repo-onboarding
Repository onboarding and agent bootstrap. Use at the start of a new repo session or before any task to load AGENTS.md, architecture/skills indexes, and discover local Codex skills.
Repository onboarding and agent bootstrap. Use at the start of a new repo session or before any task to load AGENTS.md, architecture/skills indexes, and discover local Codex skills.
Ensures all AI-generated output fields have proper validation. Auto-activates on "AI 輸出", "LLM", "Gemini", "GPT", "truncate", "截斷" keywords. Lesson learned: 2026-01-08 Quick Feedback, Report, Deep Analyze truncation bugs.
Present structured multi-choice questions to users via MCP-based QA artifacts. Use when: (1) Need to ask user multiple structured questions, (2) Gathering preferences or requirements through multi-choice options, (3) Clarifying ambiguous instructions with structured choices, (4) Getting decisions on implementation choices. Triggers on: "UAUQ", "ask me questions", "I need to ask the user", "gather requirements", "clarify with user".
A simple hello world skill that demonstrates how to create a basic Claude Code skill. Use when the user asks to say hello or test a basic skill.
Design, optimize, and refactor AI agent systems based on Anthropic best practices and latest research. Guides you through architectural decisions with interactive questionnaire, loads current documentation, and launches specialized agent-architect for detailed analysis.
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.
Retrieval-Augmented Generation systems, vector databases, embedding strategies, and production RAG architectures for enterprise LLM applications. Use when building RAG, semantic search, or knowledge-aware AI systems.
Generates images using Pollinations API. Validates model constraints and dimensions. Use for: image generation logic, model selection, constraint validation. DO NOT use for: video generation (use generating-videos), UI styling (use styling-ui).
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
Skill for configuring OpenAI Agents SDK to work with alternative LLM providers using base URL and API key
Loop automatizado de melhoria contínua que usa o Chat RAG para identificar débitos técnicos, implementa correções, reingere a base de conhecimento e valida até eliminar 100% dos débitos.
Programmatic agent definitions for the Claude Agent SDK in TypeScript and Python. Use when creating agents for SDK-based applications rather than filesystem-based Claude Code.
Monitors background agents efficiently using local file reads instead of TaskOutput API calls. Use when running parallel background agents, checking agent progress, detecting completion status, or minimizing token usage during multi-agent orchestration.
Master CQL, IQL, BCQ - offline RL from fixed datasets without environment interaction
Use this skill when running, managing, or analyzing yanex experiments. Includes executing experiments via CLI, parameter sweeps, dependencies, querying experiment history, comparing results, and maintaining experiment logs. Invoke when users mention yanex, experiments, training runs, parameter sweeps, or need to track ML experiments.
Creates a permanent backend instance for Claude Imagine. Use this skill when the user wants to set up a new persistent backend server.
Reduce LLM API costs without sacrificing quality. Covers prompt caching (Anthropic), local response caching, prompt compression, debouncing triggers, and cost analysis. Use when building LLM-powered features, analyzing API costs, optimizing prompts, or implementing caching strategies.
Use this skill in the scenario of deep learning project development.
Fine-tune LLMs with Unsloth using GRPO or SFT. Supports FP8, vision models, mobile deployment, Docker, packing, GGUF export. Use when: train with GRPO, fine-tune, reward functions, SFT training, FP8 training, vision fine-tuning, phone deployment, docker training, packing, export to GGUF.
Automatically generates skills from Context7 MCP documentation responses