Om Shukla's Work | ContraWork by Om Shukla

Om Shukla

Specialized Graphic/Web Designer and Automation expert.

New to Contra

Om is ready for their next project!

Delhi, India

Work Posts About

Delhi, India

Most designers don’t know why their work is bad. They just feel it. So I built AUTOPSY ⚡ Upload a design → It tells you what’s wrong Why it fails How to fix it Then shows the fix + the best version with a cinematic reveal 🎬 Same design. No guessing. Try it: https://app.flora.ai/techniques/autopsy #FLORATechnique

We think products belong to their time. They don’t. They’re just designed that way. So I built WARP ⚡ A system that removes time as a constraint and lets any object exist across eras. One product → Reimagined as an ancient artifact A Bauhaus object A 60s hallucination A cyberpunk machine A 2150 future form Then everything converges into a single cinematic film 🎬 Same object. Different timelines. Completely different meaning. This isn’t about style. It’s about how design adapts — And what happens when it’s pushed beyond its era. Try it: https://app.flora.ai/techniques/warp

I kept noticing the same thing: Different brands. Same visuals. Every category has invisible rules — and most brands follow them without realizing it. So I built DISRUPT ⚡ A system that takes a product and: • Identifies the clichés holding the category back 🔍 • Creates 3 distinct disruption strategies • Translates strategy into actual visuals 🎯 • Places them into real campaign contexts 🏙️ • And brings it all together into a short film 🎬 The goal wasn’t to generate better images. It was to make better creative decisions repeatable. That’s what DISRUPT does. Try it: https://app.flora.ai/techniques/disrupt Built for the FLORA x Contra challenge

🏎️ Infinite synthwave arcade game — in a single HTML file. No models. No textures. No audio. Just pure procedural math ⚡ Neon city, laser combat, and music — all generated in real-time. The world pulses with a custom audio-reactive engine 💥 🔗 https://omma.build/p/advanced-webgl-game-engine-architecture-lwlv9o Play it. Survive the grid. Drop your high score 👇

379

🌌 I built a multiverse simulator that runs entirely in your browser. No assets. No textures. No audio files. Just pure math ⚡ Every planet, star, and even sound is generated in real-time using shaders. Zoom from entire universes → galaxies → down to a single planet surface seamlessly 🪐 Featuring a Gargantua-inspired black hole from Interstellar with real-time gravitational lensing 🕳️ Each click creates a completely new universe. 🔗 https://omma.build/p/omnis-multiverse-space-simulator-build-w2f5a8 Explore it. Break it. Let me know what you find 👇

426

Freelancers lose thousands of dollars every year to scope creep. You say "yes" to a quick favor, and suddenly you're doing hours of unpaid work. 💸 Enter NeuraFlow 🧠 — an autonomous CI/CD pipeline for your freelance contracts. No chatting with AI bots. No manually copying prompts. Just drop a client proposal or change request into your database, change the status to "Pending Signature," and NeuraFlow runs completely in the background to: 🔍 Audit Proposals: Flags dangerous, vague phrases and provides concrete, copy-paste rewrites to protect your boundaries. ⚖️ Guard Your Scope: Compares mid-project requests directly against your original signed SOW. 🛑 Push Back Professionally: Automatically verdicts requests as "Out of Scope" and drafts a diplomatic email with a calculated change order estimate ($). 🚩 Track "Repeat Offenders": Detects clients who constantly ask for free work across multiple projects. ⚡ Fire Real-Time Alerts: Sends instant Gmail & Slack notifications when a high-risk scope threat is detected. Why it's reusable (Build Once, Reuse Forever): NeuraFlow works for any freelancer, agency, or consultant in any industry. A vague scope is a universal threat. ✅ Zero setup per client: The text is the context. Just paste and protect. ✅ Database-driven autonomy: No chat interfaces. Just change a Notion status and walk away. Your profitability, guarded autonomously. 🚀 🔗 Try the Agent: https://www.notion.so/marketplace/custom-agents/neuraflow (https://www.notion.so/marketplace/custom-agents/neuraflow)📁 Duplicate the Database: https://www.notion.so/3338770f9c6d80b4bf6cd11df38527fd?v=3338770f9c6d80fba613000c8957e5f7&source=copy_link

