OpenAI plugins

Build and deploy production-grade LLM applications with LangGraph for agent orchestration, advanced RAG pipelines leveraging vector and hybrid search, prompt engineering patterns, and automated evaluation. Covers embedding model selection, vector index optimization, and multi-agent architectures for document Q&A, chatbots, and semantic search over proprietary data.

Build production-ready data pipelines with Apache Airflow and dbt, manage scalable data warehouses, and implement vector search and RAG systems using embedding models and vector databases.

Build and evaluate production-grade AI agents using LangGraph, RAG systems, MCP servers, and prompt engineering patterns—with behavioral testing and reliability monitoring.

Delegate code review, investigation, and complex coding tasks to OpenAI's Codex within Claude Code, with support for adversarial reviews, background job management, and readiness checks.

Accelerate LLM application development with production-ready patterns for context window management, RAG pipelines, prompt caching, observability via Langfuse, and agent architectures.

Build, deploy, and monitor AI-powered cloud applications on Azure using containerized apps, serverless functions, OpenAI integration, AI Search, and observability across .NET, Python, and Node.js.

Automate professional equity research workflows: generate earnings reports, initiating coverage, pre-earnings analysis, morning meeting notes, and sector landscapes. Screen stocks, track catalysts, update financial models, and maintain investment theses with cited sources.

Orchestrate creative AI image generation workflows: search a 1300+ curated design gallery for inspirations, craft batch prompts for parallel variations and concepts, auto-enhance short prompts, and generate images via MeiGen server with ComfyUI or OpenAI-compatible APIs.

Run comprehensive SEO audits and optimizations: crawl up to 500 pages, analyze backlinks and Core Web Vitals, validate schema and hreflang, generate content clusters and sitemaps, and track regressions—all from Claude Code.

Orchestrate multi-LLM workflows across providers (Claude, Gemini, Codex, Copilot) for the full software lifecycle — research, architecture, implementation, code review, security audit, testing, and delivery — using structured Double Diamond phases and autonomous agents.

Evaluate and improve LLM applications by instrumenting agents, chatbots, and RAG pipelines with DeepEval tracing, generating test suites, running evaluations, and exporting traces to Confident AI for observability and iterative refinement.

Manage AI-driven development workflows with hierarchical task trees, dependency graphs, automated subtask expansion, PRD-to-task parsing, status tracking, and intelligent task orchestration via natural language commands.

Full-cycle development workflow for solo developers: project scaffolding, multi-agent collaboration (Cursor PM & Claude Code), CI/CD automation, auth/payments setup, code reviews, release management, and cross-session memory.

Generate and edit images using GPT Image 2 and OpenAI-compatible endpoints with 70+ structured prompt templates across 18 categories, plus build polished visual web artifacts like pages, dashboards, prototypes, slide decks, and data visualizations using HTML/CSS/JavaScript/React.

Direct AI coding agents to create or update promptfoo evaluation suites with configs, prompts, tests, deterministic assertions, and provider setups following best practices. Streamline LLM eval coverage, regression debugging, and new eval matrix generation in JavaScript or Python projects using OpenAI or Anthropic models.

Implement a structured, spec-driven development lifecycle with AI agents: discuss requirements, research, plan, execute code, verify, and manage milestones. Includes multi-model plan review, automated code review, test generation, UI auditing, project documentation, and session handoff for continuous AI-assisted development.

Generate, edit, and inpaint images via GPT Image 2 CLI skill, using a reference prompt gallery to match styles for UI mockups, diagrams, posters, research figures, anime, and Chinese typography workflows.

Debug and fine-tune language models using the Tinker API: diagnose training pipeline issues, replicate research papers, run RL/SFT/DPO experiments, and monitor training logs—all from the command line.

Detect and rewrite AI-generated Korean text to sound human-written, using a multi-phase pipeline that scans for 40+ AI-typical patterns across 10 categories, preserves content, and validates semantic equivalence.

Integrate Perplexity Sonar API for AI-powered web search with verifiable citations into Node.js/Python apps. Handle full lifecycle workflows: auth setup, error debugging, rate limiting, caching optimization, monitoring, security guardrails, CI/CD testing, and scalable deployments to Vercel/Docker.

