CI/CD principles — pipeline taxonomy, trigger design, supply-chain hygiene (SHA-pinned actions), OIDC cloud auth, caching (and the setup-* cache-key pitfalls that silently disable it), matrix strategy, test gates, release automation, deployment strategies, and running CI locally with act. Suggestion-mode (trade-offs over mandates). GitHub Actions recipes in RECIPES.md. Use when designing, reviewing, or scaffolding CI/CD workflows.
Generate Playwright tests. Use when user says "write tests", "generate tests", "add tests for", "test this component", "e2e test", "create test for", "test this page", or "test this feature".
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with Azure AI, including voice assistants, voice-enabled chatbots, real-time speech-to-speech translation, voice-driven avatars, or any WebSocket-based audio streaming with AI models. Supports Server VAD (Voice Activity Detection), turn-based conversation, function calling, MCP tools, avatar integration, and transcription.
Wenn es um Geldwaesche: Verhandlung, Vergleich und Eskalation in Geldwäscheprävention, AML und KYC geht: entwickelt Verhandlungsziel, Vergleichskorridor und Eskalationspfad; liefert eine Verhandlungs- oder Eskalationslinie mit Optionen.
Run frontclippy against a local HTML file, live URL, snapshot JSON, suite, or manifest and summarize the findings. Use when the user asks to audit a UI, inspect frontclippy output, emit SARIF, or run capture plus analysis.
Use before and after changing code in a git repo: collects the change's impact list (what it can break, and what new behavior must fit), checks it against the per-repo behavior map with ,behavior-map, maps unmapped areas, and maintains entries (area init, update, add, refresh, promote, resolve).
Use when a raw or admitted request should become a minimum repository intent for later shaping, without creating an RFC, delivery brief, spec, or executable queue item.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
Reviews a GitHub PR for correctness, security, design, and maintainability. Auto-loads project conventions from rules and AGENTS.md files based on changed file paths. Use when asked to review a PR, check a PR, or give feedback on a pull request.
Use only when the user explicitly asks to use Cockpit, invokes a Cockpit command or skill, or asks to install, configure, develop, debug, inspect, or verify Cockpit itself; do not activate for generic app, Flutter, UI, or E2E work.
Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning.
Version catalog strategy, dependency management, BOMs, and version constraints for Java/Gradle projects. Covers version centralization, never-downgrade policy, bundle patterns, resolution strategies, and compatibility matrices.