productivity▌

File-based task organization and progress tracking for complex multi-step projects. \n \n Creates and maintains three persistent markdown files (task_plan.md, findings.md, progress.md) to preserve context across sessions and tool calls \n Automatically detects active plans on startup and prompts context recovery; supports session restoration after /clear via catchup script \n Enforces structured workflow: plan phases upfront, log discoveries and errors immediately, update progress after each act

ln-302-task-replanner

Track keyword rankings over time with trend analysis, movement detection, and competitive benchmarking. \n \n Records and monitors keyword positions across traditional SERPs and AI-generated responses, with historical trend analysis and significant movement alerts \n Tracks SERP features (featured snippets, PAA, image/video packs) and AI Overview citation rates for comprehensive search visibility \n Compares rankings against competitors with share-of-voice metrics and head-to-head keyword analys

Version-control external repositories within a main project using Git submodules. \n \n Add, update, and remove submodules with commands for locking specific commits, branches, or tags \n Clone repositories with submodules using --recursive or manual initialization and update steps \n Batch operations across all submodules via git submodule foreach for pulling, checking status, and branch management \n Nested submodule support with recursive initialization and updates for complex dependency hier

This skill helps download transcripts (subtitles/captions) from YouTube videos using yt-dlp.

Build knowledge-grounded LLM applications with vector databases, semantic search, and retrieval strategies. \n \n Supports six vector database options (Pinecone, Weaviate, Milvus, Chroma, Qdrant, pgvector) and six embedding models optimized for different use cases and providers \n Covers five advanced retrieval patterns: hybrid search combining dense and sparse retrieval, multi-query generation, contextual compression, parent document retrieval, and HyDE (hypothetical document embeddings) \n Inc

Transform content into professional slide deck images with customizable styles and audience targeting. \n \n Generates slide outlines with style instructions, then creates individual slide images in 10+ preset styles (blueprint, corporate, sketch-notes, minimal, etc.) or custom dimension combinations \n Supports audience targeting (beginners, executives, experts), language selection, and configurable slide counts (5-30 slides based on content length) \n Includes two-round confirmation workflow w

Identifies high-quality leads by analyzing your business, searching for target companies, and ranking them with personalized outreach strategies. \n \n Analyzes your product/service and ideal customer profile to find matching companies based on industry, size, technology stack, and pain points \n Prioritizes leads with fit scores (1-10) and provides decision-maker titles, LinkedIn URLs, and company context for each prospect \n Generates personalized outreach strategies, value propositions, and c

HTTP endpoints for webhooks, external API integrations, and custom routes in Convex applications. \n \n Supports multiple HTTP methods and path matching with dynamic route parameters via pathPrefix for flexible endpoint design \n Handles diverse request types including JSON bodies, form data, raw bytes, and file uploads with built-in storage integration \n Includes webhook signature verification patterns for Stripe, GitHub, and Clerk with examples for secure event processing \n Provides authenti

Web search with LLM-optimized results, relevance scoring, and flexible filtering. \n \n Supports four search depth modes (ultra-fast, fast, basic, advanced) with configurable latency and relevance tradeoffs \n Includes domain filtering, time range constraints, date ranges, country boosting, and raw content extraction \n Returns results with title, URL, content snippet, and relevance score; optional image results and favicons \n Automatic OAuth authentication via Tavily MCP server or API key conf