← all publishers

aselimc

@aselimc source repo

60 published skills

  1. Experiment Tracking · aselimc
    Track ML experiments with W&B or MLflow. Log hyperparams, metrics, artifacts, and system metrics.
    1 install
  2. Model Serving Infra · aselimc
    Production model serving. Triton, TorchServe, BentoML. Dynamic batching, autoscaling, health checks.
    1 install
  3. Sim To Real Transfer · aselimc
    Bridge simulation to real hardware. Domain randomization, system ID, hardware abstraction.
    1 install
  4. Architecture Diagrams · aselimc
    Generate Mermaid diagrams for system architecture, data flows, class hierarchies, and API sequences.
    1 install
  5. Hyperparameter Search · aselimc
    Systematic hyperparameter optimization with Optuna. Bayesian search with pruning.
    1 install
  6. Quantization Pipeline · aselimc
    Model quantization for deployment. PTQ, QAT, INT8/FP16/INT4, hardware-specific calibration.
    1 install
  7. Code Quality Standards · aselimc
    Org-wide code quality standards for linting, formatting, type safety, and error handling.
    1 install
  8. Infrastructure As Code · aselimc
    Terraform modules, state management, environment separation, cloud provisioning.
    1 install
  9. Sensor Fusion Pipeline · aselimc
    Multi-sensor fusion. EKF/UKF state estimation, camera-LiDAR-IMU calibration, point cloud registration.
    1 install
  10. Motion Planning Control · aselimc
    Motion planning and control. MoveIt2, Nav2, trajectory optimization, PID/MPC, ros2_control.
    1 install
  11. Monitoring Observability · aselimc
    Three pillars of observability. Metrics (Prometheus), logs (structured), traces (OpenTelemetry).
    1 install
  12. Pytorch Training Pipeline · aselimc
    Standard PyTorch training patterns with AMP, DDP, checkpointing, and best practices.
    1 install
  13. High Performance Computing · aselimc
    Performance optimization. Vectorization, memory layout, GPU acceleration, profiling, parallelism.
    1 install
  14. World Model Implementation · aselimc
    Learned dynamics models for prediction and planning. RSSM, JEPA, Dreamer, imagination-based RL.
    1 install
  15. Rl Algorithm Implementation · aselimc
    Implement RL algorithms (PPO, SAC, TD3) with proper numerical stability and vectorized envs.
    1 install
  16. Self Supervised Pretraining · aselimc
    Self-supervised visual representation learning. Contrastive, masked, distillation, and JEPA methods.
    1 install
  17. Data Augmentation Strategies · aselimc
    Domain-appropriate data augmentation for CV, robotics, and NLP pipelines.
    1 install
  18. Model Export And Optimization · aselimc
    Export PyTorch models to ONNX/TensorRT for production deployment. Validate numerical equivalence.
    1 install
  19. Containerization Orchestration · aselimc
    Docker multi-stage builds, docker-compose, Kubernetes manifests, Helm, GPU support.
    1 install
  20. Detection Segmentation Pipeline · aselimc
    Object detection and segmentation pipelines. COCO/VOC formats, DETR/YOLO/Mask2Former, mAP/mIoU evaluation.
    1 install
  21. Frontend Component Architecture · aselimc
    Frontend component design. State management, routing, accessibility, responsive design, performance.
    1 install
  22. Read Arxiv Paper · aselimc
    Use this skill when when asked to read an arxiv paper given an arxiv URL
    1 install
  23. Ros2 Development · aselimc
    Idiomatic ROS2 development. Lifecycle nodes, QoS, launch files, TF2, custom messages.
    1 install
  24. Config Management · aselimc
    Config-driven design patterns. No hardcoded values in business logic.
    1 install
  25. Database Patterns · aselimc
    Database design. Schema normalization, indexing, migrations, query optimization. SQL and NoSQL.
    1 install
  26. Numerical Methods · aselimc
    Numerical solvers. ODE/PDE, FEM, sparse linear algebra, stability analysis.
    1 install
  27. Proposal Reviewer · aselimc
    Review technical project proposals for quality, overpromises, legal risk, and internal consistency. Use when the user asks to review, check, evaluate, or critique a project proposal, grant proposal, or any section thereof. Also use when asked to find overpromises, check for legally binding language, verify consistency between sections (objectives vs work packages vs deliverables vs budget), or assess proposal readiness for submission. Accepts proposals as docx, pdf, or plain text input.
    1 install
  28. Pytorch Lightning · aselimc bundle
    Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
    1 install
  29. Environment Design · aselimc
    RL environment design. Gymnasium API, vectorized envs, observation/action spaces, curriculum.
    1 install
  30. Physics Simulation · aselimc
    Physics engine patterns. Rigid body dynamics, collision detection, constraint solvers, determinism.
    1 install
  31. Prompt Engineering · aselimc
    Systematic prompt design. Structured output, few-shot, chain-of-thought, and anti-patterns.
