05-deepak-patidar
- 24 skills
- 0 followers
- 4 hours ago last updated
- ▌ Code Quality · 05-deepak-patidarWriting and reviewing maintainable, correct code in any language. Use when writing new modules, reviewing code, refactoring, naming things, handling errors, or when the user says "clean this up", "code quality", "review this", "refactor", "is this good code", or "best practices".
- ▌ System Design · 05-deepak-patidarEnd-to-end system design — scale, caching, queues, async work, consistency, resilience, capacity. Use when designing how a whole product fits together, handling load or growth, adding background jobs/queues/caches/webhooks/real-time features, or when the user says "system design", "scale", "handle more users", "cache", "queue", "async", or "high availability".
- ▌ AI Engineering · 05-deepak-patidarBuilding production features powered by LLMs — model selection, prompt design as engineering, structured output, RAG, evals, cost/latency budgets, and guardrails. Use when adding AI features to a product (chat, extraction, summarization, classification, search), designing prompts that ship to production, building RAG pipelines, or when the user says "LLM feature", "integrate AI", "prompt engineering", "RAG", "embeddings", or "evals".
- ▌ Change Hygiene · 05-deepak-patidarVersion-control and change-flow discipline — commits, branches, pull requests, code review flow, and history that stays useful. Use when committing, branching, opening or reviewing PRs, resolving merge conflicts, planning how a big change lands, or when the user says "commit", "PR", "pull request", "branch strategy", "git workflow", "merge", or "revert".
- ▌ AI Agent Design · 05-deepak-patidarDesigning and building AI agents — tool design, agent loops, context management, permissions/guardrails, memory, multi-agent orchestration, MCP, and agent evaluation. Use when building an agent that takes actions (calls tools/APIs, writes files, automates workflows), designing tool schemas, debugging agent misbehavior, or when the user says "AI agent", "agentic", "tool calling", "function calling", "MCP server", "autonomous", or "multi-agent".
- ▌ Database Design · 05-deepak-patidarSchema design, data modeling, migrations, and query correctness for relational databases (and when to use non-relational). Use when creating or altering tables, designing schemas, writing migrations, modeling money/inventory/ledgers, adding indexes, or when the user says "schema", "data model", "migration", "database design", or "normalize".
- ▌ AI Build Quality · 05-deepak-patidarGetting reliably high-quality software out of ANY AI model (Claude, GPT, Gemini, local models) — task packaging, context, verification, and drift control. Use when delegating coding work to an AI model, writing prompts/specs for AI-driven development, reviewing AI-generated code, setting up CLAUDE.md/AGENTS.md-style project instructions, or when the user says "have the AI build", "prompt for", "why did the model do this wrong", or "AI code review".
- ▌ Testing Strategy · 05-deepak-patidarDeciding what to test, at which level, and how to keep tests trustworthy. Use when writing tests, setting up a test suite, reviewing test coverage, fixing flaky tests, doing TDD, or when the user says "test", "coverage", "unit test", "integration test", "e2e", or "how do I test this".
- ▌ Deployment Safety · 05-deepak-patidarSafe shipping to production on any platform (Render, Vercel, AWS, Docker, bare VM). Use when deploying, releasing, configuring CI/CD, writing Dockerfiles or infra config, running migrations against production, or when the user says "deploy", "release", "go live", "ship", "rollback", or "production".
- ▌ Docs And Runbooks · 05-deepak-patidarDocumentation that survives — READMEs that get someone running, ADRs that preserve decisions, runbooks that work at 2 a.m., and onboarding docs that scale the team. Use when writing or updating any project documentation, setting up a new repo, documenting operations or deploy procedures, capturing a decision, or when the user says "document this", "write a README", "runbook", "onboarding", "ADR", or "nobody knows how this works".
- ▌ Release Readiness · 05-deepak-patidarThe final gate before any launch, major release, or "is this production-ready?" question — orchestrates all engineering-discipline skills into one go/no-go review. Use when the user says "ready to launch", "production ready", "go live checklist", "release", "ship it", "pre-launch review", or before delivering a milestone to real users/clients.
- ▌ Payments And Money · 05-deepak-patidarEngineering money movement — payment integration, ledgers, reconciliation, refunds, billing, and the discipline that prevents losing or double-charging money. Use when integrating a payment gateway (Razorpay, Stripe, PayU, …), recording payments/credits/balances, building billing or subscriptions, handling refunds and disputes, or when the user says "payments", "billing", "checkout", "refund", "reconciliation", "ledger", or "wallet".
