Skill UI

This skill converts unstructured documents (PDF, EPUB, DOCX, etc.) into actionable, structured agent skills. Instead of providing simple summaries, it deep-dives to extract core frameworks, mental models, key principles, techniques, and anti-patterns from educational material. Use this when you need to transform academic knowledge into a reusable, machine-readable toolkit for agents like Copilot CLI, Amp, or Claude Code.

This module provides a lazy adapter registry to seamlessly integrate OpenMed's clinical PII detection with major NLP frameworks like Microsoft Presidio, spaCy, and LangChain. It allows users to use OpenMed for enhanced PII recall, merge spans, or implement on-device PHI redaction guardrails without rewriting entire pipelines.

This skill constructs a comprehensive, chronologically sorted patient timeline from raw clinical entities extracted from medical notes. It specializes in temporal normalization, resolving both absolute and relative dates (e.g., 'two days after admission') against a defined anchor date. The resulting sorted sequence of diagnoses, medications, and procedures is ready for immediate visualization or seamless export to FHIR resources.

This diagnostic skill audits the entire local setup of Claude Code against several known, complex cache and cost bugs (CC#40524, B4, B5). It checks critical components including version compatibility, sentinel placeholders, session resuming logic, and attribution headers. Use this tool to ensure your development environment is optimized, stable, and minimizes unexpected operational costs and functional regressions.

This skill helps developers programmatically discover, filter, and inspect the entire OpenMed model registry. It allows users to find the correct model key for specific clinical tasks (e.g., diseases, oncology, PII detection), filter by language, size, or task, and review model metadata before loading. It pairs with `loading-openmed-models`.

A comprehensive, authorized methodology for security assessments covering cloud platforms, container runtimes, and Kubernetes clusters. It guides users through checking critical areas such as IAM privilege escalation, metadata SSRF, container escape paths, and granular RBAC misconfigurations, ensuring testing is systematic and non-destructive.

This tool provides a preferred, end-to-end method for modifying code in real-world repositories. It simulates a professional development workflow: cloning the target repository, running changes on a dedicated task branch, and critically, verifying the implementation through an independent red $\to$ green $\to$ regression test loop. It is designed for fixing GitHub issues, implementing new features, or adding functions to existing codebases, ensuring the structural integrity and correctness of the changes.

This skill maps chronic conditions extracted from clinical notes to CMS-HCC V28 categories. It estimates the Risk Adjustment Factor (RAF) score, which is crucial for Medicare Advantage payments. It serves as decision support for coders by identifying candidate HCCs, applying complex coding hierarchies, and checking for MEAT documentation evidence for human validation.

Provides decision support for mapping diagnoses and procedures extracted by OpenMed to standardized ICD-10-CM and ICD-10-PCS codes. This skill suggests candidate codes along with detailed clinical rationale, helping human coders narrow down options, route findings to specific chapters, and pre-fill encounter records. Note that the output is advisory and requires mandatory validation by a certified medical coder.

This specialized skill guides users through analyzing complex Active Directory Certificate Services (AD CS) abuse scenarios. It is essential for proving how a weakness in a template, CA policy, or issuance right can lead to unauthorized privilege acceptance (e.g., via PKINIT, Schannel). The workflow focuses on mapping the entire certificate issuance chain to the resulting accepted service path.

A specialized downstream skill for CTF-sandbox workflows. Used to analyze complex security challenges driven by AI agent interactions, prompt injection, or infrastructure vulnerabilities. Focuses on tracing control chains involving untrusted input, tool side effects, deployment drift, container runtime issues, and CI/CD supply chain provenance. Ideal for rigorous vulnerability assessment in modern, distributed systems.

A specialized skill for advanced runtime analysis of Android applications, primarily used in CTF and security research. It covers techniques like hooking specific system boundaries (JNI, WebView), bypassing security measures (SSL pinning, root checks), and recovering sensitive data or request signatures. Ideal for deep inspection of app trust boundaries and complex mobile logic.