Orchestrate multi-agent AI systems with AI SDK v5 for task decomposition, handoffs, routing, and coordination across OpenAI, Anthropic, and Google providers. Use commands to initialize projects, generate specialized agents with custom prompts and tools, test workflows with metrics, and deploy orchestrator agents for complex task handling in TypeScript.

导入已有中文网络小说（半成品或完本）并自动解析为标准项目目录结构，支持长/短篇路由分流，打通从导入→分析→去AI化→封面设计→趋势研究→继续写作的完整创作管线，配合Agent协作与路由系统实现网文写作的逆向工程与正向产出闭环。

Monitor usage limits, reset times, and cost across multiple AI CLIs (Claude, Codex, Gemini, z.ai) from a unified terminal dashboard, with automatic recommendations for the CLI with most available capacity

Extends Claude Code with spec-driven development workflows: autonomous long-running tasks, multi-agent deep research, structured feature planning with EARS requirements and constitution-based specs, GitHub issue fixing and PR review, skill benchmarking and creation, image generation, and session learning capture.

Run AI-powered code reviews on uncommitted changes, branch diffs, or specific commits using external LLM CLIs (OpenAI Codex, Google Gemini), with an optional MCP server for direct tool access and collaborative reasoning.

Build production-grade LLM gateways with OpenRouter: route requests across 400+ models by task or criteria, chain fallbacks for reliability, cache responses to cut costs/latency, monitor usage/costs/latency, redact PII for compliance, and benchmark performance using Python OpenAI SDK wrappers.

Use Claude to manage Granola AI meeting notes workflows end-to-end: automate installations and upgrades, integrate with GitHub/Linear/Slack via Zapier for action items, optimize costs/performance/security, export data, troubleshoot issues, and deploy enterprise setups with RBAC/observability.

Integrate Speak AI SDK into language learning apps: scaffold conversations and pronunciation assessments with real-time feedback, configure auth/security/compliance, deploy to Vercel/GCP/Docker with CI/CD, optimize costs/performance/rate limits, monitor metrics, and troubleshoot via diagnostics/runbooks.

Optimize LLM prompts for OpenAI and Anthropic by automatically detecting redundancy, simplifying instructions, and rewriting to reduce token usage, lower costs, and improve performance.

Accelerate Atomic Agents app development through a guided 7-phase workflow: delegate schema design, agent and tool creation, architecture planning, codebase analysis, and code review to specialized AI sub-agents for scalable multi-agent LLM systems.

Master Cursor IDE AI workflows using 30 guided skills: install and authenticate, configure custom models and rules, optimize indexing and performance, automate Composer for multi-file refactoring and scaffolding, troubleshoot errors, manage teams with SSO, and audit compliance.

Set up end-to-end Langfuse LLM observability: trace calls via OpenAI/LangChain wrappers, evaluate prompts with scores/feedback, monitor costs/latency/security, integrate into CI/CD pipelines, deploy to Vercel/AWS/Docker, troubleshoot errors/migrations, and optimize for production scale in Node.js/Python apps.

Rapidly build, debug, deploy, secure, monitor, and scale Lindy AI agents and multi-step workflows using 24 Claude Code skills that guide webhook integrations, CI/CD pipelines, error troubleshooting, cost/performance tuning, enterprise RBAC, and migrations from Zapier, n8n, or LangChain.

Build .NET applications that provision Azure infrastructure (databases, caches, bots), integrate AI services (agents, OpenAI, voice, document intelligence, search), manage events/messaging (Event Grid, Hubs, Service Bus), authenticate via Entra ID, and handle Key Vault cryptography using official SDKs and ARM clients.

Audit GitHub Actions workflows to detect security vulnerabilities in AI agent integrations like Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Identify prompt injection risks and unsafe input flows in CI/CD pipelines before deployment.

Integrate Groq's fast AI inference into Node.js/TypeScript projects via 24 skills: build chat completions, tool calling, vision/audio processing; migrate from OpenAI/Anthropic; optimize costs, performance, rate limits; secure APIs with RBAC/PII redaction; deploy to Vercel/Docker; set up CI tests, monitoring, observability.

Integrate TwinMind AI to automate meeting transcription with speaker diarization, generate AI summaries and action items, sync tasks to Asana/Linear/Jira, handle webhooks/events, optimize costs/performance, configure security/RBAC, deploy to CI/CD/prod environments, and troubleshoot/migrate setups.

