Data analysis, machine learning, LLM apps, and prompt design (8.9K skills)
Analyze images with fal.ai vision models to detect objects, separate their regions, read text, and describe visible content. Ask questions about an image to check specific details in what it shows.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Configure prompt compression, which shortens text sent to AI models, through the OmniRoute command line. Adjust RTK filters, Caveman rules, and combined compression modes, then preview the results using real prompts.
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.
Group AI providers and models behind one model ID in OmniRoute. Choose among 19 routing strategies, define fallback sequences for failures, simulate which provider will be selected, and inspect latency, success rates, and costs.