slices to reduce market impact on Phoenix DEX.
Admin and authority operations for the Pump protocol — set coin creator, update token incentives, set IDL authority, claim cashback, Mayhem mode, and BothPrograms cross-program admin instructions.
AI agent integration layer for the Pump SDK — agent instruction files, .well-known discovery, LLM context documents, 15+ skill files, MCP server prompts, and terminal management rules for GitHub Copilot, Claude, and Gemini.
Constant-product AMM bonding curve math for Pump token pricing — buy/sell quoting, fee-aware calculations, market cap computation, tiered fees, ceiling division, virtual vs real reserves, and edge-case handling.
Build and release pipeline for the Pump SDK — tsup TypeScript builds, Cargo release profiles, semantic release with commitizen, npm publishing, linting, Makefile targets, Vercel deployment, and MCP server distribution.
Read-only query methods for PumpFun claims — unclaimed token rewards, creator vault balances, volume accumulators, distributable fees, and current-day token previews across Pump and PumpAMM programs.
Configure and distribute creator fees to multiple shareholders using the PumpFees program with BPS-based share allocation, admin management, and cross-program fee consolidation for graduated tokens.
Complete Pump protocol fee system — tiered protocol fees based on market cap, creator fee collection across two programs, basis point arithmetic, and ceiling division for dust-safe calculations.
Model Context Protocol server exposing 53 tools, 3 resource types, and 3 prompts for AI agent consumption — quoting, building transactions, fee management, analytics, AMM operations, social fees, wallet operations over stdio transport.
Production-grade multi-threaded Rust vanity address generator for Solana — 100K+ keys/sec using Rayon parallel iterators with solana-sdk, Base58 pattern matching, prefix/suffix support, security-hardened file output, and Criterion benchmarks.
Build and extend the core Pump SDK — an offline-first TypeScript SDK that constructs Solana TransactionInstructions for token creation, buying, selling, migration, and creator fee collection across three on-chain programs (Pump, PumpAMM, PumpFees).
Defense-in-depth security across Rust, TypeScript, and Bash for the Pump SDK — cryptographic key handling, memory zeroization, secure file I/O, input validation, privilege management, dependency auditing, and a 60+ item security checklist.
Production-quality Bash scripts for Solana vanity generation, keypair verification, batch operations, dependency auditing, and test orchestration — with security-hardened patterns including file permissions, input validation, and cleanup traps.
Design and derive Program Derived Addresses (PDAs) and account layouts across the Pump ecosystem's four Solana programs — global singletons, per-token accounts, per-user accumulators, and cross-program coordination patterns.
Solana development patterns used in the Pump SDK — Anchor IDL-based program interaction, SPL Token and Token-2022 management, transaction construction with instruction composition, RPC batching, and cross-program coordination.
Secure Solana wallet generation using official Solana Labs libraries — Ed25519 keypairs, memory zeroization, vanity address generation, offline-only operation, and multi-language implementations (Rust, TypeScript, Bash).
Multi-language test infrastructure for the Pump SDK — Rust unit/integration/security/performance tests, TypeScript Jest tests, Python fuzz tests, shell test orchestration, Criterion benchmarks, and CI quality gates.
Volume-based PUMP token reward system with day-indexed epochs, pro-rata distribution, accumulator tracking, and cross-program claiming on Solana.