Build recommendation engines by generating Python code for collaborative, content-based, or hybrid filtering using scikit-learn, TensorFlow, or PyTorch to personalize movies, products, or content. Analyze context to produce complete AI/ML tasks with validation, error handling, performance metrics, insights, artifacts, and documentation.

Build and orchestrate AI agents using LangChain, LangGraph, and Deep Agents — scaffold, develop, deploy, and manage stateful agent workflows with memory, RAG pipelines, human-in-the-loop approval, and parallel task execution.

Integrate Azure SDKs into TypeScript/Node.js apps to build AI-powered services for content moderation, document extraction, translation, voice interaction; manage storage, queues, databases like Cosmos and Postgres; handle authentication, Key Vault secrets, Event Hubs, Service Bus messaging; enable monitoring, real-time Web PubSub, and Playwright testing.

Generate and integrate web design assets directly into projects: accessible Tailwind color palettes with dark mode and WCAG checks, complete favicon packages with HTML tags and manifests, custom SVG icon sets, AI images via OpenAI/Gemini from descriptions, and image processing like resize/optimize/convert.

Automate comprehensive project management: audit health and permissions, generate architecture/user docs and roadmaps, handle git workflows/PRs/releases, test UX/onboarding/responsiveness via browser, consult multi-AI models, and post team updates with feedback triage.

Generate importable n8n workflow JSON files from natural language descriptions, designing complex automations with loops, branching, error handling, retries, notifications, AI content pipelines, lead qualification, document processing, and OpenAI/JavaScript integrations.

Build production Retell AI voice agents for telephony and phone automation using TypeScript/Node.js SDK: create LLM-powered agents, manage outbound campaigns, handle webhooks/errors/rate limits, troubleshoot issues, tune performance/costs, deploy with checklists and observability via 30 specialized skills.

Scaffold multi-agent AI repositories from a template (quick or full mode), query codebases with natural language via a knowledge hub, and refresh the project knowledge base during development.

Build complex multi-step Zapier Zaps from natural language automation requests, incorporating triggers, actions, filters, paths, formatters, delays, and OpenAI integrations to automate workflows across apps without manual configuration.

Launch local stdio MCP servers via Codex CLI using GPT-5 and GPT-5-Codex models with high reasoning effort and full access, enabling Claude to access local AI for advanced reasoning, code tools, and tasks.

Receive phone calls from Claude when it needs input, wants to report progress, or needs to discuss a task — enabling voice-based interaction when text is insufficient.

Delegate complex coding tasks to specialized GPT subagents (Architect, Plan Reviewer, Scope Analyst, Code Reviewer, Security Analyst) within Claude Code workflows using Codex CLI orchestration rules.

Delegate complex AI and data tasks to specialized agents that proactively build LLM applications with RAG and orchestration, design scalable ETL pipelines and warehouses, deploy MLOps workflows, optimize prompts, analyze datasets, manage context, and decompose goals into actionable hierarchies.

Build, debug, secure, deploy, and scale production Anthropic Claude API integrations using 30 specialized skills for authentication, error diagnosis, cost/performance optimization, guardrails, CI/CD pipelines, observability, and architectures in Python and TypeScript.

Design AI-assisted visual Make.com (Integromat) automation scenarios, configuring triggers, routers, iterators, modules, data mapping, error handlers, and 1000+ app integrations for workflows like AI email responders, lead qualification, and content distribution.

Query multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, and local Claude subagents) to get diverse perspectives on architecture decisions, debugging dead-ends, and technology choices, with automated synthesis of consensus and divergence.

Develop, deploy, and manage Databricks-based data pipelines, ML models, AI agents, and dashboards using code, SQL, and declarative tools for multi-environment workflows.

Trigger OpenAI Codex/GPT models to autonomously implement code, perform reviews, and execute tasks in a sandboxed environment using commands like 'codex', 'use gpt', or 'full-auto' for hands-off automation workflows.

Enable Claude to analyze local video files or YouTube URLs with full multimodal perception: extract frames and audio via FFmpeg, detect scenes/motion/silence/transitions, transcribe speech using Whisper or Gemini, generate detailed visual descriptions, summaries, and answer questions interactively.

