AI/ML plugins

Orchestrate 1,388 specialized AI skills in Claude Code to automate expert workflows for Azure SDK integrations, Odoo/Shopify configs, SEO audits, security pentests, full-stack scaffolding, agent building, and DevOps pipelines across Python, React, AWS, Kubernetes.

Search, retrieve, improve, and manage thousands of AI prompts and Claude skills from prompts.chat directly in your coding assistant. Install skills to extend capabilities, fill prompt variables, save custom prompts with metadata, and enhance them using AI.

Orchestrate swarms of AI agents for complex multi-step tasks using SPARC methodology, swarm coordination, and GitHub automation, with WASM-accelerated local execution and a cloud-based orchestration platform providing 70+ tools.

Refactors and modernizes legacy codebases by detecting code smells, SOLID violations, and technical debt, generating prioritized remediation plans with cost estimates, while preserving project context for safe incremental migrations.

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.

Generate investor-ready startup business analyses: calculate TAM/SAM/SOM market sizing, build 3-5 year financial models with cohort revenue, cash flow, burn rate, and scenarios; analyze competitive landscapes and team structures; benchmark metrics like CAC/LTV and ARR; produce full business case documents.

Run a complete academic research pipeline from deep literature review through writing, peer review simulation, revision, and finalization, with citation verification, cross-source synthesis, and AI-usage disclosure generation.

Perform end-to-end research workflows: market analysis, competitor benchmarking, trend detection, data validation, and idea vetting. A team of specialized agents retrieves and synthesizes information from web, files, and scientific literature to deliver actionable insights and strategic recommendations.

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.

Orchestrate swarms of specialized AI agents to automate end-to-end software development: plan features, implement code with Rails/Python/TS patterns, conduct multi-perspective reviews for architecture/security/performance, resolve todos/PR feedback in parallel, run browser/iOS tests, sync Figma designs, generate docs/videos, and ship PRs.

Query version-specific documentation and code examples directly from source repositories using retrieval-augmented generation (RAG), enabling Claude to access up-to-date technical references during conversations.

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

Automate multi-platform workflows across Airtable, Google Sheets, Notion, Slack, and Make (Integromat) using Composio-connected tools, with guidance on building MCP servers and orchestrating durable execution on n8n, Temporal, or AWS Step Functions.

Delegate architecture, implementation, optimization, and debugging of complex applications to specialized AI agents expert in Python/Django/FastAPI, TypeScript/React/Next.js/Angular/Vue, Go, Rust, Java/Spring Boot, PHP/Laravel/Symfony, C#/.NET, mobile (Flutter/React Native/Swift/Kotlin), Elixir/Rails, SQL, and DevOps tools.

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.

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

Coordinate specialized AI agents through the full academic paper writing workflow: from literature search and argument blueprinting to drafting, citation verification, bilingual abstract generation, journal formatting, and simulated peer review, producing publication-ready LaTeX, DOCX, or PDF output.

Delegate complex data engineering, ML, and AI workflows to specialized sub-agents that design scalable pipelines, build and optimize models, architect LLM systems, tune databases for performance, and deploy production infrastructure across clouds.

Upgrade Claude AI integrations by migrating code, prompts, and API calls from Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, automatically updating model strings across Anthropic, AWS Bedrock, GCP Vertex AI, and Azure AI Studio platforms.

Generate Product Requirements Documents (PRDs) interactively by answering questions on feature goals, users, and scope, structuring them into user stories with acceptance criteria and non-goals, then convert to prd.json format for autonomous execution by the Ralph agent system.

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.

Manage the full Hugging Face ML lifecycle from a single agent: search and select models, estimate GPU memory, train or fine-tune with TRL/Unsloth, evaluate locally, build and deploy Gradio demos on Spaces, publish datasets and research papers, and run models in-browser with Transformers.js.

Invoke MiniMax AI skills to scaffold React/Next.js frontends, fullstack apps with Node/Python/Go backends, Flutter/React Native/Android/iOS mobile projects; generate/edit DOCX/PDF/PPTX/XLSX files; produce GIF stickers, shaders, music playlists/videos; analyze images via CLI workflows.

Scaffold new Claude Agent SDK apps in TypeScript or Python by interactively gathering requirements, installing dependencies, and configuring projects. Verify apps post-creation or changes for SDK best practices, code quality, security, type safety, documentation, and deployment readiness.

