agentic-browser-testing

SKILLWorkflowCommunity
v0.0.0petrkindlmannMITAktualisiert vor 2 Mon.Quelle →

Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and explores the app via the accessibility tree to assert outcomes — no pre-written script. Covers when intent-driven beats scripted, making agent runs deterministic (pinned model, temperature

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
75Repo-Sterne
1Clients
1Formate
vor 2 Mon.Letzte Aktualisierung
Skill
Autorpetrkindlmann
Version0.0.0
LizenzMIT
KategorieWorkflow
Formateskill.md
PromptNicht veröffentlicht
Kompatibilität
Claude✓ Unterstützt
Cursor
Copilot
ChatGPT
Gemini
Über

Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and explores the app via the accessibility tree to assert outcomes — no pre-written script. Covers when intent-driven beats scripted, making agent runs deterministic (pinned model, temperature 0, seeded data, bounded steps, explicit success assertion, snapshot-not-pixel), cost/latency contro

Schlagwörter
skillclaude