데이터·AI 스킬

Coordinate multiple AI agents in a mesh, a network where peers communicate directly. It guides shared decisions, task assignment based on skills and workload, network monitoring, and recovery when agents fail or connections break.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Coordinating agents through direct peer communication
• Redistributing work from overloaded agents
• Planning recovery from agent failures

Plan, train, evaluate, and deploy neural networks using Flow Nexus cloud infrastructure. Coordinate training across multiple computing environments, tune training settings, and manage model versions, predictions, and ongoing performance monitoring.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing models for classification or time series
• Coordinating training across cloud environments
• Comparing model performance and tuning training

Coordinate multiple AI agents by adjusting their communication structure and task assignments as workloads change. The skill describes performance monitoring, switching coordination patterns, forecasting agent capacity, and validating changes with rollback when performance worsens.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a coordination structure for multiple agents
• Redistributing tasks when agent workloads become uneven
• Forecasting how many agents a workload needs

Calculate portfolio weights from a covariance matrix, which describes how asset returns move together, and expected returns using Conjugate Gradient. Save the weights with the solver used, numerical error, and timing so the calculation can be checked later.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Calculating portfolio weights from supplied return data
• Comparing Conjugate Gradient with the legacy calculation
• Keeping records of weights and calculation details

Guide market prediction workflows with LSTM, Transformer, and N-BEATS models using neural-trader commands and result storage. It explicitly identifies version 2.8.11 outputs as placeholders, so they cannot be treated as fitted models or evidence of prediction accuracy.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing market prediction model commands
• Checking whether training outputs are placeholders
• Organizing model run records

Find stored Ruflo memories by meaning, keywords, or an optional ranking method. Search across storage groups, retrieve past solutions and task context, and see which search method actually ran, including any fallback.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding solutions to previously resolved problems
• Retrieving past task context and user corrections
• Searching memories across multiple storage groups

Classify market conditions as bullish, bearish, ranging, or volatile to guide strategy selection and historical testing. Distinguish synthetic demonstrations from analysis of actual price data, with confidence levels and historical comparisons where available.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing market conditions for a stock symbol
• Choosing a strategy suited to market conditions
• Checking market conditions before a backtest

Test trading strategies against historical market data and collect performance metrics. The skill checks whether data is real or synthetic and can digitally sign results to help detect tampering before a strategy moves into live trading.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Evaluate a strategy against historical market data
• Compare returns, risk measures, and trading results
• Prepare signed backtest results for live-trading review

Run demanding neural-trader backtests, parameter comparisons, and model training in an Anthropic Managed Agent cloud container. Estimate costs, test inputs on a small run, collect performance metrics and CSV files, and verify signed results before storage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing trading strategies over several years
• Comparing many parameter combinations
• Training LSTM or Transformer models in the cloud

Import Claude Code auto-memory into AgentDB and search past notes by meaning across sessions and projects. The skill checks import status, consolidates near-duplicate entries, and returns search results with their memory sources identified.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Search past notes across projects
• Import all project memories for the first time
• Consolidate near-duplicate memories

Explain a trading model's prediction by ranking the input features that contributed to its signal. Returns a Markdown table and saves an attribution record with calculation settings, adding a digital signature when a signing key is available.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing which inputs drove a trading signal
• Saving signed records of model explanations
• Reproducing rankings with the same signal and seed

Store useful patterns and solutions in AgentDB, then find them through semantic search, which matches meaning rather than exact wording. Use saved knowledge before starting work and record successful approaches and new lessons afterward.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving successful approaches for reuse
• Finding solutions from past work
• Searching stored knowledge by meaning

Convert chat messages into template strings for local model runtimes such as Ollama or llama.cpp. Optionally route queries among a few registered intents using embeddings, numerical representations of meaning, without calling a model.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing prompt strings for Ollama
• Formatting conversations for a local model
• Routing queries among a few intents

Represent dependency trees, taxonomies, and other hierarchies inside a Poincare ball, a geometric model for hierarchical distances. Use tree depth for radius and text embeddings for direction, then measure distances to examine the encoded structure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Analyze subtrees in module dependencies
• Examine structural patterns in class hierarchies
• Organize concepts by taxonomic relationships

Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding newly available router models to chat-ui
• Writing concise descriptions of model capabilities
• Updating production and development model entries together

Generate RuVLLM settings for local language model inference and create MicroLoRA or SONA instances. Adjust their small internal weights using quality scores as feedback, with instances held in server memory for subsequent adaptation calls.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Configure local language model inference
• Prepare inference tools for an air-gapped environment
• Adjust MicroLoRA using quality feedback

Guide GAIA benchmark runs from environment checks and cost estimates to result comparison. Create a signed submission package compatible with HAL, including agent traces, metadata, and an audit report that checks for benchmark exploitation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check readiness for a GAIA benchmark run
• Estimate costs and run an evaluation
• Package existing results for submission

Compare ruflo and HAL systems for running the GAIA benchmark, an AI evaluation. Examine differences in code execution, browsing, file handling, memory, and model selection to prioritize improvements by expected impact and effort.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan the next round of GAIA improvements
• Compare code execution and browser capabilities
• Weigh improvement priorities against implementation effort

Manage stored agent memories for backups, project transfers, and team knowledge sharing. Work with RVF, a portable memory format, to export and import records, upgrade formats, inspect storage statistics, and transfer patterns between local projects.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Back up stored agent memories
• Transfer memories and patterns between projects
• Share stored knowledge with a team

Convert text, code, or documents into 384-dimensional vectors, numerical representations used for meaning-based search, similarity comparison, and clustering. Save vectors to files, check their dimensions and magnitude, and optionally record metadata in AgentDB.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing document vectors for meaning-based search
• Converting text or code for similarity comparison
• Preparing vectors for clustering related documents

Experiment with the policies that govern an AI agent, such as planning, memory, and tool use. Test one policy change per variant in a sandbox, an isolated environment, and promote only candidates with measured improvements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding policy changes that improve low evaluation scores
• Exploring initial agent settings for a new domain
• Comparing manual tuning with an evolved baseline

Reuse patterns learned in another local project, or find, download, and publish patterns through an IPFS sharing registry. It supports confidence filters for local transfers and verification checks when downloading shared patterns.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reuse learned patterns in a new project
• Find and inspect shared patterns
• Publish patterns for peers to reuse

Find candlestick and chart patterns in previously ingested market data. Classify detections by reversal or continuation, bullish or bearish direction, and reliability score, then rank and store them for later reference.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding candlestick patterns for a symbol and period
• Reviewing patterns ranked by reliability
• Organizing bullish and bearish signals

Prepare market history for pattern detection and comparison. Import opening, high, low, and closing prices plus volume, validate and normalize the values, then store them by symbol and date for later retrieval. It does not place orders.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Loading price and volume history for a symbol
• Preparing market data for pattern detection
• Normalizing data before comparing price movements