Search Results for "OpenAI API" | AgentCC

AI Wrapper Product

Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' — products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS.

scaffolding-openai-agents

Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating multiple specialists. Covers Agent class, Runner patterns, function tools, guardrails, and streaming responses. NOT when using raw OpenAI API without SDK or other agent frameworks like LangChain.

openai

Guide for OpenAI API integration

voice-agents

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

sora

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

add-voice-transcription

Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

ollama-setup

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

AI Integration

Generates LLM API integration code for OpenAI, Anthropic, and Google. Includes prompt engineering patterns, streaming responses, error handling, cost estimation, and RAG pipeline setup.

gpt-imagen

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

openai-image-gen

Generate images using OpenAI's GPT Image API (gpt-image-1.5). This skill should be used when the user asks to generate, create, or produce images, illustrations, or visual assets. Handles prompt optimization, API calls, and saves output images to disk. Supports transparent backgrounds, multiple sizes, and quality levels.

speech

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

OpenAI Automation

Automate OpenAI API operations — generate responses with multimodal and structured output support, create embeddings, generate images, and list models via the Composio MCP integration.

ai-dev

Provides expert support on artificial intelligence, machine learning, and LLM integration. Covers OpenAI API, Anthropic Claude API, Hugging Face, LangChain, RAG systems, vector databases, fine-tuning, prompt engineering, and AI feature integration. Use this agent when the user mentions concepts such as AI, artificial intelligence, ML, machine learning, LLM, ChatGPT API, Claude API, Gemini API, RAG, embedding, vector, fine-tune, or model training.

openai-docs

Use when a user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits). Prioritize the OpenAI developer docs via the MCP tools and restrict any fallback browsing to official OpenAI domains.

gateway-proxy

Expert guidance for configuring kgateway and agentgateway for AI/LLM routing, MCP server routing, and API gateway patterns. Use when setting up gateway proxies for Ollama, OpenAI, Anthropic, Gemini backends, configuring HTTPRoutes, troubleshooting Gateway API issues, or working with OrbStack Kubernetes networking.

content-scout

YouTube channel monitoring and daily content briefing pipeline. Monitors configured channels for new uploads, downloads videos, extracts/classifies visual frames (charts, slides, screens vs talking heads), transcribes audio, and generates a daily markdown brief with key takeaways. Use when: (1) processing YouTube videos for visual and transcript analysis, (2) generating daily content briefs from monitored channels, (3) running the content-scout pipeline or any of its steps, (4) managing channel watchlists, (5) frame extraction or classification tasks. Requires: yt-dlp, ffmpeg, Python 3.10+, PIL/Pillow, imagehash, python-slugify. Optional: OpenAI API (transcription fallback), notion-client (Notion sync).

conversation-summarizer

Summarize AI text conversations into structured, actionable overviews. Use when a user provides a conversation log, chat export, or dialogue transcript and wants a summary. Supports multiple formats: JSON logs with turn-based structure, ChatGPT/Claude exports, OpenAI API message arrays, JSONL chat logs, and plain-text transcripts with role markers. Triggers on requests like "summarize this conversation," "give me an overview of this chat," "extract key decisions from this dialogue," or "what action items came out of this conversation."

ai-vision

Multimodal UI understanding and single-step planning via OpenAI-compatible Responses APIs. Use when you need AIQuery/AIAssert and plan-next to extract UI element coordinates, validate UI assertions, summarize screenshots, or decide the next UI action from an image. External agents handle execution via adb/hdc and multi-step loops. Defaults to Doubao models but can be pointed at other multimodal providers via base URL, API key, and model name.

imagegen

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

openai-whisper

Local speech-to-text with the Whisper CLI (no API key).

imagegen

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (scripts/image_gen.py) and require `OPENAI_API_KEY` for live calls.

subtitle-translator

Translate SRT subtitle files using LLM APIs with OpenAI-compatible format. Supports both single-language and bilingual output. Use when you need to translate subtitle files (.srt) from one language to another while preserving timestamps. Processes in batches of 50 sentences with progress logging.

openrouter-openai-compat

Configure OpenRouter as an OpenAI API drop-in replacement. Use when migrating from OpenAI or using OpenAI-compatible libraries. Trigger with phrases like 'openrouter openai', 'openrouter drop-in', 'openrouter compatibility', 'migrate to openrouter'.

OpenAI Automation

Automate OpenAI API operations -- generate responses with multimodal and structured output support, create embeddings, generate images, and list models via the Composio MCP integration.

OpenAI

Work with OpenAI — integrate, configure, and automate. Use when asked to set up OpenAI, use the OpenAI API, integrate OpenAI into a project, troubleshoot OpenAI errors, or build OpenAI automation.

openai-docs

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.

openai-image-generation

anand-testcompare

Generate or edit images with OpenAI's Images API without Python. Use when the user asks to create, generate, modify, or inpaint images and wants a CLI workflow runnable with `sh` or `bun` from any directory via an absolute script path.

sora

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.

knowpatch

LLM knowledge cutoff compensator — knowledge corrections for breaking changes and API drift. Covers: renamed packages (shadcn-ui→shadcn), changed APIs (z.string().email()→z.email()), new config formats (.eslintrc→eslint.config.js), current model IDs, Apple platform changes. Versions are NOT cached — always verify via package manager. Useful for: install, create, scaffold, upgrade, migrate, latest, version, dependency, shadcn, tailwind, vite, zod, eslint, react, next, svelte, nuxt, django, fastapi, pydantic, ruff, uv, claude, gpt, gemini, openai, anthropic, deepseek, qwen, llama, mistral, kimi, minimax, glm, node, bun, python, typescript, macos, xcode, swift, swiftui, supabase, npm, pip, cargo, package.json, pyproject.toml, requirements.txt.

install-agentpmt-mcp

Install and configure the AgentPMT MCP server for any AI agent. Use this skill when the user wants to connect Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Zed, OpenAI Codex CLI, Gemini CLI, or any MCP-compatible client to the AgentPMT tool marketplace. Also use when the user mentions AgentPMT setup, MCP server configuration, agent tool marketplace, or connecting an AI agent to paid tools and APIs.

imagegen

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.