Claude Skills by oyi77

Use when agent harness optimization patterns for token efficiency, memory

Use when agentic security patterns for AI agent systems including attack

Use when monitor performance of other skills, identify bottlenecks, suggest

Use when structured AI engineering curriculum — 382 skills + 99 prompts

Use when automatically commit and push OpenClaw changes to GitHub. Enable

Use when autoGen multi-agent conversations — AssistantAgent, UserProxyAgent,

Use when core autonomy protocol for AI agent operations. Defines how

Use when orchestrate multi-skill workflows by routing tasks to the right

Use when convert technical books and documents (PDF, EPUB, DOCX, HTML,

Use when manage Cloudflare DNS, CDN, and security rules via API. Use

Use when knowledge base hub — PARA-structured company memory combining

Use when company-kb — Company Knowledge Base Skill. Use when relevant

Use when querying and maintaining the knowledge base for project context, decisions, and architecture documentation on session start.

Use when crewAI multi-agent orchestration — agents, tasks, crews, tools,

Use when dify AI workflow platform — LLM apps, knowledge bases, agents,

Use when automatically discover, evaluate, and activate community skills

Use when diagnose and fix MCP gateway routing issues, health checks,

Use when build applications using Google Gemini API. Handle chat completions,

Use when coordinate multi-agent consensus using TiDB-backed shared memory.

Use when deterministically coordinating autonomous planning and execution

Use when proactive agent that detects signals and suggests actions with

Use when andrej Karpathy's 4 coding principles — think before coding,

Use when knowledge base and memory system for AI agents. Covers company

Use when langChain/LangGraph patterns — chains, agents, tools, memory,

Use when llamaIndex data framework — ingestion, indexing, query engines,

Use when lLM deployment and serving — vLLM, Ollama, TGI, llama.cpp. Model

Use when fine-tune LLMs and ML models — LoRA, QLoRA, PEFT, Hugging Face.

Use when route AI model requests to the optimal provider based on task,

Use when integrate with OmniRoute AI Router for multi-provider LLM routing,

Use when advanced prompt engineering — chain-of-thought, few-shot, tree-of-thought,

Use when rAG pipeline design — document chunking, embedding strategies,

Use when run AI models on Replicate cloud API. Deploy image generation,

Use when manage revenue pipelines, track Stripe/analytics metrics, and

Use when automatically improve OpenClaw and 1ai-skills at runtime. Analyze

Use when generating and managing vector embeddings for semantic search

Use when self-reflection + Self-criticism + Auto-learning from corrections

Use when microsoft Semantic Kernel — AI orchestration, plugins, planners,

Use when automatically detect source types and build AI skills using

Use when monitor and analyze skill effectiveness in real-time. Track

Use when dynamically creates and manages AI agent teams for complex tasks.

Use when starting any conversation - establishes how to find and use

Use when vector database operations — Pinecone, Weaviate, Qdrant, ChromaDB.

Use when activate an AI general manager persona with full context awareness

Use when foundational core infrastructure skill providing system foundation

Use when zero-copy vector operations for efficient similarity search

Use when parsing and analyzing Cobalt Strike Malleable C2 profiles using

Use when mapping advanced persistent threat (APT) group tactics, techniques,

Use when parse Windows LNK shortcut files to extract target paths, timestamps,

Use when parse Windows Prefetch files using the windowsprefetch Python

Use when performing memory forensics analysis using Volatility 3 to extract