데이터·AI 스킬

Build advanced AgentDB workflows with database synchronization, multiple databases, and search that combines meaning with attribute filters. Covers similarity measures, diverse search results, and operational patterns for distributed AI applications.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sharing stored patterns across multiple AgentDB instances
• Filtering semantic search by date or category
• Separating knowledge and conversation databases

Train, deploy, and manage neural networks with Flow Nexus in isolated E2B environments. Use custom architectures or ready-made templates, run predictions, monitor distributed training across multiple environments, and evaluate models before sharing them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train an image classification model
• Forecast time series with LSTM
• Deploy a sentiment analysis template

Create AgentDB learning plugins that use recorded experience to improve agent decisions. Choose a learning method, store states, actions, and rewards, train models, and evaluate suggested actions through CLI and API workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train agents from historical experience
• Build decision-making for games and navigation
• Combine experience from multiple agents for training

Search document collections by meaning using embeddings, numerical representations of text. Compare text similarity, route queries among a few predefined patterns, and use a compressed search index when memory is limited.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding documents with similar meaning
• Comparing the similarity of two pieces of text
• Reducing memory use for large vector collections

Tune AgentDB memory use and search speed through quantization, which stores vectors more compactly, search indexes, caching, and batch operations. Includes configuration examples and benchmarks to help balance accuracy, speed, and storage as datasets grow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reduce memory use in an AgentDB application
• Tune search speed while preserving accuracy
• Plan settings for millions of vectors

Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build agent memory that reuses past experiences
• Record and assess sequences of agent actions
• Consolidate similar experiences into reusable patterns

Coordinate background tasks with specialized agents for research, optimization, audits, and more. Use execution history, quality scores, success rates, and latency to guide agent selection, track performance, and check benchmark compliance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose specialized agents for different task types
• Review agent quality, success rates, and latency
• Record execution feedback to inform future assignments

Plan and implement a unified AgentDB memory backend for agents. Migrate SQLite and Markdown data, add HNSW indexing for similarity search, and support shared memory and SONA learning patterns while preserving compatibility with existing systems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Consolidating separate agent memory systems
• Migrating SQLite and Markdown data to AgentDB
• Finding stored information with similar meaning

Store and retrieve knowledge across agent sessions with AgentDB. Organize memories into tiers, search learned patterns, combine related memories into context, and record causal links to support later work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reuse knowledge from previous agent sessions
• Store and search learned patterns
• Combine related memories into context

Coordinates multiple AI agents with agentic-flow to run tasks in parallel or through dependent stages. It covers team communication structures, shared memory, workload balancing, failure recovery, and performance monitoring for complex workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Develop APIs, user interfaces, and tests in parallel
• Connect design, implementation, testing, and review stages
• Share API schemas across agents

Set up a realtime evaluation folder with a suitable shared harness, the framework that runs evaluations. Prepare prompts, tool definitions, realistic starter data, and a README, then validate the setup with evaluation and test runs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Start a single-turn text-to-speech evaluation
• Set up evaluations using saved audio
• Build multi-turn simulations with mock tools

Creates self-contained HTML charts, tables, diagrams, and dashboards for display within a conversation. It keeps figures traceable to calculations and checks readability in light and dark themes, including narrow mobile layouts, before showing the page.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explaining numerical findings with charts
• Presenting comparisons as tables or diagrams
• Showing a dashboard within a conversation

Analyze CSV, Parquet, and JSON files to answer questions through grouping, joins, cleaning, time series, and charts. Chooses DuckDB or Polars and a suitable processing location based on the task and available memory.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Summarizing and joining data files
• Exploring trends and distributions
• Cleaning data before analysis

Create and update dashboards with charts, metrics, and tables drawn from connected data sources or attached files. Link displayed values to their sources so readers can inspect queries, calculations, and freshness while reviewing business indicators or recurring reports.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Track KPIs and progress toward targets
• Visualize CSV, TSV, or JSON data
• Build recurring reports from connected data

Design multi-agent workflows for research, reviews, and migrations. Organize work across different evidence sources, add independent checks, and combine findings while preserving source references, unresolved questions, and limits on what was examined.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan research across multiple evidence sources
• Review implementation and tests from different angles
• Compare candidate solutions with independent judges

Provide Jarvis with a static catalog of system voices through the included voice_source.json file. This skill supplies reference data only; it does not provide a workflow for choosing voices, handling voice requests, or creating widgets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Supply Jarvis with its system voice catalog
• Check the catalog file included with the skill
• Determine whether the skill includes a voice-selection workflow

Create charts and dashboards with a consistent approach to chart selection, color validation, labels, and interaction. Includes a palette checker and accessibility rules for readable visualizations in both light and dark modes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a chart type that fits the data
• Validate chart colors for color vision differences
• Build charts for light and dark modes

Build custom interactive charts, network diagrams, and maps with d3.js. Guides data-driven drawing, tooltips, zooming, animation, responsive sizing, and accessibility, with examples that work in plain JavaScript or frameworks such as React, Vue, and Svelte.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building charts with custom layouts and styling
• Creating network diagrams and geographic visualizations
• Adding tooltips, zooming, and animated transitions

Build voice assistants and conversational characters with ElevenLabs. Configure voices, language models, and external tools, then connect conversations to a website widget or use Twilio integration for outbound phone calls.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a voice bot for customer support
• Embedding a voice assistant on a website
• Building an interactive voice character

Store conversation history and project material locally, then search by meaning and retrieve original text. Organize memories by person or project, track dated relationships and facts, and keep diary entries that connect work across sessions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Import conversation history or project files
• Search past discussions by meaning
• Organize records by person, project, and topic

Initialize a new MemPalace for AI memory through a guided setup process. The skill retrieves setup instructions for a configuration that uses ChromaDB as its data storage backend and follows the returned steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a new MemPalace
• Setting up AI memory with ChromaDB
• Following guided initialization steps

Train and run Uni-Mol Tools models to predict molecular properties from CSV data. Organize experiments into projects, compare model performance, rank results, and manage storage through interactive commands or machine-readable JSON output.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train molecular property models from CSV data
• Predict properties with a trained model
• Organize experiments and compare model performance

Manage Ollama models and run text generation, chat, and embeddings, which represent text as numerical vectors, through command-line requests. Check server status, inspect model details, and receive structured JSON output for agent workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Download models and inspect their details
• Generate text or chat with a chosen model
• Convert text into numerical vectors

Create, inspect, edit, and validate Dify workflow definition files from the command line. This wrapper provides access to node and connection edits, model and prompt settings, file comparisons, and import or export through the upstream CLI.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a Dify workflow from a template
• Inspect and validate workflow definition files
• Edit nodes and their connections