数据与 AI技能

Build workflows on OpenServ where multiple AI agents share tasks and pass results between steps. Examples cover research, writing, and image creation, with guidance on finding agents, setting dependencies, and connecting sequential or parallel work.

中文简介正在准备中。当前显示英语简介。

• Connect research and writing agents
• Build a research-to-image content pipeline
• Combine results from parallel tasks

Use Chainbase CLI to investigate blockchain records, including token holders, prices, wallet activity, and DeFi positions. Use Tops to discover trending crypto topics, inspect related posts, and track recent Twitter/X mentions of projects or keywords.

中文简介正在准备中。当前显示英语简介。

• Check major token holders and transfer history
• Review wallet balances and DeFi positions
• Run custom SQL queries on blockchain records

Analyze a token’s holders and recent traders using Nansen wallet labels. Review Smart Money holdings, meaning wallets classified as informed investors, compare flows across wallet groups, and inspect who recently bought or sold the token.

中文简介正在准备中。当前显示英语简介。

• Checking Smart Money holders and balance changes
• Comparing flows across wallet categories
• Inspecting recent token buyers and sellers

Configure coding agents, AI SDKs, and HTTP clients to send model requests through AntSeed’s local proxy. Find available providers and models, select a provider, set compatible API endpoints, and verify request usage and payment activity.

中文简介正在准备中。当前显示英语简介。

• Connect Claude Code or Codex to AntSeed
• Configure a local endpoint for AI SDKs
• Compare providers’ models, protocols, and prices

Build chat, image generation, and speech transcription features on 0G Compute Network, a distributed GPU marketplace. This skill guides SDK integration, model fine-tuning, response processing for billing, and account funding through code patterns and CLI commands.

中文简介正在准备中。当前显示英语简介。

• Integrating chat and image generation into an application
• Preparing model fine-tuning jobs
• Checking balances and funding provider accounts

Access the Nansen API without an API key and pay per request through Tempo. Set up a Tempo-managed wallet and request data such as Smart Money flows or token holders without managing a separate Base or Solana wallet.

中文简介正在准备中。当前显示英语简介。

• Access Nansen without an API key
• Retrieve Smart Money netflow data
• Retrieve token holder data

Tracks crypto funds and high-performing wallets using Nansen data. It retrieves net flows, trades, and holdings to show what these wallets are buying, selling, or holding, with filters for trader categories.

中文简介正在准备中。当前显示英语简介。

• Checking which tokens crypto funds are accumulating
• Tracking spot trades by high-performing wallets
• Reviewing aggregated holdings and their history

Plan how to split AI models and workloads across multiple GPUs. Compare memory needs, computation, communication, and waiting time to estimate completion times and choose a layout suited to response time, throughput, or cost goals.

中文简介正在准备中。当前显示英语简介。

• Running models that exceed a single GPU's memory
• Comparing ways to split work across GPUs
• Estimating communication costs within and between servers

Analyze GPU operation timings and execution traces to find costly data access, repeated computation, launch overhead, and synchronization waits. Check whether improving an individual operation actually reduces the time needed to complete a full request.

中文简介正在准备中。当前显示英语简介。

• Investigating slow GPU operations
• Assessing whether combining operations reduces data access
• Checking pipeline dependencies and buffer reuse

Compare computing devices for a defined AI model workload using memory capacity, computing speed, data transfer, energy use, and cost. Build a comparison that separates predicted performance from measurements and identifies the constraints that determine the choice.

中文简介正在准备中。当前显示英语简介。

• Choosing hardware for a specific AI model
• Checking whether a model fits in device memory
• Explaining gaps between advertised and measured performance

Estimate GPU memory, training step time, checkpoint costs, and recovery overhead for training or reinforcement learning. Compare state partitioning, recomputation, offloading, and device counts to assess whether a job can finish within its deadline.

中文简介正在准备中。当前显示英语简介。

• Check whether training can finish by a deadline
• Compare memory-saving methods and their time costs
• Plan checkpoint intervals and recovery overhead

Estimate how model architecture, precision, and context length affect weight storage, generation state, computation, and memory traffic. Compare models and attention designs with separate resource estimates for input processing and token generation.

