Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Run user-facing Instatic E2E audits with a real browser and disposable local data. Use when asked to test the app as a user, run an agent-browser pass, perform a fresh-install smoke test, audit UX friction, verify setup/login/edit/publish/public-page flows, retest E2E issues, or update the Instatic E2E protocol and feature matrix.
Triage a failing Shopware nightly / multi-job PHPUnit CI run (e.g. integration-major). Extract every failing test from the run's job logs, resolve each to its owning domain via #[Package] markers, cluster failures by error signature into root causes, verify opaque clusters with a local Docker reproduction, then file one GitHub issue per domain plus a parent tracking issue — routing collateral failures to the root-cause owner. Use when the user links a failing Actions run or job, asks to "identify all failing tests" from a nightly, asks to triage integration-major / a red nightly, or wants CI failures grouped into per-team issues.
Write or update Shopware PHPUnit tests. Use when adding or changing tests under tests/ (unit, integration, migration, BC) — including data providers, feature flags, and coverage annotations.
Diagnose and fix a Shopware 6 GitHub issue, or improve an existing Bugfixer pull request after maintainer feedback. Use when the user asks to fix an issue, create a bugfix PR, handle a qi/sw-bugfixer issue, improve a Bugfixer PR, or react to /sw-bugfixer feedback.
Review a Shopware 6 GitHub pull request or local diff. Use when the user asks to review a PR, references a PR by number ("#16638"), asks for a focused security / architecture / code-style / UX / open-source review, or when a PR needs automated reviewer feedback.
Triage a Shopware 6 GitHub bug issue. Read the issue body, identify the affected code area via rg/git/gh, check for related fixes or duplicates, then emit a Markdown summary with disposition, severity, suggested domain labels, confidence, reasoning, and supporting evidence. Use when the user asks to triage, classify, label, or assess a Shopware issue, when they reference an issue by number (e.g. "#16599"), or when a new issue arrives that needs an initial dispositioning.
以 subagent 启动的 UI 挑剔用户评审。Use when the user, AGENTS, or the current task requires “挑剔的用户”. 该 skill 会分别扮演新用户与老用户，对界面的 self explain、明确性、直觉性、效率、布局和操作习惯提出高标准意见；默认给出 5-10 条有效建议，必要时结合 ui-test 与截图检查，并把意见记入 .memory/YYYY-MM-DD/picky-user。
以 subagent 启动的 UI 漫游与异常发现技能。Use when the user, AGENTS, or the current task requires “UI漫游者”. 该 skill 负责系统性地把目标页面能点的都点一遍、把上下左右能滑的都滑一遍，重点发现空白页、越界、裁切、错位、布局失衡、状态切换异常等问题；必要时结合 ui-test 与截图检查，并把意见记入 .memory/YYYY-MM-DD/ui-volayor。
Test that your AI agent stays observational and doesn't give prescriptive advice in regulated domains (healthcare, finance, legal). Creates scenario tests for boundary enforcement and red team tests for adversarial probing. Use when your agent advises but must not prescribe.