Skill UI

This comprehensive checklist guides the safe and robust deployment of Mistral AI integrations to a production environment. It covers critical operational steps, including secure credential management, rigorous code quality gates, establishing health endpoints, implementing circuit breakers for resilience, executing gradual rollouts, and defining emergency rollback procedures to ensure system stability and high availability.

Automates the Continuous Integration and Continuous Deployment (CI/CD) process for OpenEvidence clinical decision support integrations. This setup ensures that unit tests (using mocked evidence queries and citations) and live API connectivity tests are run automatically on every pull request and merge to main. It validates critical functions like query formatting, evidence parsing, citation extraction, and response quality scoring, maintaining high reliability for medical AI applications.

A specialized skill designed for agents to proactively identify, analyze, and strategize high-impact contributions within trending Open Source repositories. It systematically performs repository discovery, extracts targeted issues (like 'help wanted' or 'good first issue'), and conducts deep feasibility analysis (including mergeability and complexity). Finally, it generates a structured 'Contribution Dossier' with actionable plans, significantly accelerating the process of becoming a top-tier OSS contributor.

Runs external LLM CLIs (OpenAI Codex or Google Gemini) to review uncommitted changes, branch diffs, or specific commits, providing an independent second opinion before merges or releases.

A comprehensive tool designed to audit the quality, relevance, and redundancy of all Claude skills and commands. It supports two modes: a rapid incremental scan for recently changed skills, and a deep full stocktake using AI judgment and expert checklists to assess viability (Keep, Improve, Update, Retire, Merge).

This skill guides the integration of Windsurf workflows into CI/CD pipelines (like GitHub Actions). It provides comprehensive mechanisms for validating configuration files and enforcing AI code quality standards. Use it to automate policy checks, detect hardcoded secrets, ensure sufficient test coverage for new files, and manage complex config deployments across repositories, ensuring highly reliable and compliant code merges.

This skill integrates advanced AI assistance into Git workflows within the Windsurf IDE. It automates complex source control tasks, including generating descriptive commit messages from staged changes, suggesting optimal branch names, assisting with merge conflict resolution, and streamlining common Git operations. Ideal for developers managing version control or needing robust support for collaborative coding environments.

A comprehensive, multi-phase checklist designed for the systematic rollout of AI coding assistants (like Windsurf) to development teams or entire enterprises. It covers critical areas including workspace configuration, security hardening (SSO/SAML, secret management), establishing team AI policies, structured developer onboarding, key performance indicator (KPI) monitoring, and emergency rollback procedures.

Guides branch completion by verifying tests, identifying the base branch, presenting merge/PR/keep/discard options, and cleaning up worktrees when appropriate.

Explains when to call the code-reviewer subagent, how to collect SHAs, fill the template, and act on its feedback so every task, feature, or merge meets quality expectations.

This advanced pipeline orchestrates complex feature development based on Request for Comments (RFCs). It breaks down monolithic changes into small, independently verifiable work units, managing dependencies through a Directed Acyclic Graph (DAG). It includes multiple quality gates, dedicated unit testing, and a safe merge queue to ensure robust integration and controlled deployment.

Runs AgentHub's init→baseline→spawn→eval→merge workflow in one command, letting teams define tasks, agents, metrics, and templates to automate evaluation and merging the winning agent.