Explore skills

Complete guide for Weights & Biases (W&B) - experiment tracking, hyperparameter sweeps, artifact management, model registry, and PyTorch Lightning integration

Use after completing any code implementation, bug fix, or refactor. Structured review with pass/fail verification before declaring done.

Comprehensive customer feedback framework including NPS, CSAT, CES surveys, exit interviews, user research, feature request management with RICE prioritization, feedback analysis, close-the-loop processes, and 90-day implementation roadmap for Voice of Customer programs

Транскрипция и суммаризация митингов, созвонов, встреч по аудио/видео файлу. Используй когда: summarize meeting, транскрибировать созвон, обработать аудио митинга, summary встречи, суммаризация записи, meeting summary, транскрипция.

PR レビューコメント・ローカルファイル・会話内のレビュー結果からフィードバックを読み取り、コードに反映する。ユーザーが「レビュー反映して」「フィードバック適用」「/smart-review-apply」と言ったら起動する。

Comprehensive social media strategy including platform selection matrix, platform-specific content strategies, content pillars, 90-day content calendar, engagement tactics, influencer partnerships, and metrics dashboard using Platform Selection Matrix, Content Pillars, and Engagement Ladder frameworks.

Reduce churn and improve retention through cohort analysis, at-risk user identification, win-back campaigns, and customer success strategies. Generate comprehensive HTML reports with retention curves, health scores, churn analysis, and 90-day implementation roadmaps.

Manage ML experiments, track results, and compare performance across different configurations. Use when setting up experiment tracking, creating experiment configs, comparing runs, or analyzing experiment results with W&B, TensorBoard, or MLflow.

Setup development environment with modern Python tooling (uv/pixi), install dependencies, and configure development tools (ruff, ty, pytest). Use when setting up new ML projects, configuring environments, or installing dependencies.

Comprehensive guide for building Python monorepos with uv workspaces - unified dependency resolution, shared lock files, editable installs, testing strategies, Docker optimization, and CI/CD patterns for managing multiple packages in a single repository

Use when fixing a bug, unexpected behavior, or test failure. Investigation-first TDD loop that traces root cause before touching code.

Помогает писать системные промпты для LLM. Используй когда нужно написать prompt, system prompt, системный промпт, инструкцию для модели.