productivity▌

Coordinate parallel code reviews across multiple quality dimensions with deduplication and severity calibration. \n \n Allocates reviews across five dimensions (Security, Performance, Architecture, Testing, Accessibility) with recommended combinations for different code change types \n Deduplicates findings from multiple reviewers using merge rules based on file location and issue type, with conflict resolution for severity ratings \n Provides severity calibration criteria (Critical, High, Mediu

Downloads transcripts (subtitles/captions) from YouTube videos. Works with both manually created and auto-generated transcripts. No API key or browser required — uses YouTube's InnerTube API directly and automatically falls back to yt-dlp when YouTube blocks the direct API path.

Multi-chain DEX swap aggregation with quote, approval, and execution across 500+ liquidity sources. \n \n Supports 20+ blockchains including Solana, Ethereum, Base, BSC, Arbitrum, Polygon, and XLayer with automatic chain name resolution \n Generates swap transaction data with autoSlippage optimization, price impact assessment, and MEV protection for large trades \n Handles EVM token approvals with merged approve+swap flow to reduce transaction steps; native tokens skip approval automatically \n

Systematically strengthen interfaces against text overflow, internationalization, errors, and real-world edge cases. \n \n Covers text handling (truncation, wrapping, responsive sizing), RTL/CJK support, date/number formatting, and translation expansion planning \n Provides error recovery patterns for network failures, API status codes, validation errors, and permission states \n Includes edge case strategies: empty states, loading states, large datasets, concurrent operations, and boundary cond

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

AI-powered autonomous extraction of structured data from complex multi-page websites. \n \n Navigates sites intelligently to locate and extract data, returning results as JSON with optional schema validation \n Supports custom JSON schemas for predictable structured output, or freeform extraction when schema is not provided \n Offers two model tiers (spark-1-mini and spark-1-pro) with credit limits and optional waiting for inline results \n Best suited for multi-page extraction tasks; use simple

Design and optimize systems connecting marketing, sales, and customer success into a unified revenue engine. \n \n Covers lead lifecycle stages (Subscriber → Lead → MQL → SQL → Opportunity → Customer), stage definitions with entry/exit criteria, and ownership accountability across teams \n Includes lead scoring frameworks combining fit (ICP attributes) and engagement (behavioral signals) with negative scoring to filter unqualified leads \n Provides lead routing methods (round-robin, territory, a

Extract clean markdown from any URL, including JavaScript-rendered single-page applications. \n \n Handles both static pages and JS-rendered SPAs with configurable wait times for rendering \n Supports multiple concurrent URL scraping with output format options including markdown, HTML, links, and screenshots \n Includes content filtering options like main-content-only mode to strip navigation and footers, plus tag inclusion/exclusion \n Optional inline question answering via --query flag for tar

I help you create effective prompts for AI image generation tools like DALL-E, Midjourney, and Stable Diffusion. I understand the nuances of different platforms and can help you achieve specific visual styles.

skill-creator