Data skills

This skill runs nf-core bioinformatics pipelines on local or public sequencing data, guiding researchers through data acquisition, setup, and results.

This skill synthesizes qualitative and quantitative user research into structured insights and prioritized opportunities to guide product decisions.

This skill decomposes natural language questions into parallel, source-specific searches, ranks results by relevance, and synthesizes a unified answer.

This skill generates professional market research reports (50+ pages) with LaTeX formatting, data-driven analysis, and curated visuals.

This skill helps you generate editable PPTX posters from HTML/CSS and export to PDF or PPTX with AI-enhanced visuals.

This skill helps you accelerate data processing with Polars by leveraging lazy evaluation and Apache Arrow backend for in-memory datasets.

This skill synthesizes multi-source results into coherent, deduplicated answers with source attribution, delivering concise, trustworthy summaries for informed

This skill helps plan and prioritize roadmaps using RICE, MoSCoW, ICE, and OKR-aligned methods to enable strategic decision making.

This skill helps you perform reconciliation workflows by guiding GL-to-subledger, bank, and intercompany reconciliations and categorizing reconciling items.

This skill assesses and classifies legal risks using a severity-likelihood framework to support contract reviews and escalation decisions.

This skill helps you understand Materialize queries, sources, sinks, and views by summarizing key concepts from the official docs.

This skill generates publication-ready infographics by analyzing content and recommending optimal layout and style combinations across 20 layouts and 17 styles.

This skill detects prompt injections and jailbreak attempts in LLM apps, ensuring safer interactions and reliable third-party data filtering.

This skill helps you streamline PyTorch Lightning training, automate distributed execution, and reduce boilerplate for scalable, reproducible experiments.

This skill optimizes LLM data curation with GPU-accelerated, multi-modal cleaning, deduplication, and PII redaction to improve training data quality.

This skill helps researchers generate genuinely novel CS and AI ideas by applying cognitive science frameworks like combinatorial creativity and constraint

This skill extracts and validates structured data from LLM responses using Pydantic, with automatic retries and real-time streaming.

This skill helps generate high-quality embeddings for semantic search and retrieval using sentence-transformers, enabling efficient RAG, clustering, and

This skill helps you build complex AI systems with declarative LM programming, automatic prompt optimization and modular RAG pipelines for reliable outputs.

This skill benchmarks code generation models across 15+ tasks, providing pass@k metrics and multi-language evaluation for robust code quality.

This skill helps you accelerate RL-based LLM post-training with slime's Megatron-LM and SGLang for scalable data generation and rollout.