Vasiliy Uvarov

Designs durable API contracts across REST, GraphQL, gRPC, tRPC, and AsyncAPI. Use when specifying interfaces, auth, versioning, errors, rate limits, or agent APIs.

The English summary is being prepared. Showing the original description.

Builds per-repo code graphs in JSON and markdown-ready derived artifacts. Use when you need blast radius, symbol-level maps, import graphs, inheritance, or test links.

The English summary is being prepared. Showing the original description.

Context-driven AI development with AGENTS.md, repo knowledge bases, Claude Code, Codex, and Copilot. Use when adopting repo-native AI workflows or multi-repo setups.

The English summary is being prepared. Showing the original description.

Scores team or opt-in individual contribution quality from commit and PR history. Use when building engineering scorecards or coaching; for AI impact use dev-ai-coding-metrics.

The English summary is being prepared. Showing the original description.

Guides dependency audits and upgrades. Use when auditing dependencies, upgrading vulnerable packages, managing lockfiles or package managers, SBOMs, or update and monorepo policy.

The English summary is being prepared. Showing the original description.

Configures and hardens Claude Code and Codex MCP servers. Use when connecting databases, APIs, SaaS, building servers, or serving a clearance-filtered knowledge base.

The English summary is being prepared. Showing the original description.

Creates and audits agent skills: SKILL.md, references, scripts, runtime metadata. Use when writing, validating, or security-reviewing a skill, or fixing truncated skill listings.

The English summary is being prepared. Showing the original description.

Designs and runs agent hives and multi-agent waves. Use when setting hive roles, code gates, dependency-graph fan-out, or verifier, vote and loop-until-dry passes.

The English summary is being prepared. Showing the original description.

AI agent architecture, graph and loop composition, protocol choice, evaluation, and observability. Use when scoping or reviewing systems before implementation.

The English summary is being prepared. Showing the original description.

Chooses among AI/ML approaches: classical ML, LLM, RAG, fine-tuning, agents, embeddings, MoE or SSM. Use when picking or scaling an architecture, or self-host vs API.

The English summary is being prepared. Showing the original description.

Designs coding-agent observability and evals. Use when measuring traces, replay, checkpoint lineage, tool grading, regression, or cost. Not for general LLM evals (ai-evals).

The English summary is being prepared. Showing the original description.

Designs provider runtimes for coding agents. Use when modeling model abstraction, streaming semantics, tool-call normalization, retries, or fallback routing.

The English summary is being prepared. Showing the original description.

Designs approval and sandbox policy for local coding agents: permission modes, isolation, network and destructive-command guards. Use when setting approvals. Not cloud sandboxes.

The English summary is being prepared. Showing the original description.

Designs session and task state for coding-agent runtimes: resume, checkpoints, compaction, cancellation, background and scheduled runs. Use when persisting agent work.

The English summary is being prepared. Showing the original description.

Builds LLM pretraining corpora from Common Crawl: extract, filter, deduplicate, decontaminate, mix, synthesize. Use when curating or ablating a pretraining corpus or data pipeline.

The English summary is being prepared. Showing the original description.

Guides multi-GPU pre-training: DDP, FSDP2, ZeRO, tensor/pipeline/expert parallelism, fp8/Muon. Use when scaling a run, training MoE, or reproducing GPT-2 on rented GPUs.

The English summary is being prepared. Showing the original description.

Runs local and self-hosted LLMs with Ollama, LM Studio, MLX, llama.cpp, and Open WebUI. Use when choosing GGUF quants, sizing VRAM, or running models privately.

The English summary is being prepared. Showing the original description.

Builds ML pipelines: EDA, features, leakage checks, evaluation. Use when doing data science or explaining fairness, privacy, speech, vision-language, or diffusion mechanics.

The English summary is being prepared. Showing the original description.

Builds and backtests demand and revenue forecasts: rolling-origin backtests, prediction intervals, reconciliation, zero-shot foundation models. Use when forecasting time series.

The English summary is being prepared. Showing the original description.

Chooses DPO, GRPO/RLVR, reward models, and over-optimization controls. Use when adapting a pretrained or SFT model with preference or verifiable reward signals.

The English summary is being prepared. Showing the original description.

Builds multi-repo context hubs and compiled markdown knowledge maps. Use when profiling repo portfolios or assembling LLM-ready cross-repo knowledge bases.

The English summary is being prepared. Showing the original description.

Designs operating models for AI in product teams. Use when planning platform ownership, provider strategy, data boundaries, evals, or sensitive-data controls.

The English summary is being prepared. Showing the original description.

Prompt engineering for production LLMs — structured outputs, evals, RAG, tool workflows, multimodal prompting, and safety. Use when designing, debugging, or shipping prompts.

The English summary is being prepared. Showing the original description.

Designs coding-agent plugin systems. Use when adding plugin manifests, extension points, or reloadable integrations, or keeping plugin cache compatible across CLI upgrades.

The English summary is being prepared. Showing the original description.