@veeramanikandanr48

accessibility covers wcag 2.1 aa compliance with semantic html, aria patterns, keyboard navigation, color contrast, and form accessibility. includes 12 preventable issue patterns and working code examples for dialogs and tabs.

agent-development covers claude code agent design with patterns for auto-delegation, tool access control, memory tuning, and prompt structure. focuses on declarative instruction design and self-documenting agents that work across sessions.

spec-miner extracts specifications from legacy codebases through systematic exploration and evidence-based documentation, using dual analytical perspectives (architecture and observable behavior) to map undocumented systems.

portfolio-manager fetches live holdings from alpaca mcp server and performs multi-dimensional portfolio analysis covering allocation, diversification, risk metrics, and position evaluation. generates detailed reports with rebalancing recommendations but lacks concrete decision logic and error handling.

Use when conducting security audits, reviewing code for vulnerabilities, or analyzing infrastructure security. Invoke for SAST scans, penetration testing, DevSecOps practices, cloud security reviews.

Clerk auth with API Keys beta (Dec 2025), Next.js 16 proxy.ts (March 2025 CVE context), API version 2025-11-10 breaking changes, clerkMiddleware() options, webhooks, production considerations (GCP outages), and component reference. Prevents 15 documented errors. Use when: API keys for users/orgs, Next.js 16 middleware filename, troubleshooting JWKS/CSRF/JWT/token-type-mismatch errors, webhook verification, user type inconsistencies, or testing with 424242 OTP.

Use when defining SLIs/SLOs, managing error budgets, or building reliable systems at scale. Invoke for incident management, chaos engineering, toil reduction, capacity planning.

Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with plugins system and hooks for event-driven workflows. Prevents 14 documented errors. Use when: building coding agents, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors, MCP config issues, subagent cleanup.