中文简介正在准备中。当前显示英语简介。

• Compare memory needs across model architectures
• Estimate resource costs of longer contexts
• Compare attention designs and expert-based models

Model ongoing requests and multi-step agent work to estimate capacity, latency, and cost per completed task. Break execution into stages, account for queues and retries, and produce workload tables with average and peak resource budgets.

中文简介正在准备中。当前显示英语简介。

• Estimate capacity for ongoing AI requests
• Analyze queues and tool waits in agent workflows
• Compare resource costs per completed task

Design AI agents and chatbots in n8n, choosing suitable nodes and connecting models, tools, conversation memory, and structured JSON output. Includes guidance on document retrieval and human approval before tool execution.

中文简介正在准备中。当前显示英语简介。

• Building a chatbot with conversation memory
• Connecting external tools to an AI agent
• Returning data in a defined JSON format

Guides LoopX benchmark experiments through benchmark-toolkit, covering run management, comparisons under matched conditions, and analysis of agent action histories. It helps explain outcomes and efficiency while tracking source versions, score validity, and evidence boundaries.

中文简介正在准备中。当前显示英语简介。

• Planning and managing benchmark runs
• Comparing baselines and treatments under matched conditions
• Diagnosing outcomes and efficiency from agent action histories

Use DeepChat's bundled command-line interface to compare models, generate media, transcribe audio, and extract text from images. Also inspect runtime status, artifact metadata, public settings, installed Skills, and MCP connections to external tools.

中文简介正在准备中。当前显示英语简介。

• Comparing models and collecting benchmark results
• Generating images, video, or speech
• Transcribing audio and extracting text from images

Design Apache Hudi tables through questions about data updates, scale, and usage. Receive an architecture decision record explaining the choices, plus configuration bundles and execution examples for supported Spark or validated Flink paths.

中文简介正在准备中。当前显示英语简介。

• Designing a new Hudi table
• Reviewing an existing table design
• Comparing Spark and Flink design choices

Inspect an Apache Hudi table’s storage layout using a read-only analysis tool. Get report-based findings on table size, uneven data distribution, excessive partitions, small files, and concentrated writes, with suggested next steps.

中文简介正在准备中。当前显示英语简介。

• Check table size and the largest partitions
• Identify accumulated small files
• Assess excessive partitioning and uneven data distribution

Crawl linked pages within a chosen website scope and collect clean text, Markdown, or HTML with page metadata. Use the resulting records as source material for AI search systems or chatbot knowledge bases.

中文简介正在准备中。当前显示英语简介。

• Collect documentation as Markdown
• Prepare source material for a chatbot knowledge base
• Gather blog content within a chosen scope

Implements mathematical models from a design report as reproducible code, runs calculations, and checks results. It records methods and validation findings in a results report and produces data-based PDF charts for papers.

中文简介正在准备中。当前显示英语简介。

• Implementing models from a modeling report
• Checking constraints and evaluating prediction errors
• Creating PDF charts from computed results

Generate scientific chart examples from bundled Python scripts using repeatable simulated data. Choose from templates such as raincloud plots, correlation matrices, and ROC charts, then receive PNG, PDF, SVG, and editable script files.

中文简介正在准备中。当前显示英语简介。

• Generating sample scientific charts from templates
• Comparing correlation and prediction chart layouts
• Customizing labels and legends in generated charts

Turns mathematical modeling competition problems and attachments into an implementation-ready report. It breaks down questions, examines ambiguous assumptions and data quality, and defines variables, equations, constraints, solution methods, and validation steps.

中文简介正在准备中。当前显示英语简介。

• Breaking down competition questions and their dependencies
• Comparing interpretations of ambiguous problem statements
• Reviewing attached data before modeling

Turn rambling dictation or transcribed voice memos into concise prompts for Claude Code. Remove filler and repetition, then organize the project context, goal, constraints, and expected deliverables while preserving the original requirements.

中文简介正在准备中。当前显示英语简介。

• Turning transcribed voice memos into prompts
• Organizing requirements from long dictation
• Removing repeated phrases and filler words

Instrument Python or TypeScript agents to record runs for Failproof AI, verify local event files, and troubleshoot missing sessions. The skill also guides building evaluator workers that score completed runs on your own infrastructure.

中文简介正在准备中。当前显示英语简介。

• Planning where an agent should record events
• Adding run logging to an existing agent
• Troubleshooting missing events or sessions