Iteratively implement plans using Claude with independent Codex reviews that validate progress against acceptance criteria, detect failures, and enforce git workflow discipline in a continuous feedback loop until quality standards are met or max iterations reached.

Fine-tune open-source LLMs on Together AI, run inference and batch jobs, deploy models to production, optimize costs and performance, debug errors, manage rate limits and security, migrate from other providers, and integrate into CI/CD workflows using Python SDK and OpenAI-compatible APIs via guided Claude Code skills.

Log AI experiments interactively from the terminal by capturing tool usage, prompts, summaries, and ratings. Generate reports with stats, top tools, rating distributions, tags, and filters by tool, tag, days, or rating. Search experiments by query, tool, tag, rating, or date with sorting and stats display.

Analyze AI prompts for clarity, specificity, completeness, and issues with 1-10 scores and targeted fixes, then optimize by rewriting with structured best practices like sectioning, examples, chain-of-thought, and guardrails for superior LLM results.

Generate AI images from prompts using MeiGen agents, search a curated gallery of 1300+ AI-generated images for visual inspiration, and orchestrate batch prompt creation for parallel image variations

Automates setup of MATLAB Agentic Toolkit: detects MATLAB installation, installs the MCP server, registers it with AI coding agents (e.g., Claude, ChatGPT), and verifies environment readiness.

Generate test fixtures that mock LLM responses, tool calls, errors, multi-turn loops, embeddings, and structured output across multiple AI providers for use with Copilot Kit's aimock library.

Refine rough prompts into precision-optimized versions for ChatGPT, Claude, and Gemini using the 4-D methodology. Receive the polished prompt, a summary of improvements made, and targeted tips to enhance future prompting.

Evaluate single ML models or compare multiple ones on test datasets across classification, regression, NLP, and generative tasks. Compute metrics, statistical significance, inference performance, costs, robustness, bias checks; generate visualized reports with confusion matrices, performance profiles, tables, rankings, and recommendations.

Orchestrate end-to-end academic research projects: plan experiments, run literature surveys, implement ML experiments, write LaTeX papers, and conduct peer reviews — all through interactive CLI agents that manage project state, delegate code tasks, and track progress.

Build and deploy AI agents to trade crypto, stocks, forex, and derivatives on Kraken via bash CLI: monitor markets, execute strategies like DCA, grid bots, basis trades, portfolio rebalancing; manage risks, staking, subaccounts with paper trading default and live opt-in safeguards. Integrates with Claude, Cursor, VSCode for stdio tool calls.

Write and navigate infrastructure security policies using MQL queries, cnspec CLI schema validation, and policy graph commands for compliance mapping

Generate vector embeddings from text data using OpenAI, Cohere, or local models, store them in a vector database with indexing, and perform semantic similarity searches to retrieve top-K matches with scores, metadata, re-ranking, and deduplication.

Automate a code review loop where Claude implements a task, Codex CLI independently reviews the changes, and Claude addresses the feedback iteratively until resolved.

Intercept and transform LLM API traffic with a mitmproxy-based server that supports OAuth authentication, sentinel key substitution, and model routing for OpenAI and Anthropic SDKs, and debug traffic flows through CLI tools or WireGuard capture.

Run a full digital marketing agency from Claude Code — plan campaigns, execute paid/SEO/email/social, audit performance, manage brands, and generate client deliverables across 158 skills and 25 agents.

Build production-ready Convex apps using guided skills for realtime React subscriptions, TypeScript schema validation, secure functions and audits, cron jobs, file storage and serving, zero-downtime migrations, HTTP endpoints, and persistent AI agents with tool integration.

Provides 59 expert skills covering the full SaaS lifecycle for non-technical founders building with AI tools: planning, design, build, database, integrations, AI features, security, testing, debugging, deployment, monitoring, marketing, pricing, growth, and business strategy.

Delegate image analysis, OCR text extraction, barcode/QR detection, and document processing to a vision expert agent using latest models like GPT-4V, Claude Vision, Mistral-OCR, Tesseract, and EasyOCR for efficient visual AI workflows.

Rapidly implement production-ready AI/ML features in apps: integrate LLMs with prompt engineering and response handling, build ML pipelines for recommendation systems, add computer vision for visual search, and enable intelligent automation using OpenAI, Anthropic, LangChain, Hugging Face, or Ollama.

