Access 50+ UI/UX styles, color palettes, font pairings, guidelines, and charts to plan, build, review, and optimize web and mobile interfaces across React, Next.js, Vue, Svelte, Tailwind, React Native, and Flutter.

Run comprehensive PR reviews with specialized agents that analyze code quality, test coverage, error handling, type design, comments, and code simplification, producing a categorized issues summary with action plan.

Fetch up-to-date, version-specific documentation, API references, and code examples for libraries like React, Next.js, Vue, Prisma, and Supabase directly into your LLM context using Context7 skills, commands, agents, and MCP server. Query via /context7:docs <library> [query] or IDs for precise lookups on setup, usage, and APIs.

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.

Automate SEO content strategy and optimization—from keyword research and article generation to structured data validation and content structure analysis—to improve search rankings.

Orchestrate AI agents with swarm coordination, SPARC methodology workflows, and 40-70+ tools for task automation, code review, and performance optimization — run locally or connect to the cloud-based Flow Nexus platform.

Empowers Claude with full-stack development expertise across multiple languages, frameworks, and cloud platforms, enabling code generation, debugging, architecture design, DevOps automation, testing, security audits, and project management workflows.

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.

Automate multi-agent code reviews on GitHub pull requests, auditing CLAUDE.md files, detecting bugs, analyzing git history and prior PRs, reviewing code comments, and scoring issues by confidence level to prioritize fixes.

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.

Delegates product strategy, legal/licensing, business analysis, project management, UX research, content marketing, customer success, technical sales, technical writing, and WordPress development to specialized AI agents

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.

Automates end-to-end feature development: explores codebase to map dependencies, patterns, and execution paths; designs architectures with blueprints, data flows, and build sequences; implements code changes; reviews for bugs, security vulnerabilities, and quality issues using high-confidence filtering.

Extend Claude Code with a dedicated DevOps team for cloud infrastructure lifecycle management—designing, deploying, securing, and operating production systems across AWS, Azure, and GCP using Kubernetes, Terraform, CI/CD, and SRE practices.

Design, build, and deploy MCP servers for Claude by interrogating your use case to select deployment models like remote HTTP, MCPB, or local stdio, implementing tool patterns with auth, adding interactive UI widgets such as forms, pickers, and dashboards for inline chat rendering, and packaging into standalone Node or Python .mcpb bundles for local distribution without user toolchain.

Fetches up-to-date, version-specific documentation and code examples for any library from source repositories, providing accurate context to reduce AI hallucinations during code generation.

Enforces high-agency, exhaustive problem-solving on AI agents using corporate PUA pressure tactics (P7-P10 engineer roles, PIP rhetoric, mama nagging, tsukkomi) with autonomous iterative development loops, agent team management, KPI tracking, and self-evolution metrics.

Delegate specialized coding tasks to domain-expert subagents for building blockchain DApps and smart contracts, secure fintech payment systems with compliance, Unity-based games with multiplayer networking, scalable IoT edge solutions, native/cross-platform mobile apps, API documentation, quant trading models, and risk management frameworks.

Prompts developers to make meaningful code contributions at decision points during coding sessions, creating an interactive learning environment that mimics a guided tutorial style, initialized via shell scripts.

Produce academic manuscripts, figures, and presentations that meet Nature-journal standards using guided, rule-based workflows for every stage of the publication process.

Automate finance and accounting workflows including journal entries, account reconciliations, financial statement generation, variance analysis, and SOX 404 compliance testing, integrated with Microsoft 365, Slack, Google Calendar, Gmail, and BigQuery for data retrieval and collaboration.

Connect to GitHub Copilot's MCP API to enable AI-powered code completions and assistant features within your development environment.

Analyze codebases using a knowledge graph to trace execution flows, assess change impact, and review pull requests. Index git repos, explore architectures, debug errors, and safely refactor with dry-run previews.

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.

