查找技能

使用fal.ai视觉模型检测图像中的物体、划分各自区域、识别文字并描述内容。还可以针对图像提问，核实画面中可见的信息。

• 识别图像中的文字
• 检测物体并划分区域
• 获取图像描述并询问可见细节

Train a custom LoRA on fal.ai, a model adaptation for personalized image generation. Use it to prepare an image model tailored to a particular brand, character, or visual style.

中文简介正在准备中。当前显示英语简介。

• Training a model for brand-specific imagery
• Preparing a custom model for a character
• Training a LoRA for a particular visual style

Build charts and interactive data visualizations with D3.js, a JavaScript library for drawing data graphics. Examples across chart types support reports, dashboards, explanatory graphics, and prototypes that let readers explore data.

中文简介正在准备中。当前显示英语简介。

• Exploring sales data with a zoomable treemap
• Showing relationships in a force-directed network graph
• Displaying daily patterns in a calendar heatmap

Turn CSV, Excel, or JSON data into a visual report page with key metrics, multiple charts, a data table, and written observations. The report uses supplied data and includes its source, reporting period, and methodology.

中文简介正在准备中。当前显示英语简介。

• Turn growth data into a visual weekly report
• Present key metrics and year-over-year changes
• Share charts alongside source data and methodology

Build focused knowledge bases from claude-mem observations, filtered by topic, project, date, or file. Load selected records into an AI conversation to ask contextual follow-up questions about past decisions, fixes, and work patterns.

中文简介正在准备中。当前显示英语简介。

• Compiling knowledge about a specific technical topic
• Reviewing decisions made during a chosen period
• Asking follow-up questions about a service's past bug fixes

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.

中文简介正在准备中。当前显示英语简介。

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

Build a room-specific sensing model by recording an empty room and occupants performing activities, then training small specialized models. The workflow continues into live monitoring of presence, posture, and breathing in the calibrated room.

中文简介正在准备中。当前显示英语简介。

• Train a sensing model for a specific room
• Record an empty room and occupant activities
• Monitor presence, posture, and breathing after training

Build AI agents that retain conversation history, user preferences, and useful interaction patterns with AgentDB. The skill covers persistent storage, meaning memories survive between sessions, plus retrieval, context management, and ReasoningBank integration.

中文简介正在准备中。当前显示英语简介。

• Add conversation history to a chat system
• Remember user preferences across sessions
• Reuse patterns from successful interactions

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.

中文简介正在准备中。当前显示英语简介。

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

Implement agents that use recorded task outcomes to choose future approaches. ReasoningBank supports matching past patterns, comparing strategies, retaining experience in AgentDB, and tracking how strategy success and learning change over time.

中文简介正在准备中。当前显示英语简介。

• Choose task strategies using past outcomes
• Compare approaches to code review or bug fixing
• Match current situations to learned patterns

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.

中文简介正在准备中。当前显示英语简介。

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

Train and evaluate RuView models using Wi-Fi measurements for pose estimation, retrieval, and adaptation to different environments. Follow laptop or GCloud GPU workflows, then package and publish trained models to Hugging Face.

中文简介正在准备中。当前显示英语简介。

• Train pose estimation without cameras or labels
• Train pose estimation with paired camera and Wi-Fi data
• Adapt models to different rooms and environments

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

Run RuView applications for occupancy, breathing and heart rate, activity, pose, sleep, and room changes. Choose suitable examples and startup commands for a simulated demonstration or a working ESP32 setup that captures WiFi signal measurements.

中文简介正在准备中。当前显示英语简介。

• Try presence and occupancy sensing
• Explore breathing, heart rate, and sleep monitoring
• Run activity and pose estimation examples

Train and evaluate models that estimate human poses from WiFi signals. Compare results against a model that always predicts the average pose, check for data leakage, and report measured improvements with clear evaluation conditions.

中文简介正在准备中。当前显示英语简介。

• Train a pose model using camera labels
• Evaluate pose estimation without a camera at inference
• Compare accuracy against an average-pose baseline

Build document search with AgentDB that finds related content by meaning. Store documents as numerical representations, combine similarity search with metadata filters, and retrieve relevant passages for systems that generate answers using source material.

中文简介正在准备中。当前显示英语简介。

• Build answers grounded in retrieved documents
• Add meaning-based search to a knowledge base
• Find documents with similar content

Turn data into chart images by selecting a suitable format from 26 options. Visualize trends, comparisons, distributions, flows, or relationships, then receive the image URL and the complete settings used to generate it.

中文简介正在准备中。当前显示英语简介。

• Visualize changes over time
• Compare categories and proportions
• Show distributions and correlations

Analyze Excel and CSV files to summarize statistics, filter records, compare groups, and join data across sheets or files. Export results as CSV, JSON, or Markdown tables for further work or sharing.

中文简介正在准备中。当前显示英语简介。

• Compare monthly sales and top-selling products
• Combine order records with customer data
• Check missing values and statistical summaries

Send research and analysis tasks to a running DeerFlow instance through its HTTP API, an interface for exchanging requests. Retrieve responses, continue conversations, upload documents, and inspect available models, skills, agents, and service health.

中文简介正在准备中。当前显示英语简介。

• Delegate research and analysis to DeerFlow
• Upload documents for a conversation
• Resume an earlier conversation

Design and build AI agents for business, research, operations, or creative work. Define essential actions and knowledge, start with a simple execution loop, and add progress tracking or separate child agents as needs emerge.

中文简介正在准备中。当前显示英语简介。

• Designing an assistant for business tasks
• Building a research agent
• Choosing essential actions and knowledge

Manage OmniRoute context settings from the command line, including token budgets and RTK filters for processing context. Switch saved server connections, import or export configurations, and inspect or expire conversation sessions.

中文简介正在准备中。当前显示英语简介。

• Adjust context token budgets and filtering rules
• Switch between saved server connections
• Import or export connection settings as JSON

Create, list, switch, and delete model routing combinations from the command line. Request suggestions using task descriptions, cost limits, and response time limits, with an option to explain recommendations or activate a suggested setup.

中文简介正在准备中。当前显示英语简介。

• Creating a routing combination with specified models
• Listing routing combinations and switching the active one
• Finding candidates within cost and response time limits

Set spending limits, token quotas, and rate limits, which restrict requests over time. Review current consumption and apply controls per API key or globally to manage AI costs across providers.

中文简介正在准备中。当前显示英语简介。

• Set spending limits for AI usage
• Assign token quotas per API key
• Review and update global rate limits