agentic-browser-testing

SKILLWorkflowcommunauté
v0.0.0petrkindlmannMITMis à jour il y a 2 moisSource →

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 →
75Étoiles du dépôt
1Clients
1Formats
il y a 2 moisDernière mise à jour
Skill
Auteurpetrkindlmann
Version0.0.0
LicenceMIT
CatégorieWorkflow
Formatsskill.md
PromptNon publié
Compatibilité
Claude✓ Pris en charge
Cursor
Copilot
ChatGPT
Gemini
À propos

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

Mots-clés
skillclaude