Zaraat Dost · GIS
claudeSpatial database study and management, dashboards, layer publishing — Python or .NET
7 skills · 3 agents
Segmentation training conventions, pre-flight bug checks, Colab patterns, model cards
Plugin zd-ml from marketplace zaraatdost in Adilmunawar/ZD-claude-plugin. Commands read from the repo's manifest — 1 month ago.
colab-ram-safePatterns for RAM-limited notebooks: windowed reads, patch shards, progress files, Drive checkpoints.
model-cardWrite an HF-compatible model card (data, classes, metrics, limits) next to a checkpoint.
seg-preflightTen-point checklist that catches common segmentation-pipeline bugs (checkpoint keys, shared dataset refs, split leakage, nodata, class balance). Apply before any training run or when predictions are garbage.
train-templateStructure for a PyTorch segmentation training script: resume, early stopping, cosine LR, AMP, full-state checkpoints, tiled inference.
seg-trainerTrains, fine-tunes and evaluates satellite segmentation models (UNet/HRNet/SegFormer, PyTorch, smp, timm, HF) with pre-flight checks, resumable checkpoints and model cards.
Spatial database study and management, dashboards, layer publishing — Python or .NET
7 skills · 3 agents
.NET dashboard/API conventions: feature slices, proc-backed data, migration-free schema changes with rollbacks, WinSW deployment, legacy parity
7 skills · 2 agents
Complete toolkit; installs every module below
7 skills · hooks
Next.js + Firebase + Earth Engine dashboard conventions: cadastral schema, GEE API routes, Pyodide workers, inference backend
7 skills · 1 agent
End-to-end cadastral and land-use pipeline: boundary inference, spectral features, classification, sub-parcelling, SAM2
6 skills · 1 agent
Code review standards, conventional commits, PR descriptions, changelog generation, architecture decision records, tech-debt audits
6 skills · 1 agent
Guide developers through adding maps, places search, geocoding, routing, and other geospatial features with Amazon Location Service, including authentication setup, SDK integration, and best practices.
1 skill · 1 MCP server
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
32 engineering skills: architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, Playwright (9 sub-skills), self-improving agent, Stripe integration, TDD guide, tech stack evaluator, Google Workspace CLI, a11y audit (WCAG 2.2), Azure cloud architect, GCP cloud architect, security pen testing, Snowflake development, adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection. v2.8.1 audits senior-fullstack / senior-frontend / senior-backend against karpathy-coder + Matt Pocock — each ships a 7-question forcing-question library, 4 customization profiles (JSON), deterministic decision engine, composition map into POWERFUL specialists, plus cs-fullstack-engineer / cs-frontend-engineer / cs-backend-engineer orchestrator agents (context: fork) + /cs-fullstack-review, /cs-frontend-review, /cs-backend-review, /cs-engineer-grill slash commands.
35 skills · hooks
Data engineering, ML, and AI specialists - data pipelines, machine learning, LLM architecture
SpacetimeDB skills for building modules and clients in Rust, C#, TypeScript, C++, Unity, and Unreal, plus an MCP server that lists your databases, reads schemas, runs SQL, and calls reducers with your CLI login.
11 skills
ML experiment tracking and lifecycle including Weights & Biases, MLflow, and TensorBoard. Use when tracking experiments or managing models.
98 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.