Run engineering workflows — standups, code reviews, architecture decisions, incident response, debugging, and deployment checklists — using Slack, Linear, Jira, GitHub, Notion, PagerDuty, Datadog, and more.

Add DeepEval evaluation loops to AI applications: instrument LLM calls, agents, and RAG pipelines with OpenTelemetry or native tracing, generate datasets, run pytest eval suites, and iterate on failures with Confident AI reporting.

Serve as an adversarial thinking partner for executives: stress-test business plans via pre-mortems and bear-case modeling, prepare for board meetings with key metrics and tough questions, navigate hard decisions using reversibility tests and stakeholder maps, conduct precise post-mortems with 5 Whys, and deploy a devil's advocate agent to uncover plan risks with mitigations.

Generate an explorable HTML report from local Claude Code session transcripts to analyze token usage, cache efficiency, subagent activity, skills applied, and the most expensive prompts.

Analyze team capacity and forecast utilization for quarterly planning, generate change requests with full risk assessment and rollback plans, track SOC 2/ISO 27001/GDPR/HIPAA compliance with audit evidence, document business processes into SOPs with RACI matrices and flowcharts, and evaluate vendors with TCO and risk analysis.

Manage GitLab projects by accessing repositories, creating and reviewing merge requests, monitoring CI/CD pipelines, handling issues, and updating wikis through remote API integration with a personal access token.

Streamlines fund administration and month-end close by automating reconciliation break analysis, accrual schedules, roll-forward tie-outs, and variance commentary — supporting controller — supporting review and audit documentation.

Orchestrate multi-LLM agents (Claude, Gemini, Codex, Ollama) and workflows for end-to-end software development: generate PRDs/specs, design UIs/architectures/databases, code with TDD/debugging, perform reviews/audits/tests, manage DevOps/infra, and automate deliveries via 98 commands/agents.

Generate Playwright tests from specs, components, and user flows; migrate Cypress/Selenium suites; analyze test coverage; diagnose and fix flaky failures; sync results to TestRail; and run cross-browser tests on BrowserStack.

Accelerate early-stage life sciences R&D by searching biomedical literature, clinical trials, drug discovery databases, and preprint repositories; analyze single-cell and genomics data with automated pipelines and lab instrument data conversion.

Launch a local MCP server in your Laravel project using 'php artisan boost:mcp' to enable Claude to execute Artisan commands, generate Eloquent queries and models, configure routes and migrations, and produce framework-specific code through natural language interactions.

Generate complete AI-powered wiki sites from git repositories as dark-mode VitePress static sites with Mermaid diagrams, source citations, hierarchical catalogues, audience-tailored onboarding guides, changelogs, deep research reports, and codebase Q&A. Export to Azure DevOps Wiki or deploy via GitHub Actions to Pages.

Access LSEG (Refinitiv) financial data and analytics to price bonds, analyze yield curves, evaluate FX carry trades and yield curves, value options, and build macro dashboards.

Generate professional financial reports (equity research earnings previews, capital markets briefings, and audience-specific company tear sheets) using S&P Capital IQ data via Kensho's KFinance API, outputting HTML, PowerPoint, and Word documents.

Generate client-facing financial reports, investment proposals, and financial plans; prepare client review materials; analyze portfolio drift and generate tax-aware rebalancing trades; identify tax-loss harvesting opportunities with wash sale tracking.

Automate the private equity deal lifecycle: inbound screening, target discovery with CRM checks and founder outreach, due diligence checklists, financial modeling (IRR/MOIC, unit economics), portfolio monitoring, AI opportunity scanning, and board-ready performance dashboards.

Automate financial analysis workflows: build DCF, LBO, comps, and 3-statement models in Excel/PPT, audit spreadsheets, and connect to financial data APIs for market research and valuation. Supports private equity, investment banking deal execution.

Search Slack channels, summarize discussions, draft announcements, and generate standup updates directly from Claude using the Slack API.

Query Claude, Cursor, or other AI agents for expert GSAP guidance to build performant animations, timelines, ScrollTrigger effects, and plugin integrations in React, Next.js, Vue, Nuxt, Svelte, or vanilla JS, following framework best practices and 60fps optimizations.

