kumaran-is

kumaran-is/claude-code-onboarding

Skill Claude Code

WCAG 2.1 AA accessibility audit skill for Angular 21.x and Flutter 3.41.x. Use when auditing UI for accessibility compliance, identifying barriers, establishing automated testing, or preparing compliance evidence. Covers axe-core automated scanning, keyboard navigation, screen reader compatibility, color contrast…

kumaran-is/claude-code-onboarding

Skill Claude Code

MUST READ before deploying any ADK agent to Google Cloud — covers Cloud Run, Agent Engine, Vertex AI, event-driven agents, and ADK CI/CD pipelines. Use when deploying ADK agents to production, not for agent code patterns (use google-adk) or project scaffolding.

kumaran-is/claude-code-onboarding

Skill Claude Code

ADK development lifecycle guardrails — 4-phase workflow (Understand → Build → Evaluate → Deploy), import precision rules, GOOGLECLOUDLOCATION debugging, code preservation, and infinite loop breaking. Load BEFORE google-adk when starting a new ADK agent feature.

kumaran-is/claude-code-onboarding

Skill Claude Code

Use when evaluating ADK agents, running adk eval, writing evalsets, configuring eval metrics, or debugging evaluation results. Covers all 8 criteria (tooltrajectoryavgscore, responsematchscore, finalresponsematchv2, rubricbasedfinalresponsequalityv1, rubricbasedtoolusequalityv1, hallucinationsv1, safetyv1…

kumaran-is/claude-code-onboarding

Skill Claude Code

ADK observability, Cloud Trace, prompt logging, agent analytics, BigQuery agent logs, ADK monitoring, ADK telemetry. Use when configuring tracing, logging, or analytics for ADK agents, debugging production agent behavior, or setting up monitoring for a deployed agent.

kumaran-is/claude-code-onboarding

Skill Claude Code

This skill provides coding standards for Python agentic AI services with LangChain/LangGraph. Use when reviewing or writing Python agentic AI code. Covers state management, tool definitions, graph structure, error handling, and observability.

kumaran-is/claude-code-onboarding

Skill Claude Code

This skill provides patterns and templates for building production AI agents with Python 3.14, LangChain v1.2.8, LangGraph v1.0.7, and FastAPI 0.135.2. Use when creating AI agents, RAG systems, graph workflows, tools, memory systems, or agent tests.

kumaran-is/claude-code-onboarding

Skill Claude Code

Run a full AI Playbook audit against an existing agentic application or AI feature. Orchestrates Decision Record reverse-engineering, security review, eval audit, launch check, and consolidated remediation planning in one flow. Use when the user explicitly runs /ai-audit or says "audit my AI app", "verify my agent…

kumaran-is/claude-code-onboarding

Skill Claude Code

AI chat interface patterns for Angular 21.x and Flutter 3.41.x. Use when building streaming chat UI, conversational AI assistants, copilots, token context indicators, feedback loops, multi-modal inputs, tool visualization, or AI-specific error handling. Covers streaming markdown, auto-scroll heuristics, memoized…

kumaran-is/claude-code-onboarding

Skill Claude Code

Fill out the AI Feature Decision Record before building any AI feature. Use when the user explicitly runs /ai-decision-record or asks to "start a new AI feature", "create a decision record", "kick off an AI design", or similar ritual phrasing.

kumaran-is/claude-code-onboarding

Skill Claude Code

Run the AI incident response procedure when something is going wrong in production AI. Use when the user explicitly runs /ai-incident-response or says "AI incident", "model is broken", "production AI is failing", "we're seeing weird outputs in prod", "hallucination in production", or similar urgent phrasing.

kumaran-is/claude-code-onboarding

Skill Claude Code

Run the unified pre-production launch checklist for an AI feature before shipping it. Use when the user explicitly runs /ai-launch-check or asks to "review my AI feature for launch", "is this ready to ship", "pre-production review", or similar ritual phrasing.