130

That makes total sense. A lot of portfolio platforms like Contra don't support LaTeX rendering, so those equations just end up looking like broken code. Here is the revised version with the math translated into clean, readable plain text so it formats perfectly on the site. AuraOps: The Autonomous Unified Release Authority 🚀🧠 Moving AI from "Assisting Developers" to "Making Production Decisions" Modern CI/CD pipelines are reactive. They lint, test, and warn—but the final decision still depends on a human. As DevOps complexity grows with security risks, compliance requirements, and sustainability concerns, developers are overwhelmed. We asked a simple question: What if the pipeline itself could decide whether code is safe to ship? That idea led to AuraOps—a multi-agent AI system integrated directly into GitLab Merge Requests that doesn’t just analyze code, but actively fixes it, verifies it, and makes the final release decision. 💡 How It Works: The Autonomous Pipeline AuraOps intercepts GitLab webhooks when a Merge Request is opened, extracts the code diff, and triggers a 3-phase autonomous pipeline powered by specialized AI agents. The Execution Flow: Phase 1 (Parallel): Security & Sustainability Analysis Phase 2 (Sequential): Validation & Risk Decision Phase 3 (Parallel): Compliance Checks & Deployment 🤖 The Multi-Agent AI System AuraOps orchestrates several distinct agents to handle the entire lifecycle: SecurityAgent: Detects vulnerabilities (SQLi, XSS, secrets), auto-remediates them by writing and committing patches, and re-validates its own fixes. GreenOpsAgent: Optimizes infrastructure using real-time carbon data and suggests lower-emission deployment regions. ValidationAgent: Runs the GitLab CI/CD pipeline to ensure AI-generated fixes didn’t break functionality, with graceful fallbacks if CI is down. ComplianceAgent: Audits code and deployment against SOC2, GDPR, and HIPAA requirements. DeployAgent: Builds and deploys the application to Google Cloud Run, selecting the greenest, most optimal region. RiskEngine (The Brain): The decision-making core that aggregates all signals into a single release scorecard and outputs a definitive APPROVE or BLOCK. 🧮 The RiskEngine Decision Model To confidently block or approve a release without human input, we engineered a weighted decision model to generate a final confidence score. The core confidence score combines three key weighted metrics: Security Score * Eco (Sustainability) Score * Validation Result The final AI decision function evaluates this combined score against a strict threshold. For example, if the total confidence score is 75% or higher, the release is securely shipped and marked as APPROVE. If it falls below that mark, the system automatically outputs a BLOCK decision to prevent risky deployments. 🧗‍♂️ Engineering Challenges Reliable Auto-Remediation: Detecting issues is easy; safely fixing them is not. We implemented multi-pass revalidation (up to 3 cycles) and auto-commits directly to GitLab. Failure Resilience: Real-world systems fail. We built AuraOps with graceful degradation—handling CI failures by safely skipping them, retrying API rate limits with exponential backoff, and bypassing missing configs without crashing. Sustainability as a Metric: Mapping cloud infrastructure to real-time carbon intensity APIs to quantify exact CO₂ savings. 🚀 The Final Output: The Release Scorecard Instead of overwhelming the developer with logs, AuraOps outputs a clean, aggregated scorecard directly in the MR containing: Security score & vulnerabilities auto-fixed Sustainability index & CO₂ emissions avoided Time saved via automation Final AI Decision + Confidence Percentage 💻 Built With AI Models: Gemini 2.5 Flash | Gemini 3.5 Pro | Claude 3.5 Sonnet Backend & Orchestration: Python | FastAPI | Uvicorn | Node.js | TypeScript Frontend & 3D Vis: React | Three.js (React Three Fiber) | CSS DevOps & Cloud: Docker | GitLab API & Webhooks | GitLab CI | Google Cloud Build | Google Cloud Run Try AuraOps : https://auraops-735853806237.europe-north1.run.app/dashboard