Build and integrate AI copilot features into web apps using CopilotKit v2, with full support for chat interfaces, agent-to-frontend communication, multiple agent frameworks, and runtime setup in React, Next.js, and other JS frameworks

Solve IMO, Putnam, USAMO, and AIME competition math problems using pure reasoning enhanced by adversarial verification that detects self-check errors missed by standard methods. Obtain calibrated confidence scores and PDF outputs for verified solutions.

Orchestrate multi-agent teams for complex AI-driven projects: decompose tasks, match capabilities, coordinate workflows, manage shared context and errors, distribute workloads, monitor performance with Prometheus and OpenTelemetry, and synthesize insights from interactions. Integrates PowerShell, .NET, Azure ops via specialist subagents.

Automate private equity workflows: screen deals, run due diligence, analyze financials, build IRR models, assess unit economics, monitor portfolio performance, and generate investment memos and value creation plans.

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.

Persist memory across AI coding agent sessions by capturing tool usage and insights, compressing via LLM, and injecting relevant past context into future interactions. Recall session history, search observations, and forget specific data via natural language commands.

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.

Build and debug n8n workflows via an MCP interface with expert guidance for AI nodes, binary data, custom code, error handling, expressions, and deployment.

Query biomedical literature and preprints (PubMed, biorxiv), search clinical trials, explore drug-target associations (Open Targets, ChEMBL), and run preclinical analyses (RNA-seq, single-cell QC, scvi-tools) directly from the coding environment

Delegate full-stack development workflows to Claude via 213 specialized agents, commands, and skills: refactor code, generate tests/deployments/Dockerfiles/K8s manifests, audit security/performance, document APIs/onboarding, orchestrate Git ops, and apply patterns across JS/TS/Python/Rust/Go/Java stacks.

Spawn parallel AI subagents in isolated git worktrees to compete on tasks like code optimization, refactoring, test writing, or bug fixing. Evaluate results using pytest metrics or LLM judging on git diffs, rank agents, and merge the top performer into your base branch.

Perform product market research workflows: generate user personas, behavioral segments, and customer journey maps from surveys, CSVs, or feedback; conduct competitive landscape analysis with competitor profiles and differentiation maps; run sentiment analysis on reviews for insights and recommendations; estimate TAM/SAM/SOM with growth projections; output markdown reports.

Perform AI-powered code reviews on GitHub and GitLab pull requests by connecting to Greptile API. View and resolve review comments directly within Claude Code. Query indexed repositories for code search, codebase Q&A, and context retrieval to accelerate development workflows.

Launch GPU/TPU clusters, training jobs, and inference servers across 25+ clouds using SkyPilot. Deploy to Kubernetes pods and Slurm jobs; debug YAML configs and optimize costs in your AI workflow.

Build AI agents that generate and interact with React UI components using Tambo: auto-integrate into existing React/Next.js/Vite apps by detecting stack, installing packages, wiring providers, and adding chat UI; or CLI-scaffold new generative UI apps with starter components and schemas.

Run structured product management processes from discovery and strategy through roadmap and PRD generation, with skills for user research, prioritization, financial analysis, AI maturity assessment, and career leadership transitions.

Look up Python code examples and enforce Pythonic style — fetch syntax, concurrency, ML, and HPC references from pythonsheets.com while writing, debugging, or optimizing code, and get linting guidance for readable, idiomatic Python.

Build and debug streaming AI agents with the AG-UI .NET SDK: create agents with tools, state, multimodal messages, human-in-the-loop approvals, reasoning traces, and protobuf transport, plus diagnose common runtime issues.

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.

Semi-automated research assistant for academic literature review, paper writing, and project knowledge management. Integrates with Zotero and Obsidian to search papers, extract writing patterns, generate structured manuscripts, manage citations, and produce conference materials. Also includes general-purpose development tools for code quality, debugging, Git workflows, and project scaffolding.

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.

Invoke /deploy to initiate TensorZero deployment workflow, which prompts plugin upgrade before unlocking full deployment capabilities for AI/ML applications.

Run 10 AI agents to fully automate Obsidian vault management: triage Gmail/Hey emails and inbox notes, extract deadlines from Google Calendar, transcribe audio into structured notes, audit and defragment vault structure, generate weekly agendas, evolve knowledge graph, and handle multilingual inputs.

Leverage Common Room's product usage, engagement, and intent signals as a GTM copilot to research accounts and contacts, generate call prep briefs with talking points and objections, draft personalized email/LinkedIn/call outreach, build targeted prospect lists, produce weekly meeting briefings, and create strategic account plans.

Quickly pack local or remote GitHub repositories into AI-optimized formats (XML, Markdown, JSON, plain) with compression, file filters, git diffs/logs, and clipboard copy using simple slash commands.

