Multi-agent architectures with LangGraph. Use when building systems with multiple collaborating agents, implementing supervisor or swarm patterns, creating hierarchical agent workflows, or designing agent handoff mechanisms. Covers langgraph-supervisor, langgraph-swarm, agent-as-tool patterns, and context engineering for multi-agent systems.

Build production-grade agentic workflows with LangGraph using graph-based orchestration, state machines, human-in-the-loop, and advanced control flow

Expert guidance for LangGraph Python library. Build stateful, multi-actor applications with LLMs using nodes, edges, and state management. Use when working with LangGraph, building agent workflows, state machines, or complex multi-step LLM applications. Requires langgraph, langchain-core packages.

Design and implement multi-agent workflows with LangGraph 0.2+ - state management, supervisor-worker patterns, conditional routing, and fault-tolerant checkpointing

LangGraph skill for building stateful agent graphs, subgraphs, checkpoints, conditional flows, parallel execution, streaming, and multi-agent orchestration.

Hybrid language detection algorithm for Vigil Guard v2.0.0. Use for language-detector Flask API, entity-based hints, Polish PESEL/NIP detection, 3-branch pipeline integration, accuracy troubleshooting, and langdetect integration.

Design evolving language systems for fictional worlds. Use when creating language families, dialects, linguistic history, or when language should reflect cultural and historical development.

Package development and extraction of reusable code. Use when working with package development, code reusability, or when user mentions packages, composer packages, extract package, reusable code, package development.

Deploy and manage Lark (Feishu) bot for Milady meme generation, command handling, and team collaboration. Use when setting up Lark webhooks, handling bot commands, deploying to production, or integrating with Lark messaging.

Expert guide for Layer Cake, a headless Svelte visualization framework managing scales, dimensions, and data flow while supporting SVG, Canvas, HTML, and WebGL rendering contexts for responsive data visualizations.

Guides adding new Higher Inductive Types to the ComputationalPaths library. Use when creating new HITs, defining fundamental group (pi1) calculations, implementing encode-decode proofs, or adding new topological spaces.

>

Transform "I want to learn X" into actionable learning roadmaps using metalearning principles: identify the critical 20%, build expert vocabulary, sequence logically (why before how), prioritize curre

Learn about Nexus integrations and MCP. Load when user mentions: learn integrations, what is MCP, connect tools, integration tutorial, add integration, external tools, API connections, third party, how to integrate. 10-12 min.

Master Nexus philosophy and best practices. Load when user mentions: learn nexus, nexus tutorial, system mastery, nexus best practices, how nexus works, nexus philosophy, nexus design, understand nexus, nexus deep dive. 15-18 min.

Process learning resources from markdown files, extract content, identify clusters, and create Ship-Learn-Next learning paths

Transform textbook chapters into engaging, evidence-based lectures with Google Slides. Guides instructors through learning outcomes, narrative design, active learning activities, and slide creation via Google Docs MCP.

Transform legacy codebases into AI-ready projects by generating Claude Code configurations.

Converts hierarchical legislative text from Word documents into a flat list of requirements. Use when processing regulatory documents, compliance frameworks, or legal text that needs to be extracted into individual, numbered requirements for analysis or mapping.

Le arquivos Excel (.xlsx, .xls) e CSV enviados pelo usuario. Use quando o usuario anexar um arquivo e pedir para analisar, importar ou processar os dados. Retorna o conteudo como JSON para analise.

Use when concluding significant work to extract reusable patterns and anti-patterns

Orchestrates full decomposition (scope → Epics → Stories) by delegating ln-210 → ln-220. Sequential Story decomposition per Epic. Epic 0 for Infrastructure.

>

CRISPR library design for genetic screens. Covers sgRNA selection, library composition, control design, and oligo ordering. Use when designing custom sgRNA libraries for knockout, activation, or interference screens.

Discover and analyze lien positions from AcclaimWeb and RealTDM to detect HOA foreclosures and senior mortgage survival

>

Provides comprehensive guidance for Lime ECharts including chart creation, configuration, data visualization, and interactive charts. Use when the user asks about Lime ECharts, needs to create charts, visualize data, or work with ECharts features.

Use when recalling conversations from Limitless Pendant, finding what was discussed in meetings, searching lifelogs, or answering 'what did I say about' questions

Analyzes dbt model dependencies, traces upstream sources and downstream consumers, identifies circular dependencies, and visualizes data lineage. Use when user asks about model dependencies, wants to understand data flow, needs impact analysis, or wants to trace where data comes from or goes to.

Extended operations for Linear: milestones and issue image downloads.

Write titles that describe the problem or outcome:

Calculate linkage disequilibrium statistics (r², D'), perform LD pruning for population structure analysis, identify haplotype blocks, and visualize LD patterns using PLINK, scikit-allel, and LDBlockShow. Use when calculating LD or pruning variants.

Call LinkAI applications and workflows. Use bash command to execute like 'bash <base_dir>/scripts/call.sh <app_code> <question>'.

Displays all architecture team members and their expertise areas.

This skill enables systematic academic literature search and analysis for creating high-quality WeChat content. It provides workflows for finding relevant research papers, extracting key insights, and

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

LLM architecture, tokenization, transformers, and inference optimization. Use for understanding and working with language models.

Pydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.

Creates reference documentation structure + smart documents (ADRs/Guides/Manuals) based on TECH_STACK. Only creates justified documents (nontrivial technology choices). L2 Worker in ln-100-documents-pipeline.

Orchestrates task operations. Analyzes Story, builds optimal plan (1-6 implementation tasks), delegates to ln-301-task-creator (CREATE/ADD) or ln-302-task-replanner (REPLAN). Auto-discovers team ID.

Load architecture principles and core conventions for grounding work against project standards - simple context loading for all workflow stages

When distributing traffic across multiple servers or regions, use this skill to select and configure the appropriate load balancing solution (L4/L7, cloud-managed, self-managed, or Kubernetes ingress) with proper health checks and session management.

Load conductor workflow state from previous session and determine resumption point by analyzing git state and saved JSON state file

Load, activate, and optionally install an AI skill from a .skill file. Use this skill when the user wants to load, activate, or use a skill file. The user can invoke this skill with slash command `/load-skill [ --install | -i ] SKILLFILE`, where SKILLFILE is the path to a .skill file.

Bootstrap skill loader for instance startup. Pulls fresh skills from plurigrid/asi and loads GF(3)-balanced startup triads. MUST run at beginning of every new instance.

Imported skill load from langchain

Maintain user confidence when content isn't immediately available.

Load pre-existing Seurat objects into the immunopipe pipeline instead of starting from raw count matrices via SampleInfo. This enables analysis on already processed single-cell RNA-seq data stored in Seurat R objects.

LobeTTS - High-quality TypeScript TTS/STT toolkit with EdgeSpeech, Microsoft, OpenAI engines, React hooks, audio visualization components, and both server and browser support

Use when user mentions bookmarks, knowledge management, notes, saving URLs, or taking screenshots - provides quick reference for km (Zettelkasten notes), bookmark (URL manager), and shot-scraper (automated website screenshots) CLI tools installed on this system