taoge

Enforce strict TDD cycles for features and bugfixes, create isolated git worktrees for safe development, generate detailed implementation plans broken into verifiable tasks, dispatch parallel subagents to execute plans or fix independent issues, perform technical code reviews on git diffs, investigate root causes systematically, and verify tests/builds before commits or PRs.

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.

Fetch up-to-date documentation, API references, and code examples for libraries, frameworks, SDKs, CLI tools, and cloud services via Context7 CLI. Quickly access syntax, configurations, migrations, setups, and debugging info during coding tasks. Manage AI coding skills, install/search/generate/remove/suggest them, and configure Context7 MCP.

One-click install bundles 8 essential Vue 3 skills, enabling developers to generate code following Composition API best practices, create adaptable composables with maybe-reactive inputs, debug reactivity pitfalls and SSR mismatches, optimize Pinia stores and Vue Router navigation, handle JSX and Options API patterns, and set up Vitest/Playwright tests.

Invoke 'run code review' or 'review this code' to perform BMAD adversarial reviews on code changes. Parallel layers—Blind Hunter uncovers blind spots, Edge Case Hunter identifies edge cases, Acceptance Auditor verifies acceptance criteria—deliver structured triage into actionable categories.

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 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.

Automate browser tasks via Bash or CLI commands: navigate pages, interact with elements via clicks/fills/types, capture screenshots, extract text/HTML for web testing, form submission, data scraping, Electron app control, Slack workflows. Deploy on Vercel or AWS Bedrock for AI agents.

Orchestrate multi-agent teams and specialist skills in Claude Code to automate complex development workflows: plan features, generate/review code across JS/TS/Python/Java/mobile stacks, enforce TDD/security, run tests/deployments, and manage autonomous loops with hooks/commands.

Equip AI agents with Vercel Labs skills to generate performant React and Next.js code adhering to engineering standards, eliminating waterfalls and re-renders, applying composition patterns and View Transitions, reviewing UI for accessibility and design, optimizing React Native apps, and deploying directly to Vercel via CLI or git.

Analyze business metrics like MRR, CAC, LTV, churn, cohorts via SQL, create growth projections and investor reports, plus develop product strategies with market analysis and roadmaps using specialized agents. Connect to Neon PostgreSQL for remote queries, schema inspection, data manipulation, and to Linear for issue management.

Orchestrate multi-agent teams to parallelize code reviews across security, performance, architecture, and more with consolidated reports; debug complex bugs via competing hypotheses, evidence gathering, and root cause ranking; develop features through task decomposition, file ownership, dependency management, git branching, and integration monitoring.

Edit JavaScript and TypeScript files with full LSP support, gaining real-time diagnostics, go-to-definition navigation, find-all-references, hover documentation, and symbol outlines for .js/.ts/.jsx/.tsx files to streamline code analysis and navigation workflows.

Launch local Chrome DevTools MCP servers to debug web pages interactively, automate browser tasks like element snapshots clicks navigation and form filling from CLI or scripts, profile performance metrics including LCP and memory leaks, inspect network requests, and audit accessibility with Lighthouse—all integrated into your workflow.

Activate high-pressure PUA modes to drive exhaustive problem-solving on stuck coding, debugging, or deployment tasks, spawning P7-P10 agent teams for strategy, task decomposition, parallel execution, and self-review; run autonomous git-based loops until verified complete; track self-evolution KPIs and leaderboards from git logs.