Skill UI

This SDK provides comprehensive, production-ready patterns for interacting with the OpenEvidence clinical evidence API. It enables developers to efficiently query medical literature, retrieve clinical guidelines, and generate evidence-based recommendations. Key features include a singleton client for consistent authentication, robust error wrappers (handling retries, invalid keys), and structured data models designed to ensure audit compliance and detailed citation provenance in complex healthcare applications.

This skill guides implementing robust code signing for software artifacts (binaries, packages, containers). It ensures integrity and authenticity throughout the entire software supply chain. Learn to use traditional methods like GPG and modern, keyless approaches like Sigstore (cosign) to establish trust chains, verify provenance, and meet compliance standards (e.g., SLSA).

This guide details implementing robust container image provenance verification using Cosign, a Sigstore tool. It covers key-based and keyless (OIDC) signing methods, enabling secure supply chain practices. Users can sign images, attach critical attestations (such as SBOMs and vulnerability scans), and enforce verification in CI/CD pipelines and Kubernetes environments to ensure high integrity and trust.

Harbor is an open-source container registry designed for robust security and compliance. This guide details the comprehensive workflow for securing your container ecosystem by implementing advanced features such as vulnerability scanning (Trivy), image signing (Notary/Cosign), Role-Based Access Control (RBAC), and content trust policies. Learn how to enforce image provenance and maintain strict access control in Kubernetes environments.

This comprehensive guide outlines the end-to-end security lifecycle for Kubernetes applications deployed via Helm. It covers critical topics such as chart provenance verification (GPG signing), template scanning (using tools like kubesec and checkov), enforcing strict security contexts, managing secrets securely (ExternalSecrets), and defining robust RBAC rules for CI/CD pipelines.

AKF is the native metadata format specifically designed for tracking AI-generated or AI-modified content. It allows users to stamp files (including DOCX, PDF, images, and code) with detailed trust scores, source provenance, and compliance metadata. This tool is essential for professional workflows requiring strict auditing, compliance assurance, and verifiable data lineage, especially concerning regulations like the EU AI Act, HIPAA, and SOX.

This guide details how to implement secure, keyless software signing using the Sigstore ecosystem components (Cosign, Fulcio, Rekor). It establishes cryptographic provenance for container images and binaries by binding identity via OIDC, ensuring verifiable integrity and tamper-proofing throughout the CI/CD supply chain.

This skill provides robust mechanisms to verify the integrity of AI agent plugins, tools, and dependencies. It generates deterministic SHA-256 manifests (INTEGRITY.json) for all components, allowing users to detect unauthorized modifications, track provenance, and ensure that deployed assets match their published versions. Use this during CI/CD pipelines, code review, and pre-production promotion to secure the entire agent ecosystem.

Utilize advanced media intelligence to analyze audio, image, video, and text for synthetic manipulation and AI-generated content. This skill detects deepfakes, traces the original AI synthesis source, applies and detects watermarks, verifies speaker identity, and provides comprehensive media provenance analysis, ensuring media authenticity claims are rigorously supported.

This skill provides a comprehensive workflow for querying documented, authoritative public APIs across scientific, environmental, and medical domains (e.g., NASA, PubChem, USGS). It ensures that data retrieval is reproducible, auditable, and traceable by defining explicit endpoints, handling pagination, and verifying data provenance, rather than relying on general knowledge inference.

This skill integrates 10 major academic literature APIs (including PubMed, arXiv, OpenAlex, Crossref, etc.). It guides users on converting complex research intents into reproducible, verifiable lookups for papers, preprints, citations, and open-access full texts. It ensures results include verifiable provenance and follows a rigorous workflow for maximum accuracy in scholarly research.

This tool functions as a post-task epilogue, designed to audit and record the entire research journey. It scans the conversation history at the end of a coding or research session to extract critical research artifacts, including decisions, experiments, dead ends, claims, heuristics, and major pivots. It systematically writes this provenance data into the structured `ara/` directory, ensuring a faithful and auditable trace of how the project truly evolved.