Craft production-quality UI for dashboards, admin panels, and SaaS apps by establishing a design system with tokens and patterns, then auditing code against that system for spacing, color, depth, and consistency violations — all within Claude Code.

Build, deploy, and maintain Expo mobile apps with native capabilities—create native modules, integrate SwiftUI/Jetpack Compose, set up API routes, handle upgrades, configure Tailwind styling, and automate CI/CD workflows for app store submissions and update monitoring.

Query official Microsoft docs via MCP server or mslearn CLI to fetch concepts, tutorials, quickstarts, API references, verified code samples, limits, and best practices for Azure, .NET, M365, Windows, and Power Platform. Generate hybrid agent skills with dynamic lookups and troubleshoot SDK errors during coding or debugging.

Automate sell-side M&A workflows: build acquirer universes, draft CIMs and teasers, model accretion/dilution, generate pitch deck slides and financial data packs, and track deal pipelines with milestones and action items.

Invoke to prompt the AI to ask targeted questions clarifying ambiguous coding requests, specifying objectives, scope, constraints, environment, and acceptance criteria before any implementation begins. Ensures precise requirements are gathered explicitly only when needed, improving code accuracy without unnecessary interruptions.

Run AI code reviews on uncommitted changes, branch diffs, or specific commits using OpenAI Codex CLI or Google Gemini CLI. Analyzes git diffs via bash scripts. Launches bundled Codex MCP server as subprocess for direct LLM tool access.

Automate the full PRP workflow: plan features via interactive PRDs, investigate issues, implement with validation loops, review code quality, commit, and create PRs — all with specialized agents and autonomous execution.

Orchestrate self-correcting AI coding workflows with multi-agent teams in parallel git worktrees, persistent FTS5-indexed SQLite research wikis, auto-research loops, quality gates, and multi-LLM councils to decompose large refactors, debug issues, build features, and manage sessions across Node.js, Python, Rust, Go projects.

Persists Claude Code's conversation context across sessions by syncing memory with a Letta agent, enabling the agent to accumulate context and provide guidance based on past interactions.

Annotate codebases with dimensional analysis comments documenting units, dimensions, and decimal scaling. Automatically scan for arithmetic patterns, discover project-specific units, propagate annotations through expressions and functions, and validate consistency to detect mismatches and bugs in DeFi protocols or numerical code.

Develop, deploy, and integrate serverless web scrapers and automation workflows using Apify Actors. Convert existing code, generate output schemas, and scrape data from 15+ platforms for lead generation and analysis.

Draw cryptographically random Tarot card spreads via Bash and Python to interpret context, action, obstacles, and outcomes for guiding decisions on vague or ambiguous coding prompts and planning. Invoke for entropy-driven insights when feeling lucky or prompts lack specificity.

Automatically discover and hierarchically load AGENTS.md files across project directories into Claude's agent context, merging instructions with conflict detection and caching for specialized behaviors without manual setup. Sync all agent contexts into CLAUDE.md under organized sections with backups and summaries.

Tail, filter, and AI-analyze real-time logs from deployment platforms like AWS, Vercel, Kubernetes, Supabase, Docker, Cloudflare, Netlify in your terminal using Gonzo TUI. Automatically detects platforms, generates optimized pipe commands with normalizers, and configures AI for insights.

Generate multi-stage CI/CD pipelines in YAML for GitHub Actions, GitLab CI, Jenkins, and CircleCI. Automate workflows covering linting, testing, Docker image builds/pushes, security scans, and gated deployments to staging/production on Kubernetes.

Multi-agent orchestration system with MCP tools and Claude Code plugin agents. 51 specialized agents for development workflows, code quality, deployment, research, and more.

Generate written legal research reports from Westlaw caselaw, statutes, and administrative decisions with inline linked citations to Westlaw and Practical Law sources.

