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.
Modernize the claude-flow v3 command-line interface by splitting large command files, adding interactive prompts, connecting hooks that run on execution events, and organizing multiple commands into automated workflows with progress reporting.
Set up RuView sensing nodes by building and flashing ESP32 firmware, configuring WiFi and the receiving address, and checking serial logs. Diagnose missing CSI streams, the WiFi signal measurements sent by sensing nodes.
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.
Connect agent tasks into a sequence where each step receives the previous output. Use custom prompts or predefined workflows to analyze code, plan refactoring, generate tests, optimize performance, or transform data through multiple stages.
Review Homecore plugins by distinguishing built-in native code from external Wasm packages. Check signatures, publisher identity, paths, resource limits, and host permissions, then use the documented verification command to assess the plugin’s trust boundaries.
Automate checks, code formatting, agent coordination, and session records around Claude Code operations. Uses hooks, actions triggered before or after work, to preserve context and connect development tasks with shared memory.
Set up radar sensing for contactless heart rate, breathing rate, presence, and distance measurements. It covers supported hardware, firmware, and combining radar with WiFi CSI, sensing data derived from wireless signals, for shared readings and 3D views.
Verify RuView changes with Rust and Python tests, output hashes that detect processing changes, and firmware hash records. Packages test logs and audit evidence into a witness bundle that recipients can check with a single command.
Coordinate multiple AI agents with agentic-flow to run tasks in parallel or through ordered stages. Configure shared memory, team structure, workload distribution, retries, and task reassignment, then monitor how the group performs.
Check code and agent outputs, track reliability scores, and roll back changes that fail a chosen threshold. Includes quality reports, live monitoring, and integration with automated build and deployment workflows.
Organize software releases on GitHub, from version suggestions and release notes to testing, builds, and deployment. Coordinate multiple packages or repositories, roll changes out in stages, and configure rollback to restore an earlier release when problems occur.
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.
Integrate RuView through shell commands, an HTTP API, or WebAssembly builds, which run compiled code in browsers and supported edge devices. Covers survivor scan commands, result exports, API hosting, and browser or ESP32 deployment paths.
Get RuView running with a Docker demo using simulated WiFi signal data, source checks, or live sensing with supported hardware. Choose a starting path based on available equipment and open a working sensing dashboard.
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.
Create and improve GitHub Actions workflows for automated testing and deployment. Coordinate multiple AI agents to review pull requests, investigate failed runs, scan for security issues, and manage releases across repositories.
Measure and optimize claude-flow v3 startup, search, attention processing, and memory use. Compare benchmarks against performance targets, track changes over time, and identify regressions to guide further optimization.
Restructure claude-flow v3 into focused modules using Domain-Driven Design, which groups code by responsibility. Define module boundaries, event communication, and plugin interfaces to support a modular architecture with independently testable business logic.
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.
Connect RuView sensing data to AI agents through tools for presence, breathing, and heart rate. Explore agent coordination and prototype storing agent state and decisions alongside sensing data in a shared RVF container.
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.
Review and strengthen security in claude-flow v3 by addressing dependency risks, password hashing, credential generation, input validation, file paths, and command execution. It also guides threat modeling and tests for security-critical code.
Work with AI as a coding partner, choosing who writes code and who guides the work. Supports role switching, test generation, ongoing code review, debugging, and step-by-step explanations for learning.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)