- ▌ Product UX Quality · 05-deepak-patidarMaking software feel finished — UI states, forms, mobile, errors users can act on, accessibility, and the polish gap between "works" and "quality product". Use when building any user-facing screen or flow, reviewing UX, handling forms/validation, or when the user says "polish", "UX", "user experience", "looks unfinished", "empty state", "mobile", or "make it production quality".
- ▌ Saas Multi Tenancy · 05-deepak-patidarTenant isolation and lifecycle for multi-tenant SaaS — data scoping that fails closed, tenant context propagation, noisy neighbors, per-tenant operations. Use when building B2B/B2C SaaS with multiple customers on shared infrastructure, adding tenant-scoped tables or features, debugging cross-tenant data leaks, or when the user says "multi-tenant", "tenant isolation", "SaaS", "workspace", "organization data", or "row-level security".
- ▌ API Contract Design · 05-deepak-patidarDesigning HTTP/REST APIs, request/response shapes, error formats, versioning, pagination, idempotency, and webhooks. Use when adding or changing endpoints, integrating a frontend with a backend, designing public or partner APIs, or when the user says "API design", "endpoint", "REST", "contract", "breaking change", or "webhook".
- ▌ Architecture Design · 05-deepak-patidarDesigning module, service, and layer boundaries for applications. Use when starting a new project or feature area, restructuring code, deciding monolith vs services, defining layers (API/service/data), or when the user says "architecture", "structure", "refactor the design", "how should I organize", or "design this system's components".
- ▌ Legacy Code Changes · 05-deepak-patidarMaking safe changes in unfamiliar, undertested, or legacy codebases — comprehension before modification, characterization tests, seams, and incremental replacement. Use when working in a codebase you didn't write, inheriting a project, touching code with no tests, planning a refactor of old code, or when the user says "legacy", "inherited this code", "old codebase", "nobody knows how this works", or "should we rewrite".
- ▌ Requirements To Spec · 05-deepak-patidarTurning vague ideas, feature requests, and client asks into buildable, verifiable specs before any code is written. Use when starting a feature or product, when a request is ambiguous, when scoping an MVP, when writing user stories or acceptance criteria, or when the user says "build me", "I have an idea", "requirements", "spec", "scope", or "what should the MVP include".
- ▌ Root Cause Debugging · 05-deepak-patidarSystematic debugging and incident diagnosis — finding the actual cause instead of patching symptoms. Use when investigating a bug, a production incident, flaky behavior, "works on my machine", data corruption, or when the user says "debug", "why is this happening", "broken", "investigate", "root cause", or pastes an error/stack trace.
- ▌ Dependency Discipline · 05-deepak-patidarChoosing, pinning, upgrading, and auditing third-party dependencies — and supply-chain safety. Use when adding a library or framework, running npm/pip/cargo installs, responding to a CVE or security advisory, upgrading major versions, or when the user says "which library", "add a package", "dependency", "vulnerability alert", "outdated packages", or "supply chain".
- ▌ Threat Model Security · 05-deepak-patidarSecurity-first development and review. Use when building or reviewing auth, sessions, payments, file uploads, user input handling, multi-tenant data access, secrets, APIs exposed to the internet, or when the user says "security", "vulnerability", "harden", "pentest", or before any production launch. Applies to defensive work on systems the user owns.
- ▌ Data Privacy Compliance · 05-deepak-patidarEngineering for personal data — minimization, retention, deletion, subject rights, and compliance basics (GDPR, India DPDP, CCPA-class laws) as buildable requirements. Use when handling user personal data (names, mobiles, emails, addresses, IDs), designing signup/KYC/contact features, adding analytics or third-party trackers, planning data retention or deletion, or when the user says "privacy", "PII", "GDPR", "DPDP", "compliance", "user data", or "right to be forgotten".
- ▌ Observability Readiness · 05-deepak-patidarLogging, metrics, tracing, alerting, and audit trails so production problems are diagnosable from the outside. Use when adding logging, setting up monitoring or alerts, instrumenting a service, preparing for launch, or when the user says "logging", "monitoring", "observability", "alerts", "metrics", "audit trail", or "how do I know if it's working in prod".
- ▌ Performance Improvement · 05-deepak-patidarMeasurement-first performance work — backend latency, database queries, frontend load times, memory, cost. Use when something is slow, when optimizing, before adding caches, or when the user says "performance", "slow", "optimize", "speed up", "latency", "memory", "N+1", or "page load".