Skills for agents,
on-chain.

Pull schema-valid JSON out of messy free text — emails, invoices, chat logs, receipts. Typed fields, ISO-normalized dates and numbers, a confidence score per field, and explicit nulls instead of invented values. The reliable bridge from prose to a typed object an agent can trust.

Decide the next semantic version from a current version plus a list of changes. Applies the SemVer rules — a breaking change bumps major, a feature bumps minor, a fix bumps patch, and the highest-severity change wins — and returns the bump level and the exact next version. Deterministic release automation for agents.

Turn malformed JSON into valid JSON. Fixes trailing commas, single quotes, unquoted keys, // and /* */ comments, Python literals (True/False/None), and output truncated mid-structure — then reports exactly what it changed. The dependable cleanup step for any agent parsing another model's output.

Turn any URL into clean, LLM-ready Markdown. Strips nav, ads, cookie banners, and boilerplate, keeps the main article, and returns title, byline, published date, and a short fact list. The reliable way for an agent to read the web without drowning in markup.

Audit a wallet's ERC-20 approvals on Base. Flags unlimited and stale allowances, identifies the risky and unverified spenders, and returns a prioritized revoke plan with ready-to-send calldata. Stops a drained-approval exploit before it costs an agent its balance.

Inspect a SQL statement before it runs. Flags unscoped DELETE/UPDATE, DROP and TRUNCATE, missing WHERE clauses, and full-table scans; classifies the risk; and returns a safer rewrite (a WHERE guard or a LIMIT). Stops an agent from nuking a table by accident.

Generates Playwright test scripts from a target URL and a concise test specification.

Comprehensive API health checker: probe endpoints, validate responses against schemas, measure latency, check SSL certs, detect rate limits, and generate a structured health report (JSON or markdown). Works with REST, GraphQL, and WebSocket APIs. Outputs actionable diagnostics.

Generate comprehensive API documentation from source code, OpenAPI specs, or example requests. Produces structured Markdown docs with endpoint descriptions, request/response examples, authentication guides, error catalogs, and SDK usage snippets.

Turn a one-line brief into a token launch on Base — pick name/ticker/supply, set sane defaults for an LP and a fair launch, and produce the exact steps an agent runs to deploy and seed liquidity. Built for Bankr-style agent launches.

Use this skill for any cryptocurrency or blockchain-related task. Triggers include crypto price lookups, portfolio tracking, DeFi analysis, token research, blockchain explanations, wallet security, NFT evaluation, trading strategies, market analysis, on-chain data, tokenomics breakdowns, smart contract overviews, crypto tax basics, exchange comparisons, and Web3 concepts. Use whenever the user mentions Bitcoin, Ethereum, altcoins, DeFi, NFTs, staking, yield farming, wallets, gas fees, Layer 2, DAOs, airdrops, or any blockchain/Web3 topic.

Pull schema-valid JSON out of messy free text — emails, invoices, chat logs, receipts. Typed fields, ISO-normalized dates and numbers, a confidence score per field, and explicit nulls instead of invented values. The reliable bridge from prose to a typed object an agent can trust.

Deep analysis of any EVM wallet address: token holdings with USD values, NFT inventory, DeFi positions (lending, staking, LP), transaction history patterns, gas spending analysis, counterparty mapping, and risk flags (interaction with known scam contracts, approval exposure). Works across Base, Ethereum, Arbitrum, Optimism. Essential for portfolio review, counterparty due diligence, or pre-trade wallet assessment.

Analyze DeFi yield opportunities across Base, Ethereum, Arbitrum, and Optimism. Given a portfolio amount and risk tolerance, identifies optimal yield strategies across lending (Aave, Compound), DEX LPs (Uniswap, Aerodrome), liquid staking (Lido, Rocket Pool), and vaults (Yearn, Beefy). Calculates real APY after fees, IL risk, protocol risk scores, and gas costs. Returns ranked strategies with step-by-step execution instructions.

Comprehensive smart contract security analysis for EVM chains (Base, Ethereum, Arbitrum, Optimism). Given a contract address or source code, identifies rug pull patterns, privilege escalation risks, token honeypot mechanics, liquidity lock status, holder concentration, and common vulnerability classes (reentrancy, flash loan, oracle manipulation, access control). Returns a severity-rated security report with risk score, specific findings, and actionable recommendations. Essential pre-investment due diligence for any agent interacting with DeFi protocols or tokens.

Comprehensive cloud infrastructure configuration reviewer that audits Terraform, CloudFormation, Pulumi, Kubernetes manifests, Docker Compose, and Helm charts for security misconfigurations, cost optimization opportunities, reliability risks, and compliance violations. Checks against CIS benchmarks and AWS/GCP/Azure best practices. Identifies over-provisioned resources, missing encryption, open security groups, absent backup configurations, and single points of failure. Produces a structured severity-rated report with affected resources, remediation code snippets, and estimated monthly cost impact. Supports multi-cloud and hybrid deployments.

Generate comprehensive, ready-to-run test suites from any source code — API routes, React/Vue components, backend services, CLI tools, database models. Supports Jest, Vitest, Pytest, Go testing, Playwright, Cypress. Produces unit, integration, E2E, and API tests with edge cases, error paths, security checks, mocking, fixtures, and test data factories. The complete test-writing replacement for any codebase.

Validate .env files and environment variable configurations — detect missing required vars, type mismatches, malformed values, duplicate keys, and insecure patterns. Returns a structured report with errors, warnings, and auto-fix suggestions. The guard rail before any deploy, docker-compose up, or CI pipeline runs.