Triages and classifies AI use cases against your governance registry, runs structured impact assessments across regulatory regimes, reviews vendor AI terms for data training and liability risks, monitors policy drift, and drafts updated usage policies — all while connecting to Slack, Google Drive, and Lexis+ Protégé for research and collaboration.

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.

Automate long-form webnovel creation: initialize projects interactively with genre/characters/worldbuilding/outlines, generate beat sheets/chapters (2000+ words), extract entities/relationships to SQLite indexes, visualize status/entity graphs in read-only dashboard, recover interrupted workflows, and validate chapters via agents for inconsistencies, pacing, OOC, reader pull, and quality reports.

Build and orchestrate advanced Claude Code agentic workflows by creating meta-prompts, subagents, hooks, MCP servers, slash commands, and skills; execute hierarchical plans, run autonomous coding loops, apply expert debugging and productivity frameworks like 5 Whys or Eisenhower Matrix, and audit components for compliance and quality.

Track real-time prices for cryptocurrencies, stocks, forex, and commodities from multiple exchange APIs and WebSockets. Set watchlists and alerts, export data to CSV/JSON, analyze trends with technical indicators, volume, patterns, and generate trading signals, forecasts, and recommendations.

Scaffold, build, evaluate, deploy, publish, and monitor AI agents on Google Cloud using the Google ADK Python SDK.

Build and configure neural network architectures like CNNs and RNNs for ML tasks such as image classification and text generation. Generate PyTorch code with validation and error handling, get metrics and insights, save artifacts, and produce documentation.

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.

Generate AI videos from text prompts or images using Kling AI API in Python. Build scalable production pipelines with async Redis queues, batch processing, rate limiting, webhooks, monitoring, cost controls, content filters, security audits, cloud storage uploads, and CI/CD integration.

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.

Write Markdown contracts (.prose.md) that orchestrate multi-agent AI workflows, compile and validate them, then execute them in a virtual machine with session, parallel, loop, and conditional support — all with an auditable trace.

Manage Google Ads and Meta Ads campaigns, run SEO audits, optimize content for AI search engines (GEO), and generate schema markup — all from Claude. Includes keyword research, broken link scanning, landing page scoring, and content calendar planning powered by Google Search Console and advertising APIs.

Run end-to-end YouTube content strategy workflows: research competitors via channel scraping and analysis, generate tiered video ideas with validation, produce structured briefs and detailed outlines including demo prep, craft CTR-optimized titles and thumbnail concepts.

Automate training and optimization of ML models for classification and regression on datasets: analyze data, select/configure algorithms, cross-validate, evaluate metrics, generate Python code using scikit-learn/PyTorch/TensorFlow/XGBoost, and save artifacts.

Set up Ollama for local AI model inference on macOS, Linux, or Docker with automated installation, hardware-optimized model selection, GPU configuration, verification, model pulls, API testing, and client integration via Python, Node.js, or REST for zero-cost, privacy-first LLM workflows.

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。

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.

Generate production-ready Google Cloud code examples, starter kits, and templates for AI agents and apps from official ADK, Genkit, and Vertex AI sources. Adapt to Python, TypeScript, or Go with security, monitoring, Firebase, and Terraform IaC integration.

Generate BUY/SELL trading signals for cryptocurrencies and stocks using technical indicators like RSI, MACD, and Bollinger Bands. Scan and rank watchlist opportunities with confidence scores, stop-loss/take-profit levels, multi-timeframe analysis, and markdown reports including risk guidance.

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.

Track real-time crypto derivatives markets—futures, options, perpetuals—with funding rates, open interest, liquidations, IV, Greeks, and basis across Binance, Bybit, Deribit using Python CLI tools, and use an AI agent to analyze data and generate trading signals.

Build, debug, optimize, secure, and deploy FireCrawl web scraping pipelines for LLM/RAG data ingestion: scrape/crawl sites to markdown/JSON, extract structured data, handle rate limits/errors, add monitoring/observability, scale with backoff/caching, and integrate into Node/Python apps from dev to production.

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

Generate and execute automated Python pipelines for data cleaning, transformation, validation, and ETL in ML workflows. Analyze context to produce AI/ML code with built-in validation, error handling, performance metrics, saved artifacts, and documentation.

Generate and run Python code to analyze images via computer vision, performing object detection, classification, and segmentation. Handles validation, errors, performance metrics, saves outputs as artifacts, and adds documentation. Trigger with 'analyze image' prompts or process-vision command.

