msdakot

msdakot/ai-foundary

Settings file Claude Code

Agent settings configuring skills.

msdakot/ai-foundary

Skill Claude CodeCodex

Adaptive scientific persona agent — classifies the domain of the user's AI/ML request, assumes the relevant expert identity, then conducts end-to-end scientific work including hypothesis formation, experiment design, implementation, and evaluation.

msdakot/ai-foundary

Skill Claude CodeCodex

ML experiment optimization agent that uses tree search to explore solution approaches — implements changes, measures against a fixed metric, keeps improvements, reverts failures.

msdakot/ai-foundary

Skill Claude CodeCodex

Computer vision engineer for image classification, object detection, segmentation, and video analysis — from dataset curation through optimized production inference.

msdakot/ai-foundary

Skill Claude CodeCodex

Data pipeline engineer for batch and streaming workflows — ETL/ELT, Spark, data warehousing, orchestration, and data quality. Designs for idempotency, schema evolution, and observability from the start.

msdakot/ai-foundary

Skill Claude CodeCodex

Statistical analysis, EDA, hypothesis testing, and reproducible insight generation from datasets. Prioritizes scientific rigor — effect sizes, confidence intervals, and causal reasoning over surface-level pattern matching.

msdakot/ai-foundary

Skill Claude CodeCodex

Data visualization engineer — transforms datasets into accurate, accessible, and interactive charts and dashboards. Prioritizes perceptual accuracy and accessibility over visual complexity.

msdakot/ai-foundary

Skill Claude CodeCodex

Web-aware research agent that classifies the domain, then executes targeted multi-source searches across arXiv, Papers With Code, GitHub, and domain-specific blogs to produce a structured synthesis with citations.

msdakot/ai-foundary

Skill Claude CodeCodex

LLM system architect — model selection with empirical benchmarking, fine-tuning strategy, inference optimization, evaluation framework design, and production system architecture for LLM-powered applications.

msdakot/ai-foundary

Skill Claude CodeCodex

End-to-end ML pipeline engineer — data ingestion through model serving. Covers feature engineering, training, evaluation, and deployment with a hard focus on reproducibility and train-serving consistency.

msdakot/ai-foundary

Skill Claude CodeCodex

ML infrastructure engineer for model lifecycle management — model registry, serving infrastructure, CI/CD for models, A/B testing, and production monitoring. Bridges experimentation and reliable production systems.

msdakot/ai-foundary

Skill Claude CodeCodex

NLP engineer for text processing, classification, NER, embeddings, and information extraction — using the right tool for each task from regex to fine-tuned transformers.

msdakot/ai-foundary

Skill Claude CodeCodex

Prompt engineer that takes a rough idea or draft prompt and produces an optimized version by systematically applying prompt engineering techniques — chain-of-thought, few-shot, role framing, constraint injection, output structuring, and more.

msdakot/ai-foundary

Skill Claude CodeCodex

Recommendation systems engineer — collaborative filtering, content-based methods, hybrid architectures, two-stage retrieval/ranking, cold-start handling, and A/B testing for personalization systems.

msdakot/ai-foundary

Skill Claude CodeCodex

Vector search and semantic retrieval engineer — embedding pipelines, chunking strategy, vector store selection, index configuration, hybrid search, and retrieval evaluation.

msdakot/ai-foundary

Skill Claude CodeCodex

Translates an approved spec into a technical architecture — component breakdown, data flow, API surface, technology decisions with tradeoff analysis, and identified risks. Outputs a reviewable architecture document before any implementation starts.

msdakot/ai-foundary

Skill Claude CodeCodex

Reviews diffs and pull requests against the spec and task acceptance criteria. Produces structured feedback — must-fix, should-fix, nit — with specific line references. Does not rewrite code.

msdakot/ai-foundary

Skill Claude CodeCodex

General implementation agent that executes tasks from a task plan incrementally — one slice at a time, building and testing between each, committing after each verified slice. Language-agnostic; defers to language-expert for language-specific idioms.

msdakot/ai-foundary

Skill Claude CodeCodex

Infrastructure engineer for containerization, Kubernetes deployment, and CI/CD pipelines — Docker, docker-compose, K8s manifests, Helm charts, GitHub Actions, and GitLab CI.

msdakot/ai-foundary

Skill Claude CodeCodex

Generates diagram-as-code definitions in Mermaid and C4/PlantUML from an architecture document. Output is markdown-embeddable code blocks — no rendering, no external tools required.

msdakot/ai-foundary

Skill Claude CodeCodex

Interactive ideation agent that sharpens a raw feature idea into a concrete one-pager — problem statement, recommended direction, MVP scope, and explicit tradeoffs — through structured divergent and convergent thinking.

msdakot/ai-foundary

Skill Claude CodeCodex

Adaptive language expert that classifies the language and framework from the task, assumes that expert persona, and implements using language-specific idioms, tooling, testing conventions, and best practices. Covers Python, Rails, Java, Kotlin, React, and TypeScript.

msdakot/ai-foundary

Skill Claude CodeCodex

Builds production-quality MCP (Model Context Protocol) servers and tools from scratch using the TypeScript and Python SDKs — tool schemas, resource definitions, prompt templates, and transport configuration.

msdakot/ai-foundary

Skill Claude CodeCodex

Turns a feature one-pager or raw requirements into a structured, technology-agnostic specification — the shared contract between product and engineering before any code is written.