Manages the full litigation lifecycle — intake, holds, deadlines, privilege logs, demand letters, claim charts, chronologies, depo prep, and brief drafting — with integrations for eDiscovery, court dockets, legal research, and Slack. Adapts to in-house, firm, or solo practice via a configurable practice profile.

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.

Scaffold, develop, evaluate, deploy, publish, and monitor AI agents using Google's ADK, with built-in support for the full agent lifecycle from project creation to production observability.

Manage Google Ads and Meta Ads campaigns, run full SEO audits with keyword research and schema markup, and optimize content for AI search engines (GEO) — all from your editor.

Generate test reports by parsing JUnit XML, Jest JSON, pytest results, and coverage data into Markdown/HTML formats with metrics, failures, slowest tests, trends, and CI annotations. Aggregate results across frameworks for summaries and exports in HTML, PDF, or JSON.

Generate production-ready Kubernetes manifests for Deployments, Services, Ingresses, HPAs, ConfigMaps, and Secrets incorporating best practices like health probes, resource limits, autoscaling, and TLS termination to streamline cluster deployments.

Audit codebases with a security agent that scans for vulnerabilities like SQL injection, XSS, CSRF, auth flaws, insecure dependencies, and secrets; generates severity-rated reports including file locations, explanations, compliance checks, and code fixes with examples.

Track regression tests across code releases by mapping git commits to pytest or Jest tests, tagging markers for suites, flagging coverage gaps, generating pass/fail reports with flaky detection, viewing history, and enforcing runs in CI/CD pipelines.

Generate production-ready GitOps workflows for Kubernetes using ArgoCD or Flux, creating manifests, sync policies, multi-environment promotions, RBAC configurations, notifications, and CI/CD integrations for secure, scalable continuous deployments.

Research and contribute to the Model Context Protocol (MCP) specification by searching GitHub PRs, issues, and discussions across the modelcontextprotocol org using gh CLI and GraphQL with variant terms for prioritization and history dives, plus remote access to official docs, guides, and resources at modelcontextprotocol.io.

Configure VSCode extensions to test APIs with httpYac including auth scripts and CI/CD workflows, monitor multiple dev server ports like Vite and Next.js in real-time, and deploy static sites via SFTP to Nginx servers with secure setups.

Build production .NET backends with Akka.NET actors, Aspire orchestration, EF Core patterns, concurrency primitives, and Kubernetes clustering; run integration tests via TestContainers/Playwright; optimize performance/databases; analyze CRAP scores, benchmarks, and concurrency bugs using 61 skills and 11 agents.

Audit project dependencies for supply chain risks by scanning for single maintainers, unmaintained repositories, low popularity, risky features, and CVEs, enabling focused security audits and threat scoping workflows.

Generate professional Excel financial models including DCF valuations with FCF projections, WACC, sensitivities; LBO analyses with debt schedules, IRR/MOIC; budget vs actual variance reports with waterfalls; and dynamic pivot tables via natural language prompts and auto-invoked skills.

Use AI to generate conventional commit messages from staged Git changes. Analyzes code diffs to classify updates as feat, fix, refactor, chore, or docs, then crafts standardized messages with proper prefixes for consistent Git history, changelogs, and automation compatibility.

Follow NIST SP 800-61 to handle security incidents: classify breaches, preserve evidence, analyze logs using Bash tools on Linux, contain threats, investigate IOCs, eradicate malware, and recover systems. Invoke playbook with 'sir' shortcut for quick response workflow.

Manage environment configurations and secrets across dev/staging/prod deployments using .env files, Kubernetes ConfigMaps/Secrets, and AWS SSM. Audit values, encrypt secrets with sops, validate schemas, detect drift, and run promotion workflows. Generate secure, scalable DevOps setup code for Docker, Kubernetes, Terraform, AWS, and GCP infrastructure.

Build and deploy Vizro dashboards end-to-end via a enforced 2-phase workflow: gather requirements, design layouts and visualizations in YAML specs, implement Python code from examples and schemas, then run Playwright E2E tests with browser automation.

