Index of DecisionsAI browser automation — Playwright, browser-use, browser-qa, and workflow integration across Codex, Cursor, Claude, and Pi.
Scanned 9/10/2026
Install to Claude Code
Skills Directorynpx -y skills add tensology/decisionsai --skill decisions-browser-stack --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Decisions Browser Stack?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/tensology-decisions-browser-stack)More formats (shields.io, HTML) on the badges page.
---
name: decisions-browser-stack
description: Index of DecisionsAI browser automation — Playwright, browser-use, browser-qa, and workflow integration across Codex, Cursor, Claude, and Pi.
---
# Decisions Browser Stack
DecisionsAI projects browser skills into every installed harness on setup/start.
## Layers
| Layer | What it is |
|-------|------------|
| **Playwright** | Decisions venv + Chromium; Hermes tool + workflow steps |
| **browser-use** | Optional Python package (`pip install browser-use`) for agentic browsing |
| **ECC QA skills** | browser-qa, webapp-testing, e2e-testing |
| **RTK** | Shrinks noisy test/git output in agent hooks |
## MCP / API
- **fal.ai** — see `~/.decisions/harness/mcp-recommendations.json` for fal-ai MCP template (`FAL_KEY`)
- **Higgsfield** — not integrated in Decisions yet; use fal-ai-media or manual export
## Defaults in workflows
Workflow `pre_chain` merges ponytail, fallow (JS/TS projects), `decisions-harness-stack`, `browser-qa`, and `decisions-playwright`.
## Evidence
Always return screenshots, audit JSON, or URLs checked when closing a browser step.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