Follow guided steps to build production-ready SaaS from idea discovery through UI/UX design, architecture, code generation, review, and deployment. Use optional phase arguments like design, architecture, develop, or deploy for targeted guidance powered by Vercel, Supabase, Stripe, OpenAI, and Cloudflare.

Build, deploy, and manage Vercel projects including Next.js apps, AI features with the AI SDK, serverless functions, microfrontends, monorepos, and marketplace integrations. Automate CI/CD pipelines, configure environment variables, manage storage and authentication, and optimize performance and security

Build, configure, and deploy AI agents using the Motus framework through guided editor commands. Define ReAct agents with custom tools, workflows, persistent memory, and guardrails, then serve them locally or to cloud platforms.

Rapidly implement production-ready AI/ML features in apps: integrate LLMs via prompt engineering and response handling, build ML pipelines for user behavior-based recommendations, add computer vision for photo-based product search, and deploy intelligent automations.

Refine rough prompts for AI platforms like ChatGPT, Claude, and Gemini into precision-optimized versions using the 4-D methodology, receiving the polished prompt, an improvements summary, and actionable tips.

Build, debug, and evaluate durable LLM workflows using the Output SDK — scaffold projects, manage encrypted credentials, orchestrate multi-step agents with Temporal, write and validate prompt files, and run cost analysis on workflow executions.

Refine product specifications iteratively through debates between multiple LLMs including Claude, OpenAI, Gemini, and Grok until consensus is reached. Activate interview mode for guided refinement, verify early agreements, and optionally integrate with Telegram for notifications.

Deploy generative AI models like GPT and Llama from providers including Azure OpenAI, AWS Bedrock, and GCP Vertex AI on SAP AI Core within SAP BTP. Orchestrate workflows with RAG using vector databases, templating, grounding, embeddings, and tool calling. Manage ML training pipelines via Argo Workflows and configure content filtering plus data masking for PII protection using SAP AI Launchpad.

Generate complete Korean podcast episodes from URLs, tweets, articles, or PDFs by analyzing sources, writing scripts, synthesizing audio with OpenAI TTS, converting to MP4, and automatically uploading to YouTube.

Orchestrate a multi-agent AI swarm that autonomously manages the full software development lifecycle — from brainstorming and design review through TDD implementation, PR management, code review, security audit, and release — using Claude Code, Gemini CLI, and Codex CLI with quality gates and knowledge base curation.

Build production LLM pipelines with DSPy 3.2.x: define typed signatures and modules, evaluate with rich-feedback metrics, optimize via GEPA, and reason over 100k+ token contexts using recursive RLM agents.

Turn rough dictated requests into structured prompts, critique plans with a panel of AI reviewers before committing, close sessions with handoff notes, and optionally pull second opinions from Codex or Gemini.

Rapidly implement production-ready AI/ML features in apps, including LLM integrations with prompt engineering, ML pipelines for recommendations, computer vision for visual search, and intelligent automation, using a specialized agent.

Run adversarial debates between multiple LLMs to cross-validate code, architecture, reviews, security, research, and planning tasks, producing specialized outputs like code, reviews, or plans.

Helps Qdrant users optimize and manage vector search deployments through tuning performance, diagnosing search quality, scaling clusters, deploying infrastructure, upgrading versions, and using client SDKs.

Orchestrate cross-agent AI workflows: delegate tasks to peers, request independent implementation plans and code reviews from different AI agent backends, coordinate multi-agent communication via ask/ack and broadcast primitives, and manage repowire installation from within an agent session.

Generates business intelligence dashboards, infographics, AI images/videos, and automates posting to social media (WeChat, X, Xiaohongshu) with tools for document parsing, Obsidian integration, and browser automation.

Conduct comprehensive security audits and incident response across cloud, API, mobile, and AI systems with pre-built skills for compliance, threat modeling, and red teaming.

Transform WPS Notes into a personal knowledge engine for long-form creative and academic writing. Automates memory retrieval, idea connection, insight generation, structured note-taking from any source (URLs, PDFs, images, audio transcripts), and multi-platform content formatting.

Runs operational-misalignment diagnostics on AI agents using iFixAi, guiding you from setup through fixture authoring to inspection with configurable judges from multiple model providers.