Find the perfect skill

Data & AI

Continuously monitors RL training logs via tail -f, extracting key metrics (reward, loss, episode length, success rate) and flagging anomalies like gradient explosion or convergence stalls. A research focus is scanning rollout and judge outputs to detect reward hacking patterns, systematic biases, and high-scoring cases mismatched with human preferences. Helps during exploratory RL experiments that require close inspection of undesirable model behaviors.

Data & AI

Helps write, optimize, or explain SQL queries. Looks for issues like missing indexes, N+1 patterns, unnecessary SELECT *, and suggests improvements. Best used when you need to generate clean SQL or troubleshoot query performance.

Data & AI

AI-driven design and optimization of natural killer cell therapies for cancer immunotherapy. Covers CAR-NK engineering, memory-like NK generation, and KIR/HLA matching optimization for allogeneic treatment.

Data & AI

Extracts structured data from websites using browser automation, handling dynamic content, pagination, and anti-bot measures. Activates when users ask to scrape, crawl, or extract data from URLs. Useful when data is not available via APIs or simple HTTP requests.

Data & AI

Automate data cleaning, transformation, and validation for ML tasks. Generates and executes robust ETL pipelines with quality reports and performance metrics.

Data & AI

Searches for available GPU machines on Vast.ai based on specific requirements like GPU model, VRAM, budget, and region. Helps compare offers and select the best machine for renting GPUs.

Data & AI

Analyzes app store review CSV data containing id, date, user_name, title, content, rating, and app_version columns. Generates visualizations such as rating distribution, monthly trends, and version ratings, along with keyword analysis for positive and negative reviews. Useful for understanding user satisfaction, tracking app quality over time, and identifying issues in specific versions.

Data & AI

Sets up a PostHog-based metrics tracking plan with event funnel, KPI benchmarks, and kill/iterate/scale decision thresholds. Useful when defining success metrics, tracking KPIs, or deciding when to kill or scale a feature.

Data & AI

Executes SQL queries against a Supabase PostgreSQL database for SELECT, INSERT, UPDATE, and DELETE operations. It connects using the DATABASE_URL from .env and accepts raw SQL or natural language descriptions of queries. Useful for interacting with tables like competition, team, race, admin, flight, halfflight, and feedback.

Data & AI

Expert in building scalable ML infrastructure and automation pipelines across cloud platforms. Covers the complete MLOps lifecycle including pipeline orchestration, experiment tracking, model versioning, and CI/CD for models. Useful for tasks involving production ML systems, model deployment, and workflow automation.

Data & AI

This skill generates time series forecasts using Nixtla libraries (TimeGPT, StatsForecast, MLForecast). It helps with demand planning, model comparison, and forecast evaluation through ready-to-run scripts.

Data & AI

CLI assistant to manage and query a local database of academic papers using the `papi` command. Supports listing, searching (exact text, BM25, hybrid), showing summaries/equations, and adding papers via arXiv ID or PDF. Use before MCP RAG tools for fast, low-cost lookups.