Skill UI

Run a GEPA learning cycle via metaharness learn to optimize a harness genome against a SWE-bench-style slice manifest. Supports dry-run for cost estimation and --run for explicit execution. Requires a metaharness repo checkout.

This tool performs static security scanning of declared MCP surfaces using the `harness mcp-scan` command. It reads configuration files like `.mcp/servers.json` and `.harness/claims.json` without executing any tools. The tool flags policy, permission, and dependency issues, exiting with code 1 if findings meet the specified severity threshold. It supports CI integration and graceful degradation when the harness binary is unavailable.

Scaffolds a new standalone AI agent harness via metaharness new, with templates and host presets. Dry-run by default, requires --confirm to write, and refuses to write inside the calling repo.

A comprehensive audit worker that integrates Open Infrastructure Architecture (OIA) manifest analysis, threat modeling, and MCP security scanning. It computes a composite worst-case severity score and persists time-stamped audit records in a memory namespace. Primarily designed for scheduled CI/CD pipelines to detect architectural drift and security regressions over time.

This skill evaluates repository readiness for agent harness adoption using a 5-dimension scorecard including harnessFit, compileConfidence, taskCoverage, toolSafety, and memoryUsefulness. It outputs JSON or table formats and supports alert thresholds. Gracefully degrades if metaharness is unavailable, ensuring CI integration stability for development workflows.

This tool runs the Darwin Shield security benchmark to evaluate detection harnesses against a 10-vuln/9-decoy corpus. It grades True Positive Rate (TPR) and False Positive Rate (FPR) against four baselines, outputting structured JSON results. Useful for benchmarking security detection capabilities in automated pipelines.

Calculates weighted similarity scores between two harness fingerprints using cosine, categorical, and Jaccard metrics. Outputs an overall score and per-component breakdown for comparing harnesses or detecting configuration drift. Pure TypeScript implementation without external dependencies.

This skill generates enterprise-grade threat models for MCP surfaces by invoking the harness binary. It categorizes security threats and outputs severity levels such as clean, low, medium, or high with detailed findings. Ideal for pre-launch security reviews and periodic audits to detect drift. Supports JSON or table formats and gracefully degrades if harness is unavailable.

This library provides comprehensive patterns for building robust Clinical Decision Support Systems (CDSS) integrated into Electronic Medical Records (EMR). It ensures patient safety by implementing critical checks such as drug interaction screening, weight/age/renal-adjusted dose validation, and standardized clinical scoring (e.g., NEWS2). The engine uses pure functions, guaranteeing high testability and reliability for critical medical insights.

A comprehensive guide detailing architectural patterns for developing robust Electronic Medical Record (EMR) and Electronic Health Record (EHR) systems. Covers critical areas like patient safety protocols, structured clinical workflows, drug interaction checking, audit trail implementation, and WCAG accessibility standards. Essential for building highly reliable and compliant healthcare IT solutions.

An automated verification system designed for critical healthcare application deployments (EMR/EHR). This harness enforces stringent patient safety standards by running multiple mandatory test gates, including Clinical Decision Support System (CDSS) accuracy, Protected Health Information (PHI) leakage prevention, and data integrity checks. A single failure in critical gates automatically blocks deployment, ensuring regulatory compliance and optimal patient safety in the CI/CD pipeline.

A comprehensive guide to building HIPAA, GDPR, and other global compliance systems for healthcare applications. This pattern outlines best practices for protecting Protected Health Information (PHI) and Personally Identifiable Information (PII) by implementing robust access controls, Row-Level Security (RLS), and mandatory audit trails. Essential for any feature handling patient or clinical data.