Create high-converting landing pages with persuasive copy, clear CTAs, social proof, and optimized structure. Use when building sales pages, product pages, lead capture pages, or conversion-focused pages.

Foundational Carbon patterns covering memory safety, modern syntax, C++ interop, and Carbon idioms. Use when writing Carbon code or migrating from C++. This is the entry point for Carbon development.

Builds LLM-powered applications with LangChain.js for chat, agents, and RAG. Use when creating AI applications with chains, memory, tools, and retrieval-augmented generation in JavaScript.

Comprehensive guide for building production-grade LLM applications using LangChain's chains, agents, memory systems, RAG patterns, and advanced orchestration

Building LLM applications with LangChain - chains, agents, RAG, memory, and production patterns for AI-powered apps.

LangChain.js - TypeScript framework for building LLM-powered applications with agents, chains, RAG, tools, memory, and integrations for OpenAI, Anthropic, Google, and hundreds of other providers

Multi-agent systems with LangGraph - supervisor/swarm patterns, state coordination, multi-provider routing. Use when building multi-agent workflows, coordinating agents, or need cost-optimized orchestration. Uses Claude, DeepSeek, Gemini (no OpenAI).

You are an expert in last-mile delivery operations and urban logistics. Your goal is to help optimize the final leg of delivery from distribution center to customer, balancing cost efficiency with cus

Access Last.fm listening history, music stats, and discovery. Query recent tracks, top artists/albums/tracks, loved tracks, similar artists, and global charts.

Use when optimizing end-to-end latency, reducing response times, or improving performance for latency-sensitive applications. Covers latency budgets, geographic routing, protocol optimization, and latency measurement techniques.

Latent-Latency Skill

Multi-agent distributed context preservation protocol using cryptographic sharding, gossip propagation, and Byzantine fault tolerance to maintain coherent shared memory across dynamic agent networks.

Manage people performance with Lattice's performance management platform.

Activate when the user needs help writing, optimizing, or understanding LimaCharlie Query Language (LCQL) queries for searching telemetry.

Implement progressive lead scoring based on user engagement and conversion events.

lean4-ffi-constructor-layout

This skill should be used when working on Lean 4 formalization projects to maintain persistent memory of successful proof patterns, failed approaches, project conventions, and user preferences across sessions using MCP memory server integration

Proactively learn about the user through onboarding and ongoing observation. Use at session start and when you notice potential preferences.

authentic-assessment design for effective learning measurement.

Recognize and capture reusable patterns, workflows, and domain knowledge from work sessions into new skills. Use when completing tasks that involve novel approaches repeated 2+ times, synthesizing complex domain knowledge across conversations, discovering effective reasoning patterns, or developing workflow optimizations. Optimizes for high context window ROI by identifying patterns that will save 500+ tokens per reuse across 10+ future uses.

Create and maintain multilingual glossaries and terminology databases for consistent educational translations.

impact-measurement for measuring learning effectiveness and business impact.

Design adaptive learning pathways that personalize content based on learner performance, preferences, and goals.

Recommend optimal learning resources, activities, and pathways based on learner data and performance patterns.

Integration patterns and best practices for adding persistent memory to LLM agents using the Letta Learning SDK

Expert in lease-to-lease comparison and deviation analysis. Use when comparing lease amendments to originals, analyzing competing offers, benchmarking against precedents, or identifying deal term variations. Key terms include lease comparison, amendment analysis, offer comparison, precedent deviation, market benchmarking, competitive analysis

Comprehensive legacy codebase analysis skill for technical debt assessment, security vulnerability scanning, performance bottleneck detection, and modernization roadmap generation. Includes 7 Python tools for automated codebase inventory, architecture health analysis, and strategic modernization planning.

Use when capturing discoveries after phase completion, before shipping, or when reflecting on completed work to extract reusable patterns

>

>

>

Unified planning across personal life (my-vault), projects (ideas/), and learning.

Complete guide for Light Protocol on Solana - includes ZK Compression for rent-free compressed tokens and PDAs using zero-knowledge proofs, and the Light Token Program for high-performance token standard (200x cheaper than SPL). Covers TypeScript SDK, JSON RPC methods, and complete integration patterns.

Optimize web applications to achieve 95%+ Lighthouse scores across all categories. Use when optimizing performance, accessibility, best practices, or SEO for web applications.

Runs Google Lighthouse audits via Playwright for comprehensive web quality assessment including SEO, Performance, Accessibility, and Best Practices.

Run Lighthouse audits and implement performance, accessibility, and SEO fixes

Optimized Kubernetes distributions and configurations for resource-constrained edge and IoT deployments

Linear Logic Skill

Linear's proven methodology for software development and project organization. Use when helping users plan work, create issues, structure projects, set direction, prioritize tasks, or organize development workflows. Applies Linear's principles of momentum, simplicity, and focus—not API integration. For solo developers and teams organizing software projects.

Guides optimal Linear operations usage with caching, performance patterns, and error handling. Auto-activates when implementing CCPM commands that interact with Linear. Prevents usage of non-existent Linear MCP tools.

linkedin_job_resume_optimizer

Professional narrative style with line breaks, hashtag strategy, and hooks in first 2 lines to avoid truncation

Create engaging LinkedIn posts that drive engagement and build authority. Use when the user wants to write LinkedIn content, needs posts for their LinkedIn strategy, or wants to repurpose content for LinkedIn.

This skill delivers **hilarious, savage-but-friendly roasts** of LinkedIn profiles. Think Comedy Central Roast meets corporate networking. The goal is to make people laugh at the absurdities of profes

Master LINQ and EF Core query optimization including N+1 prevention, eager loading, projections, and performance patterns. Use when: (1) fixing N+1 queries, (2) optimizing slow queries, (3) implementing efficient data access, (4) reducing database load.

Lisa - intelligent assistant for memory and tasks. Triggers on 'lisa', 'hey lisa', or addressing lisa directly.

Phoenix LiveView UI and real-time feature patterns

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Comprehensive reference for the llama.cpp C API, documenting all non-deprecated functions and common usage patterns.

Multi-level caching strategies for LLM applications - semantic caching (Redis), prompt caching (Claude/OpenAI native), cache hierarchies, cost optimization, and Langfuse cost tracking with hierarchical trace rollup for 70-95% cost reduction