Use ruLake as the agent's working memory. Auto-invoke /rulake-memory:memory-recall when the agent needs to look up something it might already know; auto-invoke /rulake-memory:memory-remember after the agent learns or decides something worth pinning. Closes the self-learning loop without requiring the agent author to wire it explicitly.
The English summary is being prepared. Showing the original description.
Run a safe, structured wellness intake that escalates red flags to professionals.
The English summary is being prepared. Showing the original description.
Verify Rash Studio scenes, ActionScript subset behavior, resource links, portable embeds, exports, and desktop or mobile interaction. Use for Rash acceptance checks, compatibility review, security review, or release validation.
The English summary is being prepared. Showing the original description.
Create or modify Rash Studio projects, SVG animation templates, timeline keyframes, interactive scenes, and website embeds. Use for Rash authoring requests, not general Flash or SWF conversion.
The English summary is being prepared. Showing the original description.
Use ruPet as a practical companion for Ruflo and ruvnet tool workflows, or improve ruPet creation and repair prompts. Use for requests that name ruPet or ask for its tool-aware guidance; ordinary tasks and merely displaying the pet do not need this skill.
The English summary is being prepared. Showing the original description.
Diagnose common Cognitum Seed device issues — won't pair, no WiFi, firmware stuck, MCP tools not appearing in Claude Code. Use when the user reports a Seed-related symptom and asks "why isn't this working?".
The English summary is being prepared. Showing the original description.
Evolve this harness with Darwin Mode — frozen model, evolving harness (real, sandboxed, safety-gated).
The English summary is being prepared. Showing the original description.
Inspect README portability, publication assets and command risks with deterministic evidence. Use when reviewing package documentation, preparing an npm release, or diagnosing first run instructions.
The English summary is being prepared. Showing the original description.
Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.
The English summary is being prepared. Showing the original description.
MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring for sub-100ms response times.
The English summary is being prepared. Showing the original description.
Complete security architecture overhaul for claude-flow v3. Addresses critical CVEs (CVE-1, CVE-2, CVE-3) and implements secure-by-default patterns. Use for security-first v3 implementation.
The English summary is being prepared. Showing the original description.
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
The English summary is being prepared. Showing the original description.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)