Data analysis, machine learning, LLM apps, and prompt design (9.1K skills)
Run compute jobs that need cloud CPUs, GPUs, or elastic capacity on Modal. The skill writes a function in the workspace, runs it with the user's authenticated Modal CLI, and saves outputs and run details for later traceability.
Inspect large data files before reading their contents into an agent’s context. The skill returns a compact pointer with schema, shape, samples, and key values using bounded memory, so the agent can select specific rows, columns, or ranges to read.
Use this skill to run social science analyses or read Stata and SPSS data. It reports estimates and uncertainty, checks code against a preregistration plan, verifies fixed random seeds, and reproduces results through R while flagging risks without certifying the analysis.
Create a skill from an idea or improve an existing draft through test prompts, output review, and benchmarks that compare results. The workflow can also refine a skill description to help it trigger for the right requests. A later part of the source material was unavailable.
Support visual inspection and management in industrial settings across more than 20 sectors, including retail, energy, mining, ports, chemicals, and steel. The provided script can analyze an image or generate a report using Baidu Qianfan AppBuilder.
Manage algorithm experiments, adjust parameters, and review visualized results while working to optimize complex algorithms. It is intended for tasks that involve iterative algorithm improvement and experiment tracking, and its included script requires an AppBuilder token.
Use Apify Actors, prebuilt web scraping tools, to collect structured data from social media, search engines, ecommerce sites, and other pages. The skill selects an Actor for the request and can return results as JSON or CSV, with rate limits and ethical scraping guidance.
Use this skill to understand image contents with GPT-4 Vision. It can describe a picture, extract text from screenshots, identify visible objects, and answer questions about an image, returning the result in a structured format.
苹果FoundationModels框架用于设备上的LLM——文本生成、使用@Generable进行引导生成、工具调用，以及在iOS 26+中的快照流。
The English summary is being prepared. Showing the original description.
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
The English summary is being prepared. Showing the original description.
Plan a parsing workflow for repeated text such as forms or quizzes. Use regular expressions for predictable patterns, score extraction confidence, and reserve language model checks for uncertain edge cases to help control cost.
LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存。
The English summary is being prepared. Showing the original description.
PostgreSQL 数据库模式，涵盖查询优化、架构设计、索引和安全。基于 Supabase 最佳实践。
The English summary is being prepared. Showing the original description.
LLM API 使用成本优化模式——基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示词缓存。
The English summary is being prepared. Showing the original description.
PostgreSQL 数据库模式，用于查询优化、架构设计、索引和安全性。基于 Supabase 最佳实践。
The English summary is being prepared. Showing the original description.
在解析结构化文本时，用于在正则表达式（Regex）和大型语言模型（LLM）之间进行选择的决策框架——优先使用正则表达式，仅针对低置信度的边界情况引入 LLM。
The English summary is being prepared. Showing the original description.
Apple FoundationModels 框架，用于设备端大语言模型（LLM）—— iOS 26+ 中的文本生成、配合 @Generable 的引导式生成、工具调用以及快照流式传输。
The English summary is being prepared. Showing the original description.
Apply ClickHouse patterns to analytical data work, from MergeTree table design and query optimization to bulk or streaming ingestion, materialized views, and performance checks. It also covers time-series, funnel, retention, and cohort analyses for large datasets.
Use when analyzing FASTQC quality reports from sequencing data, identifying quality issues in NGS datasets, or troubleshooting sequencing problems. Interprets quality metrics and provides actionable recommendations for RNA-seq, DNA-seq, and ChIP-seq data.
The English summary is being prepared. Showing the original description.
Transform, clean, reshape, and preprocess data using pandas and numpy. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
The English summary is being prepared. Showing the original description.
Generate graphical abstract layout recommendations based on paper abstracts.
The English summary is being prepared. Showing the original description.
A low-level plotting library for comprehensive customization. Use when fine-grained control over every plot element is needed, creating new types of charts, or integrating into specific scientific workflows. Can export to PNG/PDF/SVG for publication. For quick statistical charts, use seaborn; for interactive charts, use plotly; for journal-style, publication-ready multi-panel charts, use scientific-visualization.
The English summary is being prepared. Showing the original description.
Generate Baujat plots for heterogeneity analysis. Identify studies that contribute most to the overall meta-analysis results and heterogeneity, helping discover potential outlier studies. Input meta-analysis data CSV, output Baujat plot PNG and contribution data CSV.
The English summary is being prepared. Showing the original description.
Generate forest plots for meta-analysis of survival data. Input is a CSV file containing study names, HR and 95% confidence intervals, output forest plot PNG and data table CSV. Supports both R and Python scripts.
The English summary is being prepared. Showing the original description.