OpenAI

cost-aware-llm-pipeline helps you build LLM workflows that control API spend with model routing, immutable cost tracking, retry handling, and prompt caching. Ideal for batch jobs, document pipelines, and Workflow Automation where output volume and quality tradeoffs need clear rules.

embedding-strategies helps you choose and optimize embedding models for semantic search and RAG workflows, with practical guidance on chunking, model tradeoffs, multilingual content, and retrieval evaluation.

develop-ai-functions-example helps you create or modify runnable AI SDK examples in vercel/ai under examples/ai-functions/src/. Use it to choose the right category, match repo conventions, and build minimal examples for provider validation, demos, or fixtures.

transcribe turns audio or video into text with optional diarization and known-speaker hints. It is well suited for Technical Writing, meeting notes, interviews, lectures, and content ops when you need a repeatable transcribe skill with clear output formats and less guesswork than a generic prompt.

The context-engineering skill helps you structure project context so agents follow conventions, reduce hallucinations, and stay focused. Use it when starting a session, switching tasks, or building a context-engineering guide for a codebase.

chatgpt-apps is the skill for building or fixing ChatGPT Apps SDK projects that pair an MCP server with a widget UI. Use it for docs-aligned setup, tool design, bridge wiring, resource registration, metadata, CSP, and repo validation. It also supports chatgpt-apps for Backend Development when backend and UI must be designed together.

context-optimization is a practical skill for Context Engineering that helps reduce token waste, preserve decision state, and manage long workflows. Use it to handle context limits, trim tool-output bloat, improve cache-friendly prompt structure, apply observation masking and compaction, and partition context when needed. It is built for real usage, not just theory.

baoyu-imagine is a multi-provider image generation skill with a typed CLI, mandatory EXTEND.md setup, reference image support, aspect ratio controls, and batch runs across OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, MiniMax, Jimeng, Seedream, and Replicate.

huggingface-local-models helps you find Hugging Face models that run locally with llama.cpp and GGUF, choose a practical quant, and launch on CPU, Apple Metal, CUDA, or ROCm. It covers model discovery, exact GGUF file lookup, server vs CLI setup, and a fast path for backend development and private local inference.

neat-freak is a knowledge cleanup skill for end-of-session handoffs. It reconciles project docs, agent memory, and code drift so CLAUDE.md, AGENTS.md, and docs/ stay accurate. Useful for technical writing, developers, and agent operators who need a cleaner, more reliable project knowledge base.

aihot is a web-research skill for current AI news, daily picks, model launches, and trend summaries from aihot.virxact.com. Use the aihot skill when you need fresh AI updates in Chinese or English, including today’s headlines, recent releases, and concise briefing-style summaries without relying on stale training data.

azure-ai-openai-dotnet helps .NET developers integrate Azure OpenAI with practical guidance on setup, auth, client selection, and usage for chat, embeddings, images, audio, and assistants. It is useful for API Development when you need a working Azure.AI.OpenAI starting point, not just a conceptual summary.

podcast-generation helps build AI-generated podcast-style audio from text using Azure OpenAI GPT Realtime Mini over WebSocket. It fits podcast-generation for Full-Stack Development, with guidance for React, Python FastAPI, PCM streaming, transcript capture, and WAV conversion. Use it when you need a practical podcast-generation guide for real app integration, not a generic prompt.

mcp-builder is a practical guide for MCP Server Development, helping you design high-quality servers that let LLMs use external services through clear, reliable tools. It covers architecture choices, tool boundaries, schema quality, evaluation thinking, and when to reuse Microsoft MCP services instead of building custom.

codex is a Claude Code skill that wraps the Codex CLI for code analysis, refactoring, and automated editing. It helps you run `codex exec` and `codex resume` with the right model, sandbox, resume flow, and quieter default output. Requires a working local Codex CLI install first.

tree-of-thoughts is a reasoning workflow skill that helps agents explore multiple approaches, prune weak branches, and synthesize a better answer. It is useful for hard debugging, planning, architecture tradeoffs, and tree-of-thoughts for Agent Orchestration.

do-in-parallel is a workflow skill for Agent Orchestration that launches multiple sub-agents in parallel across files or targets, groups repeatable work intelligently, and verifies results with meta-judges and LLM-as-a-judge review. Use the do-in-parallel skill when you need batch execution with less guesswork than a generic prompt.

The model-hierarchy skill helps agents route work to the cheapest model that can handle it, improving cost control without sacrificing routine quality. Use this model-hierarchy guide for Workflow Automation, sub-agent spawning, and simple task classification. It fits installs where you want a repeatable model-hierarchy usage pattern instead of ad hoc model choice.

create-boss turns boss chats, notes, emails, and project artifacts into a reusable skill for judgment, managing up, and persona modeling. Install it in Claude Code or OpenClaw to build real manager profiles or entrepreneur archetypes, then refine outputs with correction workflows and reusable Playbooks-ready boss guidance.

netlify-ai-gateway skill guide for Netlify AI Gateway. Learn install and usage basics, supported models, SDK setup, and backend development patterns for Netlify apps.

voltagent-best-practices is a concise VoltAgent guide for choosing agents vs workflows, organizing project layout, and wiring memory, servers, and observability. It helps teams make faster architecture decisions and reduce guesswork during skill authoring.

transform-generate-image-with-transloadit is a one-off image generation skill for creating a local image file from a text prompt or prompt plus reference images using Transloadit via the transloadit CLI. Use it for fast, prompt-driven image generation with clear output-path control and optional model selection.

codex-collab is a Claude Code skill for handing work to Codex through the codex app-server JSON-RPC protocol. Use the codex-collab skill to run tasks end-to-end, review code, research in parallel, and support workflow automation with resumable threads and reusable output.

full-output-enforcement is a writing and execution guardrail skill for complete, unabridged output. It bans placeholders, partial deliveries, and skipped middle sections, making it useful for code generation, documentation, migrations, and Skill Authoring when completeness matters.