kumaran-is/claude-code-onboarding

Skill Claude Code

Production-grade decision framework for building AI features, AI workflows, AI agents, and AI-augmented systems. Use this skill whenever the user is designing, building, debugging, reviewing, or deciding whether to add AI to a system — including any work involving LLM calls, embeddings, RAG, agents, tool use, prompt…

kumaran-is/claude-code-onboarding

Skill Claude Code

Impact-prioritized Angular 21.x best practices — CRITICAL: OnPush+Signals, async waterfalls, bundle optimization. HIGH: rendering performance, SSR hydration. MEDIUM: template optimization, state management. LOW: memory management. Load when reviewing Angular code, writing components, or optimizing performance.

kumaran-is/claude-code-onboarding

Skill Claude Code

Angular 21.x SPA development skill with TailwindCSS 4.x and daisyUI 5.5.5. Use when building Angular standalone components, services, lazy-loaded routes, unit tests, or creating UI with TailwindCSS + daisyUI. Covers component scaffolding, UI/UX design, accessibility audits, and design systems.

kumaran-is/claude-code-onboarding

Skill Claude Code

Angular 21.x UI/UX state patterns — loading states (show only when no data), error hierarchy (inline→toast→banner→full-screen), empty states, button loading, form patterns with validation, dialog/modal patterns. Load when building any Angular UI component that handles async data or user actions.

kumaran-is/claude-code-onboarding

Skill Claude Code

Angular 21.x core patterns and APIs — Signals, Standalone components, Zoneless change detection, SSR/Hydration, Dependency Injection, Component composition, Signal-based state, Testing. Load when writing Angular code for API reference, testing patterns, or SSR configuration.

kumaran-is/claude-code-onboarding

Skill Claude Code

Use before designing any REST API endpoint — covers URL structure, HTTP method semantics, pagination, caching, idempotency, and bulk operations across Python FastAPI, NestJS 11.x, and Spring Boot WebFlux 3.5.x. Complements openapi-spec-generation (spec format) and stack-specific implementation skills (code patterns).

kumaran-is/claude-code-onboarding

Skill Claude Code

Complete App Store Optimization (ASO) toolkit for keyword research, metadata optimization, competitor analysis, A/B test planning, review sentiment analysis, ASO health scoring, and launch readiness for Apple App Store and Google Play Store. Load BEFORE the iOS or Android release workflow to optimize the store…

kumaran-is/claude-code-onboarding

Skill Claude Code

Deep architectural review specialist — assesses system design changes, identifies anti-patterns, evaluates distributed systems compliance, and produces improvement recommendations. Use when reviewing architecture before implementation, assessing microservice boundaries, or evaluating event-driven system design.

kumaran-is/claude-code-onboarding

Skill Claude Code

Structured templates and process for capturing Architecture Decision Records (ADRs) — context, decision, consequences, and status. Use when making any significant or irreversible technical decision (framework selection, API design, database schema, infrastructure choice) to ensure every option considered and trade-off…

kumaran-is/claude-code-onboarding

Skill Claude Code

Full-stack system architecture skill for designing C4 diagrams, API contracts, sequence diagrams, deployment topologies, and ADRs. Use when designing new systems, choosing tech stacks, defining service boundaries, or producing architecture documentation before implementation starts.

kumaran-is/claude-code-onboarding

Skill Claude Code

Guidance for using the asc CLI in App Store Connect automation (flags, output formats, pagination, auth, discovery, timeouts). Use when asked to run or design asc commands, interact with App Store Connect via CLI, set up authentication, configure environment variables, or understand asc output formats. Triggers: "asc…

kumaran-is/claude-code-onboarding

Skill Claude Code

Triage TestFlight crashes, beta feedback, and performance diagnostics using asc CLI. Use when investigating TestFlight crash reports, analyzing beta tester feedback, reviewing performance diagnostics (app hangs, disk writes, launch time), building a crash summary by signature, filtering crashes by device or OS…