Ci Cd skills

This skill clusters JUnit failures into stable fingerprints to accelerate root-cause triage by ignoring noisy logs.

This skill summarizes GitHub Actions failure matrix across runs to help you spot unstable OS/runtime axes quickly.

This skill helps you accelerate end-to-end Playwright testing by generating, reviewing, and fixing flaky tests, and migrating from Cypress or Selenium.

This skill helps teams prepare and document Python projects for collaboration by providing templates, checklists, and dev container setups.

This skill automates end-to-end frontend deployment and go-live readiness for HyperEVM dApps from local dev to mainnet, including Vercel config and checks.

This skill performs pre-release checks for code quality, API health, deployment readiness, and versioning to ensure smooth launches.

This skill generates ViewModel tests ensuring codable round-trip, versioning stability, and multi-locale translation checks for FOSMVVM models.

This skill automates committing and pushing code to GitHub, with optional repository creation and deployment hints to streamline project deployment.

This skill analyzes GitHub Actions artifact usage from JSON exports and flags oversized or stale artifacts to protect CI budgets.

This skill helps you launch AI-driven agile projects with BMad Method, guiding setup, workflows, and development environments.

This skill enforces rigorous MLOps validation with typing, linting, testing, and security checks to improve code quality and reliability.

This skill helps you bootstrap MLOps projects with a modern Python toolchain, generating structure, config templates, and VS Code settings.

This skill analyzes GitHub Actions runs to identify and rank failure hotspots by pipeline phase, helping you prioritize fixes.

This skill audits GitHub Actions runtimes against thresholds, identifying near-timeout and timed-out jobs to prevent CI failures.

This skill submits and tracks PoYo Hailuo 02 video generation jobs via the API, handling model selection, payloads, and status polling.

This skill quantifies wasted GitHub Actions minutes from cancelled or timed-out runs to help you triage flaky workflows and save CI costs.

This skill guides end-to-end strategy development for quantitative trading, from hypothesis to validated production deployment and automated tearsheets.

This skill guides you through publishing a ClawHub skill from setup to verification, ensuring metadata accuracy and smooth deployment.

This skill generates reproducible fine-tuning run plans for transformer models, including hyperparameters, seeds, and model-card outputs for Hugging Face or

This skill helps you plan reproducible ML experiment runs with explicit parameters, metrics, and artifacts for consistent tracking.

This skill measures wasted GitHub Actions minutes from reruns to help fix flaky workflows with data.