Skill UI

This comprehensive reference architecture guides the integration of OpenEvidence into clinical decision support systems (CDS). It is designed for healthcare platforms needing evidence-based query processing, deterministic citation tracking, and full audit logging. Key considerations include HIPAA compliance, optimizing for sub-second response times in point-of-care workflows, and establishing robust data models and event pipelines.

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 simulates a senior documentation engineer, generating highly structured, evidence-based technical documentation. It processes codebases to create comprehensive wiki pages, mandating deep structural analysis, citing specific code paths (file:line), and incorporating mandatory architectural diagrams (Mermaid). Ideal for creating deep-dive system manuals, component guides, and technical deep dives with verifiable sources.

This skill simulates an expert software engineer and systems analyst. It is designed for deep, evidence-based understanding of complex codebases. Users can ask "how does X work" or request architectural reviews, ensuring every claim is grounded in actual code paths, data flows, and dependency chains, following a rigorous multi-iteration process.

Guides engineers through a disciplined four-phase debugging workflow so they investigate root causes, analyze patterns, test hypotheses, and implement fixes based on evidence before touching code.

Analyzes a code repository to generate a recommended, minimal set of read-only shell command permissions for Claude Code's settings.json. It automatically detects the project's tech stack (e.g., Python, Node.js, Go), build tools, and monorepo structure, ensuring a safe and evidence-based security baseline for new projects or auditing existing permissions.

A rigorous, security-focused code review process designed for Pull Requests (PRs), commits, and diffs. It moves beyond general reviews by focusing intensely on high-risk areas such as authentication, cryptography, external calls, and value transfer. The methodology is evidence-based, requiring detailed attack scenario modeling and generating comprehensive, auditable markdown reports to identify overlooked vulnerabilities and regressions.

Generates a precise, evidence-based installation plan for a project's component catalog (ECC). Instead of loading a full, noisy bundle, this skill analyzes the repository's actual code structure, dependencies, and CI/CD evidence to classify skills, rules, and commands into 'DAILY' (essential) and 'LIBRARY' (referenceable) buckets. It ensures only necessary components are active, optimizing the development environment.

This skill guides users through evidence-based terminal operations. It is designed for scenarios requiring direct command execution, Git status checks, debugging CI/build failures, and pushing narrow, verified fixes. It emphasizes following a structured, minimal-scope workflow and accurately reporting the repository's current state (e.g., local changes vs. pushed code).

This skill rigorously verifies all claims of completion, whether for a task, a bug fix, or a feature rollout. It prevents false assurances by demanding fresh, multi-faceted evidence, including full test suite results, comprehensive coverage reports, integration status, and validation commands. Use it before declaring a component ready for GO or accepting a sub-agent's success report.

A comprehensive debug bundle designed to collect diagnostic evidence from Glean enterprise search integrations. It systematically checks datasource configuration, indexing status, search quality metrics, and connectivity logs. This tool is crucial for troubleshooting complex issues like connector failures, stale indexed data, and permission-based search gaps without needing direct admin console access.

A specialized CLI alias designed to implement the PUA P9 protocol, simulating the role of a P9 tech lead for AI coding assistance (Codex/Claude Code). This tool helps users structure complex development tasks by focusing on writing precise prompts, managing execution steps, and strictly adhering to a defined professional protocol, minimizing direct code implementation unless reassigned. It ensures rigorous process management and evidence-based output.