Review portfolio holdings and prepare a proposed rebalancing plan from target weights. Explains that neural-trader 2.8.11 only returns equal weights, directs actual optimization to a separate skill, and does not place trades.
Run a ruflo agent on your ruOS cloud desktop through an authenticated connection. Follow its output as it runs, record execution status in ruflo, and release the task claim when the run finishes.
Turn a feature idea into a structured specification before coding. Review requirements, system connections, constraints, and failure scenarios, define testable acceptance criteria, and save the specification in memory for later development phases.
Extract MIDI or a score from an already generated music production using pitch tracking. The skill checks that MIDI is available and directs users to the dashboard for downloading it for transcription, arranging, or music software import.
Set up ruvector@0.3.3 with supporting packages, register its MCP server for agent access, and verify installation with diagnostic commands and smoke tests. Helps prepare the dependencies needed for initial use of /vector subcommands.
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.
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.
Audit project dependencies for known vulnerabilities and outdated packages. Organize findings by severity, review proposed package changes before optional automatic fixes, and rerun the audit to check whether the reported vulnerability count decreased.
Inspect how a task ran across agents by collecting recorded execution spans, or timed processing steps. Build a trace tree showing agent activity, duration, errors, and bottlenecks, with a summary of the execution flow.
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.
Check a codebase for known dependency vulnerabilities, hard-coded secrets, and risky code patterns using Ruflo security tools. Choose a scan depth, inspect matching lines, and report verified concerns with a clear account of what was checked.
Automate GitHub tasks such as creating draft pull requests and inspecting automated checks. Confirms the target repository and branch before external changes, keeps actions within authorized scope, and reports the resulting URL or identifier.
Run saved workflows and check their progress, with controls to pause, resume, or cancel execution. Also run JavaScript workflows that coordinate multiple agents and resume them using a recorded run ID.
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.
Create workflows that pause for approval and resume later, or scripts that distribute work across multiple agents. Choose a saved template for ongoing processes or a JavaScript script to collect structured results from parallel tasks.
Save an agent session’s state, settings, memory, and task progress, then restore it in another conversation. List saved sessions, inspect their details, and remove old ones when managing checkpoints for ongoing work.
Build a Claude Code mod, a plugin that extends behavior through event hooks, from ruflo’s template. Sets up function hooks with a classic fallback, user options, status reporting, validation, and tests.
Assess investment risk from supplied daily returns, summarize potential losses and drawdowns, estimate position sizes from backtest results, and review trading halt conditions. Save the assessment for later reference, with assumptions clearly stated.
Turn an approved specification into pseudocode, a plain outline of program logic, and an architecture defining module responsibilities and API inputs and outputs. After user confirmation, proceed with implementation and unit tests based on those designs.
Connect a Cognitum Music account to Claude Code through the cogmusic MCP server, a bridge that exposes music tools. The skill guides token creation, local registration, connection checks, and replacement of expired or revoked credentials.
Group related code files by analyzing a graph of their connections with ruvector. Review group assignments, community labels, and links between files to understand code organization and investigate files that stand apart.
Find code that lacks test coverage and get suggestions for tests to add next. Focus on a chosen path, inspect gaps against a coverage threshold, or use a background worker for recurring checks after feature changes.
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.
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.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)