Skill UI

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.

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.

Standing rules telling an AI agent when to recall long-term memory before acting and when to save decisions, corrections and failures afterwards. Covers entry writing, superseding old memories and handling conflicts, and works with file, local MCP or hosted memory backends.

AKF is an AI-native file format that embeds trust scores, source provenance, and compliance metadata into various file types like DOCX, PDF, and code. It supports auditing for regulations such as the EU AI Act, SOX, and HIPAA, ensuring transparency and accountability in AI-generated content workflows.

Low-level .NET SDK for creating and managing persistent AI agents with threads, messages, runs, and tools. Supports function calling, file search, vector stores, and streaming responses.

Python SDK for Azure AI Content Understanding service. Enables multimodal content extraction from documents, images, audio, and video files. Supports prebuilt analyzers for RAG and custom field extraction for automated workflows. Ideal for developers building AI-driven applications.

Build AI applications on Microsoft Foundry with the azure-ai-projects Python SDK: create and version agents, add tools like code interpreter and file search, manage threads and runs, connections, deployments, datasets, indexes, and run evaluations.

Python SDK for transcribing authorized audio files with the azure-ai-transcription client, including timestamps, authentication options, and privacy-aware handling of transcripts and credentials.

Clarity Gate is a pre-ingestion verification system designed for Retrieval-Augmented Generation (RAG) workflows. It ensures documents entering knowledge bases are properly qualified by checking for uncertainty markers and distinguishing assumptions from facts. This skill produces Clarity-Gated Documents (CGD) and validates Source of Truth (SOT) files. It helps prevent hallucinations by enforcing epistemic quality standards before data ingestion. Note that it verifies document form rather than factual truth, requiring human-in-the-loop validation for accuracy.

This skill covers strategies for compressing conversation history in AI agent sessions to manage context window limits. It focuses on optimizing tokens-per-task rather than just tokens-per-request. Techniques include anchored iterative summarization, opaque compression, and regenerative summaries. It also addresses artifact trail integrity and evaluation methods like probe-based testing to ensure critical information like file paths and decisions are preserved during compression.

Delegate bounded work to other AI agents while preserving context, file ownership, and progress checks. Covers agent selection, structured prompts, polling, remote VPS safety, and driving interactive CLIs.

Ditto mines user words from local coding-agent session logs to create private work, design, and writing profiles. It requires explicit user approval before mining begins and keeps all data local. This skill routes a compatible Ditto runtime to extract patterns from real coding history rather than questionnaires, ensuring privacy and evidence-backed personalization for AI agents.