Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Multi-agent code review that checks the current diff from 7 angles (spec compliance, modernization, bugs, CLAUDE.md rules, abstraction reuse, security, DB query performance) and produces a unified review. Works on branch diffs vs main or staged changes.
Deep investigation of CI/CD test failures - identifies root causes by analyzing logs, artifacts, git history, and source code
Analyzes Playwright trace archives (`trace.zip`) to diagnose test failures, flaky behavior, and unexpected UI states using trace steps, console output, network activity, and screenshots. Use when the user provides a trace path or trace artifact, asks why a Playwright or E2E test failed, wants root-cause analysis from CI artifacts, mentions the trace viewer, or asks whether a failure is flaky or an application bug.
Fetch and analyze Prow e2e pipeline failures for cloud-provider-azure. Downloads build logs, JUnit reports, and node-level artifacts from GCS, extracts failed tests, parses Ginkgo results, and surfaces cluster node info. Use when debugging a failing Prow e2e job, investigating a cloud-provider-azure-ccm-windows-capz or cloud-provider-azure-master-capz build, triaging CI failures, or when the user pastes a prow.k8s.io URL.
Generate test and suite specifications in the strict FinalRun YAML format. Handles automated test planning, folder grouping by feature, repo app configuration, environment-specific overrides in .finalrun/env/*.yaml, and validation via finalrun check.
Use the published FinalRun CLI to install, configure, validate, run, troubleshoot, and inspect reports for repo-local mobile test workspaces. Trigger this skill for requests involving finalrun, check, test, suite, doctor, runs, start-server.
Parse a Go e2e test from tests/e2e/, translate each step to kubectl and az CLI commands, and interactively replay the test against a live cluster. Use when the user wants to manually run, debug, or reproduce an e2e test case, or when they mention replaying a test, running a test against a cluster, or verifying e2e test behavior with kubectl and az.
Use when a Playwright E2E test fails and you have a trace archive to investigate. Optionally accepts a GitHub Actions pipeline link for additional CI context. Runs non-interactively.
When running as Zed's built-in coding agent in JETLS, prefer the faster built-in diagnostics tool for project instructions that require `jetls check` or `./scripts/selfcheck.sh`, with fallback to selfcheck when needed.
Audit Jetpack Compose performance by inspecting recomposition risk, state reads, stability, lazy layout keys, effects, derived state, allocation hotspots, and measurement evidence. Use when asked to diagnose slow Compose screens, review Compose code for performance issues, or propose targeted optimizations with verification steps.