Install command
Provided
skillsFirst-partyReview first Safety ✓ Privacy ✓
Browser Agent Workflow Automation Skill
Build robust browser automation workflows for AI agents with deterministic selectors, retries, and safe action boundaries.
HarnessClaude CodeCodexWindsurfGeminiCursorCLI
Level:advancedType:generalVerified:draft
Review first — review before installing
Open the source and read safety notes before installing.
Citation facts
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
- Source URLs
- https://playwright.dev/docs/best-practices, https://github.com/JSONbored/awesome-claude/blob/main/content/skills/browser-agent-workflow-automation.mdx
- Package URL
- /downloads/skills/browser-agent-workflow-automation.zip
- Package SHA256
- 6aa6e8c44b99d7cf368236a7567453abefb91476ba74d431c992b409c5cfc8f3
- 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.
- 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.
- Platform compatibility
- claude-code (native-skill), codex (native-skill), windsurf (native-skill), gemini (native-skill), cursor (adapter), cli (manual-context)
- Author
- JSONbored
- Claim status
- unclaimed
- Last verified
- 2026-04-10
Decision playbook
Ready to evaluate for your workflow
Signals are comparatively strong, but you should still validate source, privacy posture, and package provenance for your environment.
Compare context
Selected
0
Current score
96
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
CompleteConfirm ownership and provenance before trusting install instructions.
- Done
Source link availableRequired
Open the canonical repository and verify ownership.
- Done
Source provenance statusRequired
Marked as first-party.
- Done
Metadata reviewed
Registry metadata indicates a reviewed listing.
Safety and privacy checks
CompleteValidate risk disclosures before installation or API wiring.
- Done
Safety notes presentRequired
Review the listed safety guidance before running commands.
- Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
- Done
Trust level risk gateRequired
Trust level does not block evaluation.
Package and install checks
CompleteCheck package metadata and artifact integrity signals.
- Done
Install payload available
Install or copy payload is available for review.
- Done
Package verification flag
Package marked verified.
- Done
Checksum metadata
SHA-256 hash is present.
Compare-driven decision checks
Needs reviewUse compare context to validate trade-offs before adoption.
- Pending
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
- Pending
Baseline comparison available
No baseline peer selected yet.
- Pending
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Package install
Copy-ready — paste the snippet to get started.
Config snippet
Not provided
Copy snippet
Provided
Prerequisites
3 to clear
Platforms
6 listed
Difficulty
75/100
Adoption plan
Balanced adoption plan
Current risk score 0/100. Use staged verification before broader rollout.
Pre-adoption checks
Validate source and review signals before any execution.
- Done
Confirm source provenanceRequired
Source URL/provenance metadata is present.
- Done
Confirm metadata review state
Listing has review metadata.
- Done
Verify install payload
Install/config payload exists and can be inspected.
Security checks
Confirm safety, privacy, and package integrity signals.
- Done
Review safety notesRequired
Safety notes are present.
- Done
Review privacy notesRequired
Privacy notes are present.
- Done
Verify package integrity metadata
Package verification/checksum metadata is available.
Rollout
Adopt in controlled steps based on the selected plan.
- Pending
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
- Pending
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
- Pending
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Evidence readiness matrix · balanced
Required evidence gates are covered (6/6 signals complete).
Source provenance
PresentSource repository/provenance is listed.
Required in this preset
Metadata review
PresentReview metadata is present.
Required in this preset
Safety notes
PresentSafety notes are present.
Required in this preset
Privacy notes
PresentPrivacy notes are present.
Optional in this preset
Package integrity
PresentPackage integrity metadata is present.
Optional in this preset
Install payload
PresentInstall payload is available.
Required in this preset
Required evidence gates are covered for this preset.
Decision timeline
Decision timeline · balanced
6/6 steps complete with no blocking gaps for this preset.
triage
Confirm source provenanceRequired
Source/provenance metadata is available.
triage
Check metadata review statusRequired
Review metadata is available.
verify
Review safety notesRequired
Safety notes are available.
verify
Review privacy notes
Privacy notes are available.
verify
Validate package integrity metadata
Package integrity metadata is available.
rollout
Verify install payload and commandsRequired
Install payload is available.
No required blockers for this timeline preset.
Prerequisite readiness
Prerequisite readiness
3 prerequisites to line up before setup. Have accounts and credentials ready first.
Account & credentials1General2
Safety & privacy surface
Safety & privacy surface
2 safety and 2 privacy notes across 3 risk areas. Review closely: credentials & tokens.
