mcp-servers
Speech feedback to user via MCP audio servers. Use when providing status updates or asking questions.
Speech feedback to user via MCP audio servers. Use when providing status updates or asking questions.
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
Configure agent specs, inheritance, skills, and tools in .parac/ workspace. Use when setting up or customizing agents.
AI Agent の実行ガイドライン。TDD サイクル、品質保証、コンテキスト管理、完了報告のルールを定義。すべての開発タスク実行時に使用。
Enterprise session state management, token budget optimization, runtime tracking, session handoff protocols, context continuity for Claude Sonnet 4.5 and Haiku 4.5 with context awareness features
Expert in creating visual grammar cheatsheets for Kabardian language with morphological breakdowns and corpus examples. Generates cheatsheets with ASCII-tree morpheme visualization (like verb_translation_cheatsheet.md). Activates when user requests grammar cheatsheet, mentions "создай шпаргалку", "cheatsheet for [category]", or wants visual breakdown of Kabardian grammar with real examples.
Comprehensive guide to effective prompt engineering patterns including few-shot, chain-of-thought, ReAct, and advanced prompting techniques
Analyze your gptme conversation history for insights like token usage, costs, model preferences, and usage patterns - inspired by Spotify Wrapped.
Generate a context handoff prompt before clearing the session. Use when the user wants to preserve conversation state before running /clear, or when ending a session and wanting to resume later. Creates a summary prompt capturing task state, progress, decisions, and next steps that can be pasted into a fresh session.
Determines minimal context and routes tasks to the correct prompts, agents and tools.
Use this skill when implementing quest automation in SND macros using the Questionable plugin. Covers command usage and integration with leveling workflows.
PocketFlow framework for building LLM applications with graph-based abstractions, design patterns, and agentic coding workflows
Expert prompt engineering for LLMs and AI agents. Use when users request help writing, reviewing, or improving prompts for chatbots, AI agents, system prompts, instruction sets, or any LLM-based application. Applies research-backed techniques to minimize hallucinations and maximize reliability.
Routes to appropriate deep-RL skills based on problem type and algorithm family
Building AI agents and assistants with Convex. Use when implementing chat interfaces, AI assistants, tool-calling agents, RAG (retrieval-augmented generation), conversation threads, or integrating LLMs like OpenAI/Anthropic.
This skill should be used when users need to work with the Vercel AI SDK for building AI-powered applications. It provides comprehensive guidance on core APIs (generateText, streamText), UI components (useChat, useCompletion), tool calling, structured data generation, provider management, streaming protocols, and advanced features like middleware and custom providers.
Install agent-skills for Claude Code, Gemini Code Assist, and Codex
ChatBotプロジェクトの開発全般を支援するスキル。プロジェクト構造、コーディング規約、開発ワークフローに関する知識を提供します。ChatBotプロジェクトで作業する時、プロジェクト構造について質問された時、コーディング規約について質問された時、新しい機能を追加する時に使用してください。
Defense Manual against AI Hacking: Prompt Injection, Smuggling, and Agentic Exploits.
Complete guide for Panaversity Hackathon II (Todo Spec-Driven Development) Phases 2-5. Use when working on Phase 3 (MCP + OpenAI Agents + ChatKit chatbot), Phase 4 (Kubernetes with Minikube, Helm, Docker), Phase 5 (Cloud deployment with Dapr, Kafka, advanced features), or implementing bonus features (Reusable Intelligence, Cloud-Native Blueprints, Urdu support, Voice commands). Includes detailed references, scaffolding scripts, troubleshooting guides, and implementation patterns for AI-powered todo chatbot with event-driven architecture.
Self-improving review loop for Ralph Wiggum skills. Reviews skills against best practices, implements improvements, and continues until two consecutive clean reviews. Use when validating or improving the ralph-prompt-* skill suite.
Optimize context loading for efficient token usage. Use when working with large codebases, context limits, or when the user mentions "context", "token", "optimize", "summarize", or asks to reduce context size.