omer-metin/skills-for-antigravity
Overview
This skill provides comprehensive patterns and practical implementations for AI-powered document understanding: PDF parsing, OCR, invoice and receipt extraction, table extraction, multimodal retrieval-augmented generation (RAG) with vision models, and structured data output. It focuses on repeatable patterns that produce validated, machine-readable outputs suitable for downstream workflows. Use it when you need robust, auditable document parsing and extraction pipelines.
How this skill works
The skill prescribes concrete patterns for ingestion, OCR, layout analysis, entity and table extraction, and normalization into structured schemas. It ties each pattern to reference guidance: follow references/patterns.md for construction, references/sharp_edges.md for risks and failure modes, and references/validations.md for strict output constraints and validation rules. Implementations combine OCR engines, layout parsers, LLMs (for interpretation and RAG), and post-processing to ensure deterministic structured outputs.
When to use it
- Parsing and extracting structured data from PDFs, scans, and images (invoices, receipts, contracts).
- Performing robust table extraction from complex layouts for analytics or ETL ingestion.
- Building multimodal RAG systems that combine vision models with LLMs for context-aware document QA.
- Converting heterogeneous document outputs into validated JSON/CSV for downstream systems.
- Diagnosing recurring extraction failures or reducing OCR/interpretation error rates.
Best practices
- Start from references/patterns.md to select the appropriate ingestion and parsing pattern before coding.
- Validate every extraction against references/validations.md rules and surface schema mismatches early.
- Use the failure modes in references/sharp_edges.md to design prechecks and fallback strategies.
- Separate OCR/layout stages from LLM interpretation to limit hallucination and improve traceability.
- Normalize outputs (dates, currencies, addresses) to canonical formats and keep raw text for audit.
Example use cases
- Invoice processing: OCR + table extraction + entity normalization to produce AP-ready JSON.
- Receipt capture for expense workflows: photo ingest, OCR, merchant/date/amount extraction, validation.
- Contract clause extraction: layout parsing + sentence-level QA via multimodal RAG to populate contract database.
- Tabular data pipeline: extract complex tables from financial reports into analytic-ready CSV/Parquet.
- Document QA assistant: combine vision models and RAG for user questions over scanned manuals or reports.
FAQ
Use references/patterns.md for design patterns, references/sharp_edges.md to understand common failures and risks, and references/validations.md to enforce output rules and schema validation.
How do I reduce hallucinations from LLM-based interpretation?
Keep LLMs focused on interpretation only after deterministic OCR/layout steps, provide grounded context, use strict schema prompts, and validate outputs against references/validations.md.
38 skills
This skill helps you extract and structure data from PDFs and documents using OCR, table and invoice parsing, and multimodal vision insights.
This skill helps you design and operate AI-powered marketing workflows that generate, review, approve, and distribute content at scale while preserving brand
This skill helps you optimize Docker images, implement multi-stage builds, and enforce secure, efficient container practices for reliable deployments.
This skill helps you build and maintain an AI-native brand asset system with prompts, references, and governance to ensure consistent outputs.
This skill helps you design immersive, readable game UIs that stay invisible, balance clarity and immersion across devices, and prioritize accessibility.
This skill helps you implement consistent Tailwind CSS patterns, responsive design, and accessible components using a utility-first approach.
This skill helps you elevate AI-generated footage with professional VFX, upscaling, compositing, and color grading using AI-native and traditional workflows.
This skill helps you implement HubSpot CRM integrations using OAuth, objects, associations, and webhooks in Python and Node.js.
This skill helps you enforce secure by design practices across authentication, authorization, encryption, and risk-based defenses for applications and data.
This skill guides you through designing, analyzing, and learning from experiments to embed validated learning and practical significance into product
This skill helps you accelerate cross-platform React Native development with Expo, router navigation, and EAS build strategy for rapid iteration and reliable
This skill helps you excavate and craft compelling brand stories that resonate emotionally, align across touchpoints, and drive action.
This skill helps you develop Godot 4 games efficiently by applying best practices for nodes, signals, resources, and performance.
This skill helps you design and deploy Telegram bots with scalable architecture, natural UX, and monetization strategies.
This skill crafts precise pixel art sprites and tilesets, delivering crisp silhouettes, optimized palettes, and smooth 4-frame animations for retro and indie
This skill delivers persuasive, reader-centered copy across headlines, emails, landing pages, and product messaging to boost engagement and conversions.
This skill helps you craft accurate, actionable developer documentation and tutorials that build trust and accelerate adoption.
This skill helps implement Clerk authentication and multi-tenant patterns with best-practice middleware, user sync, and webhooks across services.
This skill helps you implement Neon serverless Postgres patterns, including branching, connection pooling, and Prisma/Drizzle integration for scalable
This skill helps you design and enforce secure-by-default software through threat modeling, secure coding, and defense-in-depth practices across projects.
This skill helps you build and monetize Roblox games with expert Lua scripting, Studio workflows, and scalable systems for millions of players.
This skill helps you manage infrastructure as code safely by enforcing state discipline, drift detection, and risk-limited changes across Terraform, Pulumi,
This skill helps you build cohesive brand identities by applying proven guidelines for logos, color, typography, voice, and touchpoint consistency.
This skill helps you select and integrate the right Discord bots, platforms, and automation to build a cohesive, scalable community tech stack.
This skill helps you design and debug enterprise knowledge graphs, emphasizing entity resolution, scalable edges, and explainable Cypher queries.
This skill guides enterprise system design using TOGAF, domain-driven design, and governance, mapping capabilities and planning technology transformations.
This skill helps you decide when to delegate or stay hands-on as a founder, maintaining velocity while scaling.
This skill helps you integrate LLMs into game development workflows, enabling rapid prototyping, safer iteration, and aligned human-driven design.
This skill helps you deploy Next.js apps to Vercel efficiently by advising environment strategies, runtime choices, and performance optimizations.
This skill helps you design transformative online courses using backward design, clear outcomes, and scaffolded modules that drive measurable student growth.
This skill helps Unreal Engine developers integrate LLM-powered NPCs and intelligent behaviors without blocking the game thread.
This skill helps you design production-ready Discord bots with Python, covering intents, slash commands, interactions, rate limits, and sharding.
This skill helps you build Telegram Mini Apps with TON integration, leveraging Web App API, crypto payments, and viral UX to monetize.
This skill helps you generate consistent, production-ready AI game assets across sprites, textures, UI, and environments using ComfyUI, Stable Diffusion, and
This skill helps technical teams apply decision-making frameworks to evaluate trade-offs, reversibility, and second-order effects for better engineering
This skill designs and optimizes growth loops to create self-reinforcing systems that compound user acquisition, activation, and retention over time.
This skill orchestrates AI tools into coherent, brand-consistent creative pipelines, enabling scalable production and rapid creative iterations.
This skill helps you perform AI-powered image editing tasks such as inpainting, outpainting, and image-to-image workflows using popular APIs.
