Skill UI

Ruflo is a powerful, cross-agent orchestration layer designed to manage complex, multi-step AI coding workflows. It supports coordinating large swarms of AI agents, managing persistent memory through semantic search, and executing sophisticated pipelines using 30+ specialized plugins. Ideal for large-scale development tasks, system benchmarking, and deep research requiring coordinated agent effort.

This skill performs a comprehensive, setup-wide health check for agentic developers. It audits various components—including skills, memory, tools, configuration, and workflow habits—to identify inefficiencies and potential improvements. It provides a detailed report and guides the user through applying targeted fixes, ensuring the agent environment remains lean and optimized.

SkillOpt-Sleep enables an AI agent to undergo a simulated "sleep cycle" for continuous, measurable self-improvement. It harvests past sessions, mines recurring tasks, and re-runs them offline. It then consolidates findings into the agent's memory and skills, ensuring only validated improvements are adopted. This process maximizes long-term competence from short-term interactions.

Reconcile code, docs, rules, memory, and workspace residue so the next session starts from one current source of truth. Best for project handoff, stale documentation, and closing out knowledge drift.

This skill facilitates the persistent storage of critical brand knowledge, including campaign learnings, brand guidelines, and competitive intelligence, into a specialized memory layer (such as a vector database). It automatically indexes content, deduplicates entries via hashing, and applies rich metadata tagging, ensuring that valuable institutional knowledge is preserved and retrievable through natural language search across different sessions.

This tool batches syncs all accumulated session learnings, campaign insights, and performance data to a persistent memory layer. It ensures valuable knowledge is automatically retained across multiple work sessions without manual saving. It supports incremental syncing based on checkpoints, making it fast and safe for continuous knowledge capture.

Share durable context and handoffs between AI agents like Claude and Codex via the local ECC Memory Vault. Use this skill to save work state, transfer context, resume tasks, or search shared project knowledge across different agent harnesses.

This guide provides detailed protocols for achieving high levels of reproducibility in Computer Aided Verification (CAV) research. It emphasizes the necessity of pinning benchmark sets, recording exact tool versions, documenting resource limits (time/memory), and providing checkable proof witnesses to ensure that evaluation claims can be independently validated by competitors or reviewers.

Use the Codebase Memory graph to explore unfamiliar code, map architecture, find symbols and relationships, trace callers and data flow, assess impact, and audit dead or complex code, with Scout, Verify, and Auditor evidence levels.

A comprehensive guide for positioning continual learning and lifelong agent research for the Conference on Lifelong Learning Agents (CoLLAs). This tool helps authors strategically re-frame their work, assess its fit, and optimize the narrative to meet the specific evidence bar of top CS venues focusing on nonstationary learning, adaptation, and memory. It covers scope calibration, required evidence types, and comparison with related ML conferences.

This skill facilitates the loading and application of relevant historical experience memories (OpenViking memories) before executing task actions. It guides the user through a rigorous process: querying memories, applying strict applicability and exclusion checks (gating), and prioritizing real-time facts over loaded guidance. Essential for complex, multi-intent conversational flows.

A comprehensive guide for positioning computer architecture manuscripts for the IEEE HPCA conference. It covers ideal scope (accelerators, memory systems, interconnects), required evidence (benchmarks, performance/energy tradeoffs), and strategic framing needed to appeal to top-tier hardware reviewers. Use it to refine your narrative and ensure your contribution meets the high standards of high-performance computing research.