# sap-sac-test-automation Designs Playwright test suites for SAP Analytics Cloud stories and dashboards: browser discovery first, a reviewed profile next, then repeatable runs gated in CI. - skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 515 installs · ★ 475 - Author: secondsky - License: GPL-3.0 · policy=link-only · description only; the file stays with the author - Source: https://github.com/secondsky/sap-skills/tree/HEAD/plugins/sap-sac-test-automation/skills/sap-sac-test-automation/SKILL.md - Updated: 2026-10-21 - HTML: https://affpapa.org/en/nevibecode/skills/sap-sac-test-automation ## What it does The skill works by one rule: discovery proposes, a person approves, Playwright executes, CI enforces. You and the agent map a story together, listing pages, widgets, locators, readiness markers and roles. That map becomes a dashboard profile draft plus a YAML scenario. Nothing gets written until you confirm file creation and pick a target folder, so `profiles//dashboard.yaml` and its neighbours stay drafts until then. For discovery you can use Microsoft Edge over CDP, Chrome DevTools MCP, the agent-browser CLI, or plain manual work. Name a browser or connection method and the skill checks that surface only. Private SAC content is not supposed to reach external services without approval. Scenarios stay free of selectors; interaction runs through component IDs from the profile, behind reusable adapters. Start CI with the safe packs: an auth check, a read-only smoke run, navigation, critical widget readiness. Planning writeback, comments, data actions and visual baselines belong in controlled or nightly stages. A live tenant with SSO and writeback needs tenant-specific evidence before anyone calls the run validated. Adding browser tooling or MCP servers that touch SAC credentials makes a dependency risk review worthwhile. ## Requirements - Works with: Playwright, Chrome ## Install ### Claude Code (native platform) 1. **Skills CLI (Vercel)** ```bash npx skills add secondsky/sap-skills --skill sap-sac-test-automation -a claude-code ``` 2. **Manually: put the files in place** - File: `~/.claude/skills/sap-sac-test-automation/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/sap-sac-test-automation/ ### Codex 1. **Skills CLI (Vercel)** ```bash npx skills add secondsky/sap-skills --skill sap-sac-test-automation -a codex ``` 2. **Manually: put the files in place** - File: `.agents/skills/sap-sac-test-automation/SKILL.md` — For all projects use ~/.agents/skills/ ### Cursor 1. **Skills CLI (Vercel)** ```bash npx skills add secondsky/sap-skills --skill sap-sac-test-automation -a cursor ``` 2. **Manually: put the files in place** - File: `.cursor/skills/sap-sac-test-automation/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/ ### GitHub Copilot 1. **GitHub CLI** ```bash gh skill install secondsky/sap-skills sap-sac-test-automation ``` 2. **Manually: put the files in place** - File: `.github/skills/sap-sac-test-automation/SKILL.md` ### Gemini CLI 1. **Skills CLI (Vercel)** ```bash npx skills add secondsky/sap-skills --skill sap-sac-test-automation -a gemini-cli ``` 2. **Platform CLI** ```bash gemini skills install https://github.com/secondsky/sap-skills --path plugins/sap-sac-test-automation/skills/sap-sac-test-automation ``` ### Windsurf (Devin Desktop) **Manually: put the files in place** - File: `.devin/skills/sap-sac-test-automation/SKILL.md` — The legacy .windsurf/skills/ path still works ### OpenCode **Skills CLI (Vercel)** ```bash npx skills add secondsky/sap-skills --skill sap-sac-test-automation -a opencode ``` ### Claude.ai **Claude.ai** - Zip the folder and upload it in Settings → Capabilities → Skills Where a file is given instead of a command, copy the files from the source to that path: https://github.com/secondsky/sap-skills/tree/HEAD/plugins/sap-sac-test-automation/skills/sap-sac-test-automation/SKILL.md ## When to use it - map widgets and locators on a SAC story - draft a dashboard profile and YAML scenario for later runs - move manual dashboard checks to deterministic Playwright tests - separate safe read-only checks from planning writeback tests - package a trace, screenshots and visual diff for a failed run ## Example prompts - Run read-only discovery on this SAC story and draft a dashboard profile, but do not create files yet - Build a `read-only-smoke.yaml` scenario for the story and show which locators come from the profile - Triage the failed run and attach the trace, screenshots and root-cause label ## Similar - [improve-codebase-architecture](https://affpapa.org/en/nevibecode/skills/improve-codebase-architecture.md) — skill · 1163035 installs - [design-taste-frontend](https://affpapa.org/en/nevibecode/skills/design-taste-frontend.md) — skill · 678700 installs - [tdd](https://affpapa.org/en/nevibecode/skills/tdd.md) — skill · 1141062 installs - [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs - [agent-browser](https://affpapa.org/en/nevibecode/skills/vercel-labs-agent-browser.md) — skill · 1200000 installs - [prototype](https://affpapa.org/en/nevibecode/skills/prototype.md) — skill · 986201 installs From the same set: [secondsky/sap-skills](https://affpapa.org/en/nevibecode/by/secondsky/sap-skills.md) — 40 cards --- NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md