    1 install
  32. Read Software Docs · aselimc bundle
    Read and navigate software package documentation websites. Use when the user provides a documentation URL and wants to understand an API, SDK, framework, or library. Triggers on requests like "read the docs at [url]", "look up [topic] in the [package] documentation", "what does [API] do according to the docs", or any task requiring fetching and comprehending online software documentation. Supports any HTML-based documentation site including Sphinx, Doxygen, ReadTheDocs, MkDocs, and custom doc sites. Common targets include NVIDIA Isaac Sim, Omniverse Kit, OpenUSD, ROS 2, PyTorch, and similar software packages.
    1 install
  33. Rendering Pipeline · aselimc
    Rendering for simulation and synthetic data. PBR, domain randomization, depth/mask rendering.
    1 install
  34. Reward Engineering · aselimc
    Design reward functions. Dense shaping, normalization, curriculum, and common pitfalls.
    1 install
  35. Secrets Management · aselimc
    Secrets handling. Never hardcode. Vault, env vars, rotation, leak detection.
    1 install
  36. Structured Logging · aselimc
    JSON-structured logging with consistent fields and correlation IDs across services.
    1 install
  37. Citation Management · aselimc bundle
    Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
    1 install
  38. Dependency Security · aselimc
    Dependency auditing. CVE scanning, SBOM, lock files, container image scanning.
    1 install
  39. PPTX · aselimc bundle
    Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
    1 install
  40. XLSX · aselimc bundle
    Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
    2 installs
  41. API Design · aselimc
    REST and GraphQL API design. OpenAPI specs, error handling, pagination, versioning.
    1 install
  42. Matplotlib · aselimc bundle
    Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.
    1 install
  43. Ml Testing · aselimc
    ML-specific testing. Shape validation, gradient flow, convergence sanity, data pipeline determinism.
    1 install
  44. LLM Serving · aselimc
    Deploy LLMs for inference. vLLM, TGI, quantization for serving, OpenAI-compatible APIs.
    1 install
  45. Git Workflow · aselimc
    Standard git workflow conventions for branching, commits, and PRs. Apply to all code changes.
    1 install
  46. RAG Pipeline · aselimc
    Retrieval-Augmented Generation. Chunking, embedding, vector stores, retrieval, and generation.
    1 install
  47. Scikit Learn · aselimc bundle
    Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
    1 install
  48. Test Pyramid · aselimc
    Balanced testing pyramid. Unit, integration, E2E tests. Coverage thresholds, fixture patterns.
    1 install
  49. Transformers · aselimc bundle
    This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
    1 install
  50. 3d Perception · aselimc
    3D vision pipelines. Point clouds, depth estimation, 3D reconstruction, pose estimation, scene understanding.
    1 install
  51. Auth Patterns · aselimc
    Authentication and authorization. OAuth2, JWT, session management, RBAC/ABAC.
    1 install
  52. Paper Writing · aselimc
    Academic paper writing. LaTeX, conference templates, experiment tables, rebuttals, contribution positioning.
    2 installs
  53. CI CD Pipeline · aselimc
    CI/CD pipeline design. Lint, test, build, scan, deploy with environment promotion and rollbacks.
    1 install
  54. LLM Finetuning · aselimc
    Fine-tune LLMs with LoRA/QLoRA, instruction tuning, and alignment (DPO/ORPO).
    2 installs
  55. Edge Deployment · aselimc
    Deploy ML models on edge hardware. Runtime selection, containerized edge, OTA updates, MQTT telemetry.
    1 install
  56. Proposal Writer · aselimc bundle
    Write technical project proposals or specific sections of proposals for research grants, technology development, and innovation projects. Use when the user asks to write, draft, or create a project proposal, grant proposal, research proposal, technical proposal, or any section thereof (e.g., abstract, objectives, methodology, work packages, budget justification, impact statement, Gantt chart). Also triggers on requests mentioning proposal-related terms like 'deliverables', 'milestones', 'work plan', 'state of the art', or 'expected outcomes'. Supports EU Horizon, NSF, TUBITAK, ERC, and generic proposal formats. Outputs via docx or pdf skills. Does NOT handle market research reports or business plans.
    1 install
  57. Threat Modeling · aselimc
    STRIDE threat modeling. Attack surfaces, trust boundaries, severity ratings, ML-specific threats.
    1 install
  58. Dataset Pipeline · aselimc
    PyTorch Dataset/DataLoader patterns for efficient, reproducible data loading and augmentation.
    1 install
  59. PDF · aselimc bundle
    Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
    1 install
  60. DOCX · aselimc bundle
    Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
    1 install