Integrate OpenEvidence medical AI for clinical decision support in healthcare SaaS: run evidence-based queries, drug interactions, DeepConsult syntheses; automate auth setup, rate limiting, caching, RBAC, monitoring, CI/CD pipelines, Docker deploys, and production checklists in TypeScript/Node.js/Python projects.

Verify blockchain smart contracts match specifications from whitepapers, PDFs, Markdown, or URLs, detecting implementation gaps, undocumented behaviors, logic discrepancies, and security issues via structured audits and generating compliance reports.

Integrate GitHub Spec-Kit CLI into a 7-phase constitution-based spec-driven development workflow for features, managing .specify/specs/ directories through Constitution, Specify, Clarify, Plan, Tasks, Analyze, and Implement phases.

Delegate coding tasks to expert AI agents specialized in Python, Go, Rust, Java, JavaScript, PHP, Ruby/Rails, C/C++, SQL, and TypeScript. They proactively write idiomatic code, refactor for performance, implement advanced features like concurrency and generics, add tests with pytest or RSpec, optimize queries/schemas, and handle builds like Cargo.toml or CMake.

Deploy specialized AI agents to synthesize research from academic papers, web sources, and GitHub repos with citations; generate API docs, OpenAPI specs, and SDKs; transcribe, analyze, and optimize podcasts; modernize legacy code across React, Python, Java; build and link knowledge graphs; orchestrate multi-agent pipelines for complex tasks.

Inspect Vertex AI Agent Engine deployments on Google Cloud to validate runtime configuration, agent health, security posture, performance, A2A compliance, and best practices. Generate readiness scores and detailed reports for production validation and monitoring.

Initialize Firestore Admin SDK in Node.js projects with authentication, manage safe CRUD operations batch writes queries schema design data migrations indexes, generate validate production-ready security rules using least privilege and emulator testing, and optimize performance costs.

Engineer production-ready ADK agents and multi-agent systems in Python, Java, or Go, generating clean code structures, unit tests, safe tools, and deployment automation for Vertex AI.

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.

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.

Provision secure GCP infrastructure for Vertex AI ADK and Agent Engine deployments using Terraform. Automate setup of Agent Engine runtime, code execution sandbox, Memory Bank, VPC Service Controls, IAM roles, and networking to enable scalable AI agent workflows.

Provision Terraform infrastructure for Genkit AI apps on Firebase Functions, Cloud Run, or GKE, handling secrets, monitoring dashboards, auto-scaling, and CI/CD pipelines in a single workflow.

Build and deploy production-ready containerized multi-agent systems on Google Cloud using ADK templates. Scaffold Python projects with code structures, CI/CD pipelines, and deployment guides targeting Cloud Run, GKE, or Vertex AI Agent Engine. Get recommendations for architectures, tool contracts, and scaffolds.

Design, implement, and deploy secure Firebase apps with Vertex AI Gemini integration in Cloud Functions for authentication, Firestore, storage, and hosting.

Implement multi-level API caching strategies using Redis for server-side storage, CDNs for edge caching, and HTTP headers for browser control, with TTL settings, tag-based invalidation, cache-aside patterns, and stale-while-revalidate to optimize performance across Node, Python, and Java backends.

Generate complete Xiaohongshu notes automatically, including AI-written content, themed covers, formatted text cards, and optional one-click publishing. Select from 8 layout themes like sketch, neo-brutalism, or botanical, plus 4 smart pagination modes via manual invocation.

Delegate 117 specialized AI agents to handle diverse workflows like code reviews, security audits, API architecture, database optimization, frontend and backend development, cloud infrastructure design, academic research synthesis, performance tuning, testing automation, and deployment orchestration across multiple languages and stacks.

AI-powered toolkit for Tencent CloudBase that automates code audits, documentation generation, git workflows, and skill management—enabling developers to maintain code quality, streamline PRs, and synchronize skills across agent environments.