← all publishers

xhalilbey

@xhalilbey source repo

Report this profile Claim this profile

• 6 skills
• 0 followers
• 12 hours ago last updated

1. ▌
   Agent Builder · xhalilbey bundle

   Design, implement, review, and debug production AI agents with Upsonic, especially local-model workflows using Agent, Task, Direct, StateGraph, Skills, Team, AutonomousAgent, MCP, Ollama, vLLM, or Outlines. Use for agent architecture, prompt and task decomposition, structured outputs, tool selection, avoiding unnecessary multi-agent or MCP complexity, local-model reliability, evaluations, retries, guardrails, and production readiness.
   0 installs
2. ▌
   Nextjs App Router · xhalilbey bundle

   Build, modify, review, or debug production Next.js applications, especially App Router projects using Server Components, Client Components, Server Actions, route handlers, middleware, caching/revalidation, metadata, auth, Supabase, Stripe, webhooks, deployment, or performance work. Use when the user asks about Next.js, React Server Components, Vercel, app directory routing, hydration issues, API routes, SSR/SSG, or full-stack web app implementation.
   0 installs
3. ▌
   Web Security Review · xhalilbey bundle

   Review, design, or implement security-sensitive web, mobile backend, API, auth, database, storage, webhook, payment, Supabase, Next.js, Cloud Run, or agent-tooling changes. Use when Codex touches login/session flows, cookies/JWTs, RLS policies, service-role keys, secrets, file uploads, webhooks, account deletion, user-generated content, rate limits, authorization, privacy, or production data access.
   0 installs
4. ▌
   Onboard · xhalilbey

   Use /onboard for a focused Cursor onboarding flow that learns basic preferences, picks a first goal, and routes the user to the right next action.
   0 installs
5. ▌
   Distributed Systems Investigator · xhalilbey bundle

   Diagnose and verify failures across distributed event pipelines, queues, consumer groups, workers, APIs, databases, vector stores, analytics stores, retries, dead-letter paths, and asynchronous consistency boundaries. Use for Kafka lag, missing events, duplicate processing, out-of-order writes, worker stalls, partial persistence, Supabase/Qdrant/ClickHouse divergence, throughput collapse, backpressure, and end-to-end data-loss investigations.
   0 installs
6. ▌
   Agent Evals And Prompt Governance · xhalilbey bundle

   Design, implement, review, and operate evaluations and release governance for production AI agents and prompts. Use for golden datasets, regression tests, prompt/model/tool versioning, structured-output validation, retrieval grounding, tool-call correctness, memory quality, routing and fallback evaluation, cost/latency budgets, canary releases, rollback gates, and comparing agent versions with reproducible evidence.
   0 installs