Skill UI

Python SDK for Biohub's ESM3 protein generation, ESMC embeddings, and ESMFold2 all-atom folding. Supports local model inference and hosted clients for protein sequence completion, structure prediction, and embedding extraction. Requires Python 3.12+ and isolated environment setup.

A comprehensive guide to using AssemblyAI for rich audio processing. This guide covers basic speech-to-text transcription from URLs or local files, along with advanced AI features. Capabilities include speaker diarization, sentiment analysis, key phrase extraction, entity detection, and powerful LLM-powered analysis (LeMUR) for summarization and Q&A. Ideal for integrating deep, multi-faceted audio insights into applications.

A comprehensive offensive checklist for assessing the security and robustness of AI and Large Language Model (LLM) applications. It covers advanced adversarial techniques such as prompt injection, jailbreaking, model extraction, data poisoning, and analyzing system vulnerabilities across components. Essential for red-teaming and security assessment.

A comprehensive security skill designed to detect and mitigate indirect prompt injection attacks. It scans untrusted external content—including web pages, PDFs, and images—for hidden, obfuscated instructions before an LLM agent processes them. The pipeline combines content extraction (HTML, OCR), normalization, and dedicated ML models (e.g., LLM Guard, Prompt Guard 2) to ensure data safety.

This skill provides comprehensive methods and frameworks to detect sophisticated AI attacks, including model extraction, membership inference, and model inversion, which abuse inference APIs. It focuses on monitoring per-principal query volume, input distribution, and confidence exposure. Use it for securing public or partner inference APIs, or for conducting pre-deployment red-teaming to assess the model's extractability and overall security posture against MITRE ATLAS techniques.

This skill analyzes completed code sessions to automatically extract reusable patterns, transforming raw interaction data into structured, learned skills. It allows the AI to continuously improve its domain knowledge by capturing techniques like error resolution, debugging methods, and workarounds, making it effective for advanced coding assistance and knowledge curation.

Design task-local harnesses, evaluation gates, and reusable skill extraction for adaptive agent workflows. This skill helps build structured systems for one-off work, shared skills, and observable checkpoints. It defines input boundaries, tool bindings, and safety checks to ensure reliable automation without manual intervention.

Diagnose why a GAIA benchmark question failed: extract the trace, classify the failure mode via a taxonomy (tool gap, reasoning miss, extraction bug, loop, dataset shift, timeout), and propose a targeted fix before resubmitting.

A robust, on-device solution for processing large-scale clinical text corpora. Supports batch NER, PII extraction, and de-identification over thousands of notes. Features include sharding, checkpointing, resumable functionality, and streaming results to JSONL, ensuring PHI safety and constant memory usage for massive datasets.

This skill deploys the OpenMed Model Context Protocol (MCP) server, exposing critical clinical NLP tools such as NER, PII extraction, and de-identification. It enables AI coding agents and chat clients to interact with OpenMed's capabilities via simple tool calls, running locally on-device to ensure user data privacy and security. Supports both stdio and Streamable HTTP deployment modes.

A comprehensive guide for installing, configuring, and validating the local long-term memory plugin (`memory-tencentdb`) within the OpenClaw environment. This guide covers everything from environment pre-checks to advanced configuration for data capture, information extraction, context recall, and vector embedding, ensuring robust, self-contained memory capabilities for RAG applications.

This skill processes clinical text to interpret laboratory results. It parses reference ranges (e.g., "135-145", "<5") and derives structured abnormal flags (low, normal, high, critical) for a given numeric value. It is unit-agnostic and respects explicit flags provided by the originating lab, making it crucial for structured clinical data extraction and interpretation workflows.