productivity▌

Diagnose and fix failing ToolUniverse tools through systematic error identification, targeted fixes, and validation.

Make your Capacitor apps fast and responsive.

Write and validate EAS CI/CD workflow YAML files for Expo projects. \n \n Fetches the latest JSON schema from Expo's API to ensure job types, parameters, triggers, and runner configurations are current \n Supports dynamic expressions using ${{ }} syntax with contexts for GitHub events, workflow inputs, job outputs, and step results \n Includes built-in validation script that checks workflow structure against the schema and reports errors before deployment \n Provides reference documentation for

Read Tool: Read file contents

Optimize Product Hunt launches with research, gallery strategy, and timing guidance. \n \n Covers listing specifications (tagline limits, gallery dimensions, topic selection) and gallery image positioning strategy with five-image framework from hero shot to social proof \n Provides tagline formulas and examples to communicate product value in 60 characters without buzzwords \n Includes launch day playbook with specific timing (12:01 AM PT), maker comment structure, and engagement timeline from p

Analyze SQL queries to identify performance bottlenecks and implement optimization techniques. Includes query analysis, indexing strategies, and rewriting patterns for improved performance.

AI agent architecture for anticipating needs, surviving context loss, and continuous self-improvement. \n \n Implements Write-Ahead Logging (WAL) Protocol to capture corrections, decisions, and preferences before responding, ensuring critical details persist across sessions \n Three-tier memory system (SESSION-STATE.md, daily logs, curated MEMORY.md) with Working Buffer for context survival during compaction and Compaction Recovery for seamless resumption \n Proactive behavior patterns including

Bootstrap a modular AI agent with OpenRouter SDK, extensible hooks, and optional terminal UI. \n \n Standalone agent core runs independently of any UI, with event-based hooks for streaming responses, tool calls, reasoning, and errors \n Items-based streaming model emits complete, progressively updated items by ID rather than accumulating chunks, enabling efficient React state management and concurrent output handling \n Supports 300+ language models via OpenRouter with dynamic model discovery; u

前置条件： 先阅读 ../lark-shared/SKILL.md。 执行前必做： 执行任何 base 命令前，必须先阅读对应命令的 reference 文档，再调用命令。 命名约定： 仅使用 lark-cli base +... 形式的命令。

Multi-chain wallet operations for EVM and Solana with balance queries, transfers, signing, and transaction history. \n \n Supports 13 tools across EVM (Ethereum, Base, Arbitrum, Optimism, Polygon, Linea) and Solana, including balance checks, fund transfers, message signing, and transaction history \n Use wallet_get_all_balances() for complete portfolio visibility across all chains with USD values in a single call \n Transfers are policy-gated by Privy TEE — only whitelisted addresses and amounts