Build robust browser automation workflows for AI agents with deterministic selectors, retries, and safe action boundaries.
Open the source and read safety notes before installing.
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
Decision playbook
Signals are comparatively strong, but you should still validate source, privacy posture, and package provenance for your environment.
0
96
—
No baseline selected
No major trust-signal divergence detected in the current selection.
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Source provenance statusRequired
Marked as first-party.
Metadata reviewed
Registry metadata indicates a reviewed listing.
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Trust level risk gateRequired
Trust level does not block evaluation.
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Package verification flag
Package marked verified.
Checksum metadata
SHA-256 hash is present.
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Baseline comparison available
No baseline peer selected yet.
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Copy-ready — paste the snippet to get started.
Adoption plan
Current risk score 0/100. Use staged verification before broader rollout.
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Confirm metadata review state
Listing has review metadata.
Verify install payload
Install/config payload exists and can be inspected.
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Review privacy notesRequired
Privacy notes are present.
Verify package integrity metadata
Package verification/checksum metadata is available.
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Required evidence gates are covered (6/6 signals complete).
Source repository/provenance is listed.
Required in this preset
Review metadata is present.
Required in this preset
Safety notes are present.
Required in this preset
Privacy notes are present.
Optional in this preset
Package integrity metadata is present.
Optional in this preset
Install payload is available.
Required in this preset
Required evidence gates are covered for this preset.
Decision timeline
6/6 steps complete with no blocking gaps for this preset.
triage
Source/provenance metadata is available.
triage
Review metadata is available.
verify
Safety notes are available.
verify
Privacy notes are available.
verify
Package integrity metadata is available.
rollout
Install payload is available.
No required blockers for this timeline preset.
Prerequisite readiness
3 prerequisites to line up before setup. Have accounts and credentials ready first.
Safety & privacy surface
2 safety and 2 privacy notes across 3 risk areas. Review closely: credentials & tokens.
| Platform | Support | Install path |
|---|---|---|
| claude-code | Native | .claude/skills/<skill-name>/SKILL.md |
| codex | Native | .agents/skills/<skill-name>/SKILL.md |
| windsurf | Native | .windsurf/skills/<skill-name>/SKILL.md |
| gemini | Native | .gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md |
| cursor | Adapter | .cursor/rules/<skill-name>.mdc |
| cli | Manual | AGENTS.md or tool-specific context file |
# Trigger
"Apply browser agent workflow automation skill for this task."
# Required output
1) Step-by-step browser plan with checkpoints
2) Selector strategy and fallback hierarchy
3) Retry and timeout policy
4) Safety boundaries for destructive actionsThis skill provides a practical framework for building browser-driven agent workflows that survive real-world UI variability. It prioritizes deterministic automation, explicit checkpoints, and safe failure handling instead of brittle click-recording scripts.
SKILL.md.SKILL.md content as reusable workflow instructions..gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md where supported..cursor/rules/*.mdc adapter for project rules.Apply browser agent workflow automation skill.
Deliver:
1) deterministic step plan,
2) selector map,
3) retry/timeout policy,
4) failure recovery playbook.
Issue: Flaky failures on dynamic pages
Fix: replace brittle selectors with role/label/text anchors and add readiness checks.
Issue: Infinite retries hide root cause
Fix: cap retries and emit structured failure reasons after each attempt.
Issue: Automation performs unsafe actions
Fix: require explicit confirmation gates for irreversible operations.
Treat tooling details as time-sensitive. Re-validate APIs, limits, pricing, auth models, and deployment flags immediately before implementation. If docs conflict with prior memory, follow current official docs and release notes.
Show that Browser Agent Workflow Automation Skill is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/skills/browser-agent-workflow-automation)Browser Agent Workflow Automation Skill side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
3 trust signals differ across this comparison (Package trust, Source provenance, Submitter).
| Field | Build robust browser automation workflows for AI agents with deterministic selectors, retries, and safe action boundaries. Open dossier | Build resilient browser automations using Playwright MCP with robust selectors, retries, and deterministic task execution. Open dossier | Write and maintain reliable end-to-end tests with Playwright — Microsoft's browser automation library that auto-waits for actionable elements and runs the same suite against Chromium, Firefox, and WebKit. Open dossier | Expert skill for reviewing Playwright trace artifacts, screenshots, action timelines, network events, retries, and CI evidence to classify flaky browser test failures without guessing from logs alone. Open dossier |
|---|---|---|---|---|
| Next steps | ||||
| Trust | ||||
| Review status | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed |
| Package trustDiffers | Package verified2026-04-10 | Package verified2026-04-10 | Package verified2025-10-16 | Package not verified |
| Source provenanceDiffers | Source-backed | No submission link | No submission link | Source-backed |
| SubmitterDiffers | — | — | — | JSONbored |
| Install risk | Review first | Low risk | Low risk | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | — | — | — | — |
| Category | skills | skills | skills | skills |
| Source | First-party | First-party | First-party | Source-backed |
| Author | JSONbored | JSONbored | JSONbored | JSONbored |
| Added | 2026-04-10 | 2026-04-10 | 2025-10-16 | 2026-06-05 |
| Platforms | ||||
| Harness | ||||
| Source repo | — | — | — | — |
| Safety notes | ✓Can design automation for live browsers, accounts, workflows, or infrastructure; use staging targets and human approval before destructive or account-write actions. Keep API tokens and service credentials least-privileged, and verify generated runbooks before scheduling or unattended execution. | ✓Can design automation for live browsers, accounts, workflows, or infrastructure; use staging targets and human approval before destructive or account-write actions. Keep API tokens and service credentials least-privileged, and verify generated runbooks before scheduling or unattended execution. | ✓`npx playwright install --with-deps` downloads browser binaries (~500 MB for Chromium, Firefox, and WebKit) from Playwright's CDN and on Linux installs system-level packages. Review your network and environment policies before running in restricted infrastructure. Generated tests have full browser-level access to any URL they target. Review test scripts before running them against authenticated sessions or production environments — Playwright can submit forms, click buttons, and make network requests as a real user. | ✓Trace artifacts can include screenshots, DOM text, URLs, request metadata, console output, and application state; review them before sharing publicly. Do not fix a trace-only symptom by adding broad waits, retries, or timeouts unless the trace evidence supports that change. Keep destructive browser actions and production-like credentials out of replayed failure reproduction. |
| Privacy notes | ✓Inputs and outputs can include browser state, account metadata, workflow payloads, infrastructure inventory, logs, and operational screenshots. Redact credentials, session data, customer records, internal hostnames, and private workspace details before sharing prompts or artifacts. | ✓Inputs and outputs can include browser state, account metadata, workflow payloads, infrastructure inventory, logs, and operational screenshots. Redact credentials, session data, customer records, internal hostnames, and private workspace details before sharing prompts or artifacts. | ✓Playwright runs entirely on your local machine. Traces, screenshots, and HTML test reports are written to local disk only and are not uploaded to Microsoft or any external service. Trace files and failure screenshots may capture sensitive content from the application under test (form data, rendered PII, session tokens visible in URLs). Store and rotate these files appropriately. | ✓Playwright traces can expose user names, emails, tokens in URLs, internal hostnames, test data, screenshots, and API payload fragments. Public PR comments should summarize trace evidence without uploading private trace files or pasting sensitive network details. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | — | — | — | — |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Source-backed guides for putting this to work.
Build Claude Code output styles for PM, support, and writing workflows without coding defaults.
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.