LLM & Agents

Expert on Shelby Protocol decentralized blob storage on Aptos blockchain. Coordinates 7 specialized sub-skills covering protocol architecture, SDK usage, smart contracts, CLI tools, RPC infrastructure, dApp building, and storage integration. Triggers on keywords Shelby Protocol, Shelby storage, decentralized storage, Aptos storage, blob storage, Shelby.

Expert on Shelby Protocol network infrastructure, RPC servers, storage providers, Cavalier implementation, tile architecture, performance optimization, connection management, and DoubleZero private network. Triggers on keywords Shelby RPC, storage provider, Cavalier, tile architecture, private network, DoubleZero, network performance, RPC endpoint, request hedging, connection pooling.

Expert prompt engineer specializing in designing, optimizing, and managing prompts for large language models. Masters prompt architecture, evaluation frameworks, and production prompt systems with focus on reliability, efficiency, and measurable outcomes.

Create event-driven hooks for Claude Code automation. Configure PreToolUse, PostToolUse, Stop, and other hook events with bash scripts, environment variables, matchers, and exit codes.

Interactive skill creator for Claude Code. Triggers when user mentions creating skills, building skills, skill templates, skill frontmatter, allowed-tools, or wants to scaffold a new skill.

Expert on testing Move smart contracts on Aptos, including unit tests, integration tests, Move Prover formal verification, debugging strategies, and test coverage. Triggers on keywords move test, unit test, integration test, move prover, formal verification, debug, coverage, assert, expect

Reusable QA harness for testing LLM agents and personas. Defines test suites with must-ace tasks, refusal edge cases, scoring rubrics, and regression protocols. Use when validating agent behavior, testing prompts after changes, or establishing quality baselines.

iOS app building and testing automation using Xcode simulator. Build, run, test iOS apps, capture screenshots, automate UI testing with XCTest, and integrate with Claude Code for mobile development workflows on macOS.

Use when storing project artifacts in basic memory storage.

AGGRESSIVELY use TOON v2.0 format for biggish regular data (≥5 items, ≥60% uniform). Auto-applies to tables, logs, events, transactions, analytics, API responses, database results. Supports 3 array types (inline, tabular, expanded), 3 delimiters (comma, tab, pipe), key folding for nested objects. Triggers on structured data, arrays, repeated patterns. Use TOON by default when tokens matter - RAG pipelines, tool calls, agents, benchmarks. Keywords "data", "array", "list", "table", "log", "transaction", "metric", "analytics", "API", "database", "query", "TOON".

Creates browser-executable JavaScript bookmarklets with strict formatting requirements. Use when users mention bookmarklets, browser utilities, dragging code to bookmarks bar, or need JavaScript that runs when clicked in the browser toolbar.

Interactive hook creator for Claude Code. Triggers when user mentions creating hooks, PreToolUse, PostToolUse, hook validation, hook configuration, settings.json hooks, or wants to automate tool execution workflows.

Guide for creating custom skills in SaaS Factory. Use when you need to create a new skill to extend Claude's capabilities with specialized knowledge, workflows, or tools.

Complete guide to Next.js 16 features, breaking changes, and migration from v15. Use when building new Next.js projects or upgrading existing ones to leverage Turbopack, Cache Components, and latest performance optimizations.

Build conversational AI agents using Vercel AI SDK + OpenRouter. Use when creating Next.js frontends with streaming UI, tool calling, and multi-provider support.

Build conversational AI agents using Pydantic AI + OpenRouter. Use when creating type-safe Python agents with tool calling, validation, and streaming.

Multi-agent parallel execution with autonomous workers. Use when plan.md has Track Assignments section or user triggers /conductor-orchestrate, "run parallel", "spawn workers". MUST load maestro-core skill first for routing.

Implements CLI user experience with output formatting, progress indicators, and interactive prompts. Uses chalk, ora, and inquirer for consistent terminal interactions. Triggers on: CLI output, progress bar, spinner, ora, chalk, inquirer prompts, error formatting, exit codes, reporter.

Turns product or tech specs into concrete Notion tasks that Claude code can implement. Breaks down spec pages into detailed implementation plans with clear tasks, acceptance criteria, and progress tracking to guide development from requirements to completion.

Integrate Replicate API for AI model deployment. Use when generating images with Flux, SDXL, or custom LoRA models via Replicate.