- SafetyExecution & processesCan design automation for live browsers, accounts, workflows, or infrastructure; use staging targets and human approval before destructive or account-write actions.
- SafetyCredentials & tokensKeep API tokens and service credentials least-privileged, and verify generated runbooks before scheduling or unattended execution.
- PrivacyData retentionInputs and outputs can include browser state, account metadata, workflow payloads, infrastructure inventory, logs, and operational screenshots.
- PrivacyCredentials & tokensRedact credentials, session data, customer records, internal hostnames, and private workspace details before sharing prompts or artifacts.
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.
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.
Prerequisites
- Target web workflow with clear start and success states
- Ability to run browser automation in local or CI environment
- Access to auth/session strategy if login is required
Schema details
- Install type
- package
- Reading time
- 7 min
- Difficulty score
- 75
- Troubleshooting
- Yes
- Breaking changes
- No
Package metadata
- Package verified
- Yes
- SHA-256
- 6aa6e8c44b99d7cf368236a7567453abefb91476ba74d431c992b409c5cfc8f3
Skill and platform metadata
- Skill type
- general
- Skill level
- advanced
- Verification
- draft
- Verified at
- 2026-04-10
Retrieval sources
https://playwright.dev/docs/best-practices
Tested platforms
ClaudeCodexOpenClawCursorWindsurfGemini
| 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 |
Full copyable content
# 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 actionsAbout this resource
Overview
This 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.
Compatibility
Native
- Claude Code / Claude: native skill usage via
SKILL.md. - Codex/OpenAI workflows: compatible with Agent Skills-style
SKILL.mdcontent as reusable workflow instructions.
Manual Adaptation
- Gemini CLI: native skill usage via
.gemini/skills/<skill-name>/SKILL.mdor.agents/skills/<skill-name>/SKILL.mdwhere supported. - Cursor: use the generated
.cursor/rules/*.mdcadapter for project rules. - OpenClaw and similar agents: use the same skill content as a reusable prompt/workflow file when native skill import is unavailable.
Prerequisites
- Clearly defined desired outcome and termination condition
- Stable environment (staging/prod) with acceptable automation policy
- Credential/session strategy for authenticated steps
Workflow Blueprint
- Define start state and target success state
- Use resilient selector hierarchy (semantic selectors first)
- Add validation checkpoints between major steps
- Use bounded retries with explicit failure reasons
How to Use This Skill
Prompt Pattern
Apply browser agent workflow automation skill.
Deliver:
1) deterministic step plan,
2) selector map,
3) retry/timeout policy,
4) failure recovery playbook.
Execution Flow
- Map the workflow into atomic actions and checks.
- Choose reliable selectors and alternates.
- Add guardrails for destructive actions (confirmations/human gate).
- Instrument logs/screenshots for every failed checkpoint.
- Run repeatedly to validate stability before shipping.
Troubleshooting
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.
Knowledge Freshness
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.
Retrieval Sources
Output Contract
- Return a concrete plan with implementation order.
- Provide production-ready commands/config/code snippets (not placeholders).
- Include explicit assumptions and unresolved risks.
- Include a verification checklist with pass/fail criteria.
Quality Gates
- All commands are copy/paste ready.
- Security-sensitive steps call out secret handling and least privilege.
- Version-sensitive guidance cites current docs used.
- Rollback path is included for risky changes.
- Final output includes quick validation commands/tests.
Source citations
Add this badge to your README
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)How it compares
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 | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI |
| 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 |
Related guides
Source-backed guides for putting this to work.
guides
Creating Output Styles for Non-Coding Claude Workflows
Build Claude Code output styles for PM, support, and writing workflows without coding defaults.
Review firstSource-backedReview firstAdded 1mo ago
Safety ✓ Privacy ✓by kiannidevFeatured in
- Best list: Claude skills for production teamsOpen 4 picks in the interactive comparison tool
- Best list: Agent workflow starter kitsOpen 4 picks in the interactive comparison tool
- Best list: Safer install paths for Agent SkillsOpen 4 picks in the interactive comparison tool
- Best list: Claude skills for design and frontend workOpen 4 picks in the interactive comparison tool
- Best list: Raycast-friendly Claude workflow resourcesOpen 4 picks in the interactive comparison tool
- Best list: Prompt and context engineering resourcesOpen 4 picks in the interactive comparison tool
- Best list: Claude Code workflow starter kitOpen 4 picks in the interactive comparison tool
Signals
Loading live community signals…
More like this, weekly
A short, calm digest of reviewed Claude resources. Unsubscribe any time.