Skill UI

Read-only diagnosis for OpenViking memory issues: trace backward from a memory file to its archive memory_diff.json, then to session messages when needed. Use it for incorrect content, wrong paths or owners, missing memories, and unexplained updates or deletes.

Work with Outpost Bio's open microbiome foundation models: embed taxonomic profiles, fine-tune Waypoint checkpoints, benchmark on Compass, pretrain on Atlas, and convert MetaPhlAn, Kraken2, QIIME 2, or MGnify tables via the waypoint CLI.

Compare multiple Japanese NLP libraries, models, or datasets across selected criteria using a comparison table. Supports both specific tool comparison (seed mode) and topic-based comparison (topic mode). Uses bundled data and web search to find relevant resources. Ideal for evaluating alternatives before choosing the best tool for your project.

This skill helps identify issues in Superpowers sessions by analyzing transcripts and evidence. It assists in troubleshooting problems like repeated work, ignored plans, or unexpected costs. The process involves locating session files, triaging dimensions, generating detailed reports, and optionally creating GitHub issues or export bundles for maintainers. All findings must cite specific paths and lines.

This skill routes goals through the acc's scored-memory loop using acc_act with runtime="solve". It enables deliberation on returned brain_frames and submission via continue. Users must reason over frames and end proposals with a prediction score. It ensures honest commitment closure and prevents solo-derivation outside the loop.

A comprehensive guide to building production-grade evaluation systems for Large Language Models (LLMs). This skill covers advanced methodologies, including Direct Scoring and Pairwise Comparison, alongside critical techniques for mitigating systematic biases (e.g., Position Bias, Length Bias). Learn how to select appropriate metrics and structure prompts to ensure reliable, consistent, and objective quality assessment across various AI applications.

Generate decision-ready reports from AI agent evaluation runs. This skill ensures autonomous, assisted, failed, and timed-out outcomes remain distinct and comparable. It defines metrics with correct denominators, handles latency and cost populations honestly, and maps evidence to decision gates. Ideal for benchmarking, regression testing, and production readiness validation of AI agents.

This MCP server provides a persistent and searchable memory bank for AI agents. It enables reading, writing, and searching long-term knowledge, architecture patterns, and decisions. The system syncs with project documentation and includes a standalone dashboard for visualization. Ideal for managing agent context and knowledge retention across complex workflows.

This skill enables systematic improvement of existing AI agents by analyzing performance metrics, identifying failure modes, and applying prompt engineering techniques. It involves establishing baselines, optimizing prompts through chain-of-thought and few-shot examples, refining role definitions, and validating changes through structured testing and A/B comparisons to ensure reliability and efficiency.

This skill optimizes multi-agent systems through coordinated profiling, workload distribution, and cost-aware orchestration. It helps improve agent performance, throughput, and reliability by identifying bottlenecks, managing context windows, and reducing latency. Suitable for complex workflows requiring intelligent coordination and efficiency tracking across multiple AI agents.

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Ensures graceful degradation and clear failure modes. Capable of agent architecture design, tool calling, memory management, and debugging complex agent systems.

This skill enables building production-ready LLM applications, advanced RAG systems, and intelligent agents. It covers vector search, multimodal AI, agent orchestration, and enterprise integrations. Learn to design architectures, optimize embeddings, ensure safety, and deploy models at scale using frameworks like LangChain and vector databases.