NanoMech: The Real-Time Multimodal AI Trading Assistant 📈🤖 Built for the Gemini Hackathon Traders know that in the market, seconds equal dollars. By the time you switch between your chart, your analysis tools, and your risk calculator, the candle has already moved, and your setup is gone. I wanted to fix this. For the Gemini Hackathon, I built NanoMech—an AI that sits on top of your screen, sees exactly what you see, and gives you a complete trade plan in seconds. No API keys required, and no leaving your chart. 💡 The Solution NanoMech runs as two frameless, transparent overlays on top of any trading platform. It uses Google Gemini 2.5 Flash's multimodal vision capabilities to visually read your screen and deliver instant insights. Overlay 1: Market Analysis Trend: Analyzes bullish/bearish market structure and moving average crossovers. Liquidity: Evaluates order book depth, bid/ask walls, and support/resistance zones. Momentum: Breaks down candlestick patterns, volume behavior, and price velocity. Overlay 2: Trade Setup & Risk Management AI-Extracted Targets: Instantly provides Entry Price, Target Price, and Stop Loss. Live CALC Engine: Calculates Risk Amount ($), Position Size (Units), and Risk-to-Reward (R:R) Ratio. Everything updates live as you type in your desired risk percentage. 🛠️ How It Works (Under the Hood) Vision-to-Text Processing: Captures the screen in real-time using the mss library and sends the raw screenshot to Google Gemini 2.5 Flash via the Google GenAI SDK. Prompt Engineering: Engineered strict structured prompts using [ANALYSIS] and [TRADE] tags to force the LLM to output reliably parseable price data. Regex Extraction: Uses regex to pull the exact Entry, Target, and Stop prices from the AI's response and wire them directly into the local risk calculator. Custom Desktop UI: Built always-on-top transparent overlays using Python's Tkinter, utilizing threading to keep the UI fully responsive during API calls. Hands-Free Scanning: Integrated a global hotkey (Ctrl+A+I) and an Auto Mode that scans the chart every 20 seconds. 🧗‍♂️ Challenges Overcome Structured LLM Outputs: Getting an LLM to consistently return prices in a parseable numeric format is notoriously tricky. We solved this with rigorous prompt engineering and robust fallback handling. Thread-Safe UI: Tkinter isn’t thread-safe. We engineered a solution to route all UI updates through root.after() callbacks from the active analysis thread. UX/UI Friction: Tuning the transparency and colors so the text remains readable across both dark and light chart themes, while ensuring our global hotkeys didn't conflict with native trading platforms. 🚀 What We Learned & What's Next This project proved just how incredibly capable Gemini 2.5 Flash is at visual reasoning. It accurately identified complex candlestick patterns, moving averages, and volume spikes from a raw image alone. The Roadmap for NanoMech: Voice Output: Speaking the trade setup aloud for a 100% hands-free experience. Multi-Monitor Support: Allowing users to select which screen the AI tracks. Cloud Hosting: Running NanoMech as a scalable web service on Google Cloud Run. Trade Logging: Automatically tracking how the AI's setups perform over time. 💻 Built With Python | Google Gemini 2.5 Flash | Google GenAI SDK | Google Cloud | Tkinter | mss | pillow | Regex Ready to try it out? Check out the code and run it yourself: https://github.com/omshukla24/NanoMech

Altus — A Breathing Travel Experience Most travel apps are static itineraries. Altus breathes with your journey. Studied these on Mobbin before designing: • Arc → restrained glassmorphism • Airbnb Luxe → aspirational travel cards • Oura → cinematic, mood-first design No static grids. No cluttered menus. • Cinematic Home → live mood-driven backgrounds • Explore → frosted destination cards • Trips → immersive booking details Cinematic, translucent, alive. Try Altus: https://altus-app--omshukla619.replit.app/ Altus doesn’t just book trips. It immerses you in the destination.

244

Phase — A Circadian Intelligence OS Most wellness apps tell you what happened. Phase tells you what's about to happen. Studied these on Mobbin before designing: • Linear → flawless dark UI, layout • Arc → restrained glassmorphism • Raycast → spotlight-style cards No static scores. No manual logging. • Circadian Arc → live 24hr energy phases • Focus Predictor → auto-schedules peak windows • Rhythm Map → biometric heatmaps Predictive, biological, intentional. Try Phase: https://phase-app--omshukla24.replit.app/ Phase doesn’t track your day. It orchestrates your energy.

215