@vasilyu1983
CAIDO at Altery (UK EMI) · 20 yrs fintech · I build and operate multi-agent systems in regulated environments
144 skills1 repository 101
Designs lakehouse platforms across Iceberg, Delta, Hudi, and Paimon. Use when choosing catalogs, CDC paths, query engines, governance, or cost controls.
The English summary is being prepared. Showing the original description.
Adapts LLMs: SFT dataset loss masking, LoRA and QLoRA, full FT vs PEFT, distillation, pruning, tokenizer fragmentation. Use when fine-tuning or compressing a model.
The English summary is being prepared. Showing the original description.
Configures Claude Code hooks and Codex hooks.json/notify. Use when adding PreToolUse guards, Stop hooks, managed hooks, format-on-save, preflight, audits, or worktree/budget hooks.
The English summary is being prepared. Showing the original description.
Runs production ML and LLM systems. Use when deploying, canarying, rolling back, monitoring drift or feature skew, promoting champions, migrating providers, or handling incidents.
The English summary is being prepared. Showing the original description.
Sizes models and token budgets using Kaplan/Chinchilla scaling laws. Use when reasoning about compute-optimal N and D, tokens-per-parameter ratios, or over-training tradeoffs.
The English summary is being prepared. Showing the original description.
Builds production voice bots and IVR with Python STT/TTS pipelines. Use when designing telephony, streaming audio, latency budgets, or voice quality monitoring.
The English summary is being prepared. Showing the original description.
Designs tool and slash-command runtimes for coding-agent CLIs: registries, deferred loading, tool search, dispatch, forks. Use when modeling tool pools. Not approvals or plugins.
The English summary is being prepared. Showing the original description.
Builds repeatable deep-research workflows for verified synthesis. Use when producing evidence-backed briefs, comparisons, dossiers, or research pipelines.
The English summary is being prepared. Showing the original description.
Creates coding-agent definitions (review, test, refactor, team) for Claude Code, Codex, and Agent SDK. Use when writing a code-review or test subagent, not a runtime.
The English summary is being prepared. Showing the original description.
Chooses subagent, team, workflow, or debate and launches it on Claude Code or Codex. Use when delegating, running agent review boards, or installing shared agents.
The English summary is being prepared. Showing the original description.
LLM serving for latency, batching, caching, quantization, and routing. Use when tuning vLLM or SGLang, sizing KV cache, adding speculative decoding, or cutting serving cost.
The English summary is being prepared. Showing the original description.
Designs RAG retrieval for LLM grounding: chunking, BM25+vector hybrid, reranking, GraphRAG. Use when adding embeddings to SQLite FTS5 search or running held-out retrieval eval.
The English summary is being prepared. Showing the original description.
Creates reusable vector-brain implementations: repo, docs, compliance. Use when building pgvector SQL, manifests, ingest scripts. Not for context design (dev-context-engineering).
The English summary is being prepared. Showing the original description.
Builds analytics engineering layers for metrics, contracts, and BI-ready models. Use when shaping dbt or SQLMesh marts, metric governance, lineage, or data quality.
The English summary is being prepared. Showing the original description.
Automates Metabase cards, dashboards, Remote Sync, embedding, tenants, and the Agent API/MCP server for AI workflows. Use when scripting, promoting, or embedding Metabase content.
The English summary is being prepared. Showing the original description.
Owns instruction files: AGENTS.md, CLAUDE.md, personal and repo rules. Use when writing, pruning, auditing them, sharing rules across Claude and Codex, or fixing ignored rules.
The English summary is being prepared. Showing the original description.
Adds per-skill learnings loops for dated patterns, mistakes, and domain facts. Use when wiring skill memory, consolidation, or drift audits.
The English summary is being prepared. Showing the original description.
Builds production AI bots with Python for support, sales, and custom domains. Use when designing conversation flows, personas, escalation, or LangGraph state.
The English summary is being prepared. Showing the original description.
Designs coding-agent settings and fleet CLI version control. Use when diagnosing precedence, managed policy, version pins, update kill switch, catalog budgets, or searchable notes.
The English summary is being prepared. Showing the original description.
Designs user-facing surfaces of coding-agent runtimes: remote and bridge sessions, transports, reconnect, terminal REPL, input history. Use when building agent UIs.
The English summary is being prepared. Showing the original description.
Designs cross-session agent memory: point-in-time facts, consolidation, tenant isolation. Use when auditing user memory or Mem0/Zep. Not for repo context (dev-context-engineering).
The English summary is being prepared. Showing the original description.
Designs LLM, agent, responsible-AI, and multimodal evals. Use when measuring quality, fairness, grounding, safety, or judge reliability. Not for test harnesses (qa-agent-testing).
The English summary is being prepared. Showing the original description.
Builds a GPT and BPE tokenizer from scratch. Use when implementing autograd, attention, a nanoGPT loop, muP hyperparameter transfer, WSD annealing, loss spikes, or mid-training.
The English summary is being prepared. Showing the original description.
Diagnoses and tunes SQL for OLTP workloads on PostgreSQL, MySQL, and SQL Server. Use when tuning queries, reading plans, indexing, or fixing lock contention.
The English summary is being prepared. Showing the original description.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)