Data analysis, machine learning, LLM apps, and prompt design (9K skills)
Set up cognee and run a first Python example that stores information and retrieves it with a question. Covers virtual environments, API key configuration, optional packages, and basic troubleshooting.
Estimate the distribution of stockholders' purchase costs for Chinese A-share stocks using price and volume data. A triangular model produces cost concentration metrics, the estimated share below the current price, and visualization charts.
Investigate and fix agent behavior in TradingAgentsCN by checking active database prompt templates, prompt assembly code, and output processing. Apply targeted changes and verify them with focused tests, template checks, and workflow logs.
Retrieve locally stored Chinese A-share prices, financial statements, and valuation context through the project's shared interfaces. Look up technical indicators, inspect available data fields, and check data dates when results disagree.
Design and generate agents in Nanobot by finding reusable tools, skills, prompts, and existing agent configurations. Guide requirements and confirmation, create focused agent assets, and follow recorded real-data testing and evaluation before publication.
Route data analysis, large-file processing, and web retrieval through context-mode tools, returning only relevant results to the conversation. This helps preserve the context window, the limited amount of information an AI can work with at once.
Check how much conversation capacity context-mode has saved during the current session. View token consumption, the context savings ratio, and a breakdown by tool in full tables, with one sentence highlighting the main savings figure.
Build repeatable business reports from connected data sources or uploaded CSV and XLSX files. Define metrics and comparisons, check the calculations, deliver a concise summary and Excel workbook, and save the report definition for future or scheduled runs.
Review product performance by comparing usage, retention, revenue, and other metrics with previous periods and targets. Turn the numbers into a scorecard, explain meaningful trends and uncertainties, and recommend investigations or improvement experiments.
Ask data questions in everyday language, from checking a single metric to investigating trends or preparing a formal report. Receive findings supported by queries, tables, or charts, with data validation and clear limitations.
Check single-cell RNA-seq data quality, filter low-quality cells using median absolute deviation, a measure of spread, and compare plots before and after filtering. Outputs include filtered data and the original dataset with quality annotations.
Analyze data distributions, trends, unusual values, and differences between groups using suitable statistical methods. The skill guides interpretation of effect sizes, meaning the magnitude of differences, alongside uncertainty and business impact, while checking for misleading conclusions.
Convert laboratory instrument files into Allotrope Simple Model (ASM) JSON, a standardized data format, or tabular CSV. Detect instrument types, validate converted data, and export Python parsing code for analysis workflows or handoff to data engineers.
Turn CSV files, pasted data, or query results into an HTML dashboard that opens in a browser. Combine key metrics, interactive charts, filters, and sortable tables in one report, with sample data available when real data is missing.
Explore a table or data file before starting analysis. Summarize its structure, missing values, duplicates, and distributions, flag potential quality issues, and suggest useful measures, grouping columns, and follow-up analyses.
Turn spreadsheets, query results, or pasted data into clear Python charts. Get help choosing chart types, formatting labels and colors, and producing static images or interactive charts with hover details and zoom.
Run nf-core workflows on local sequencing files or public GEO/SRA datasets to analyze gene expression, genetic variants, or chromatin accessibility. The skill guides environment checks, sample table preparation, workflow configuration, execution, and output verification.
Write and improve SQL for major data warehouses, accounting for differences in their syntax. Use it to build analytical queries, translate existing SQL, investigate errors, and review slow queries for performance improvements.
Review an analysis before sharing it with stakeholders. Check calculations, data selection, comparison methods, potential bias, charts, and whether conclusions follow from the evidence, then receive a readiness assessment and specific improvements.
Create or improve a company-specific data analysis skill by gathering analysts’ knowledge and examining database structures. Document business terms, metric formulas, table relationships, and common query patterns in reusable reference files.
Analyze single-cell data with scvi-tools, using deep learning to combine datasets, correct differences between experiments, and transfer cell labels. Model guides and reusable scripts cover RNA, protein, chromatin accessibility, spatial data, and downstream analysis.
Turn a plain-language data request into SQL tailored to your database. Build queries that combine tables, filter records, and calculate summaries, with explanations of each step, performance considerations, and suggestions for adjusting dates or other conditions.
Choose suitable charts for trends, comparisons, distributions, and relationships, then create them in Python with matplotlib, seaborn, or plotly. Apply guidance on colors, labels, scales, and accessibility to produce publication-quality figures or interactive charts.
Set up access to 9Router, a shared gateway for multiple AI providers, and discover available models. Find the relevant capability skills for chat, images, speech, embeddings, web search, and webpage retrieval.