AI & LLM

Claudeception enables Claude Code to build persistent knowledge by extracting reusable skills from debugging sessions and problem-solving. When you discover a non-obvious solution, workaround, or debugging technique, it captures that knowledge as a new skill that can be automatically retrieved in future sessions facing similar problems.

A comprehensive reference guide for the Langroid multi-agent LLM framework. Provides design patterns and code examples for agent configuration, stateful tool handlers, task control with done_sequences, batch processing, MCP tool integration, and quiet mode output control.

A documentation helper that records and organizes design patterns for the Langroid multi-agent framework. When you learn a new pattern, this skill guides you to add a description to the patterns catalog and create detailed reference documentation with code examples.

Stripe's official AI integration toolkit that enables AI agents to interact with Stripe APIs for payments, subscriptions, and billing. Supports popular frameworks like LangChain, Vercel AI SDK, and CrewAI, and includes utilities for metering LLM token usage through Stripe's billing infrastructure.

This skill sets up Geoffrey Huntley's 'Ralph Wiggum' autonomous coding technique - a bash loop that feeds prompts to Claude CLI for automated code generation. It supports planning mode (gap analysis) and building mode (implementation), with Docker isolation as an option for safer execution.

Execute Hugging Face Hub operations using the hf CLI. Download models and datasets, upload files to Hub repositories, create repos, manage local cache, and run compute jobs on HF infrastructure. Supports authentication, file transfers, and cloud compute management.

Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.

Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).

MolyKit is a reference skill for building AI chat interfaces using Makepad, a Rust UI framework. It provides patterns for cross-platform async programming (native and WASM), ready-to-use chat widgets, and OpenAI API integration with SSE streaming support.

This skill integrates the OpenAI Codex CLI with Claude Code, allowing users to run code analysis, refactoring, and automated editing tasks. It provides a structured workflow with explicit permission prompts before executing high-impact operations, and supports resuming previous Codex sessions.

A comprehensive guide for building Microsoft Teams bots and AI agents. Covers Teams SDK v2, integration with OpenAI and Claude LLMs, Microsoft Graph API for accessing user data and Teams channels, Adaptive Cards for rich UI, RAG with Azure AI Search, and deployment to Azure Bot Service.

A comprehensive guide for building AI-first applications using LLMs. Covers project structure, typed LLM client patterns, prompt versioning, testing strategies (mocks, fixtures, evaluations), CI/CD integration for LLM tests, and cost/performance tracking. Focuses on the principle of using LLMs for logic and traditional code for infrastructure.

This skill provides a quick reference guide for the latest AI models across major providers. It includes model IDs, pricing comparisons, usage examples, and selection recommendations for tasks like text generation, code completion, image generation, voice synthesis, and embeddings.

A comprehensive guide for building autonomous AI agents using Pydantic AI (Python) and Claude Agent SDK (Node.js). Covers agent architecture, tool design, multi-agent coordination, memory management, guardrails, and testing patterns with practical code examples.

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

cass-memory (cm) is a sophisticated memory and learning system for AI coding agents. It analyzes past coding sessions to extract reusable rules and patterns, stores them in a 'playbook', and retrieves relevant context for new tasks. The system supports team collaboration through git-tracked repo-level playbooks and provides feedback mechanisms to improve rule quality over time.

AI Partner Chat provides personalized conversations by integrating user/AI personas and vectorized personal notes. It uses a local ChromaDB database with BAAI/bge-m3 embeddings to retrieve relevant context from your markdown notes during conversations.

A comprehensive reference guide for thought-based reasoning techniques in LLMs. Covers Chain-of-Thought prompting, Zero-shot CoT, Self-Consistency, Tree of Thoughts, ReAct, PAL, and Reflexion with prompt templates, decision matrices, and best practices for improving complex reasoning tasks.

A comprehensive reference guide for understanding and optimizing context in LLM agent systems. Covers context anatomy, degradation patterns, multi-agent verification workflows, and optimization techniques like compaction and observation masking.

A comprehensive reference guide for designing multi-agent architectures in Claude Code. It covers three main patterns (supervisor/orchestrator, peer-to-peer/swarm, and hierarchical), along with context isolation strategies, consensus mechanisms, failure mode mitigations, and memory system designs ranging from simple file-based to temporal knowledge graphs.

Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use when user explicitly requests Gemini operations.

Generate structured agent prompts with FOCUS/EXCLUDE templates for task delegation. Use when breaking down complex tasks, launching parallel specialists, coordinating multiple agents, creating agent instructions, determining execution strategy, or preventing file path collisions. Handles task decomposition, parallel vs sequential logic, scope validation, and retry strategies.

Prompt Coach analyzes your Claude Code session logs stored locally on your machine to help you become a better AI-native engineer. It provides insights on token usage and costs, prompt quality scoring with real examples, tool usage patterns, productivity time analysis, and actionable recommendations for improvement.

This skill teaches Claude how to help users train specialized small language models (SLMs) using the Distil Labs platform. It covers the entire workflow from data preparation and model creation through training and local deployment with Ollama or vLLM.

Clarity Gate is a document verification system that checks whether claims are properly marked as uncertain or validated before documents enter RAG knowledge bases. It helps prevent LLMs from mistaking assumptions for facts by enforcing epistemic markers and requiring human-in-the-loop verification for unverified claims.

Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, or needs skill creation guidelines. Provides structure, naming conventions, description writing, and quality checklist.