Aggregate cryptocurrency news from 50+ RSS sources with coin, category, and time filters, relevance scoring, AI sentiment analysis, trend detection, and market impact scoring to monitor market updates, announcements, and gain real-time trading insights.

Automate full Databricks lakehouse lifecycle: build Delta Lake ETL pipelines with medallion architecture and Auto Loader, engineer ML workflows via MLflow and Feature Store, deploy jobs/pipelines with Asset Bundles and GitHub Actions CI/CD, secure via Unity Catalog RBAC, optimize costs/performance, troubleshoot errors, and monitor with system tables.

Generate plots, charts, and graphs from data via natural language requests—AI analyzes datasets, selects optimal visualization types, produces validated Python code, delivers performance metrics and insights, saves artifacts, and creates documentation.

Automate machine learning feature engineering by generating and executing validated Python code to create interactions, scale data, encode categoricals, select features via importance analysis, compute metrics, save artifacts, and generate documentation.

Set up OpenRAG locally by assessing your environment, generating requirements and Docker/uvx configs, and verifying services at localhost:3000 and :5001/docs. Then integrate its SDK into Python or JavaScript/TypeScript apps via pip/npm/uv/yarn, configure env vars/API keys, and implement chat/search clients with code examples.

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.

Build production Python applications on Azure using SDK best practices for AI agents and ML pipelines, content analysis and multimodal processing, vector/hybrid search, hierarchical storage and queues, event streaming with Event Hubs and Service Bus, OpenTelemetry monitoring, secure authentication and key management, plus infrastructure provisioning.

Validate AI/ML models and datasets for bias, fairness, and ethics using Fairlearn, AIF360 metrics, four-fifths rule, and severity classification. Generate production-ready AI/ML code with integrated validation, error handling, metrics, artifacts, and documentation tailored to modern frameworks.

Evaluate machine learning models using metrics like accuracy, precision, recall, and F1-score to perform performance analysis, validation, model comparison, and optimization. Generate production-ready AI/ML code that includes validation, error handling, performance metrics, saved artifacts, and documentation.

Perform NLP analysis on text, code, or data to detect sentiment, extract keywords and named entities, and model topics. Generate production-ready AI/ML code from natural language requirements, complete with validation, error handling, performance metrics, insights, artifacts, and documentation.

Build and evaluate supervised classification models from labeled data for tasks like spam detection or churn prediction. Generates complete Python code including training, validation, error handling, performance metrics, artifacts, and documentation.

Forecast future values from historical time series data using ARIMA and Prophet models, including trend, seasonality, and autocorrelation analysis with confidence intervals. Generate validated AI/ML code for forecasting tasks complete with error handling, performance metrics, insights, artifacts, and documentation.

Access Z.AI's multimodal AI capabilities directly from your CLI to analyze images and videos with vision models, perform OCR and UI-to-code conversion, search the web, extract pages as markdown, and explore GitHub repositories deeply. Requires Z_AI_API_KEY for seamless terminal-based workflows.

Run an AI product manager workflow: design ethical AI reviews, structure product canvases for ML features, transform PRDs into design briefs for Figma, set up statistically rigorous A/B experiments, and synthesize multi-source user signals into actionable insight briefs.

Create and validate production-grade Claude Code skills per AgentSkills.io 2026 spec and 100-point rubric, plus Anthropic agent .md files matching 16-field 2026 standard. Audit existing skills/agents or build custom subagents for orchestrators and marketplace submission.

Fetch OpenSea NFT metadata to compute rarity scores using algorithms like rarity_score or entropy, rank individual tokens, compare collections, and generate markdown reports with trait breakdowns, valuation estimates, and market insights.

Analyze cryptocurrency market sentiment by pulling data from social media, news, on-chain metrics, derivatives, whale activity, and Fear & Greed Index to generate 0-100 mood scores, weighted insights, and predictions for overall market or specific coins like BTC.

Deploy and orchestrate production multi-agent systems on Vertex AI using ADK and A2A protocol: discover agent capabilities via AgentCard, submit tasks with JSON-RPC over HTTP, manage sessions and code execution sandboxes, share state via Memory Bank, poll status, and retrieve results with artifacts.

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.

Generate production Mistral AI code and configs in Claude Code for SDK setup/auth, chat completions/embeddings/RAG pipelines, error debugging/rate limits, security hardening/compliance, CI/CD testing with Vitest/GitHub Actions, Vercel/Docker/K8s deployment, cost/performance optimization, observability, and OpenAI migrations in TypeScript/Node/Python.