mikeparcewski/agent-browser
skills/qe/agent-browser/SKILL.md
Browser automation skill with priority-ordered CLI discovery. Detects the best available browser automation tool in the system PATH and provides usage patterns for Playwright, Puppeteer, Cypress, and Selenium WebDriver. Use when: - Taking screenshots or extracting page content - Automating web forms and UI interactions - Accessibility audits - Web scraping for AI agents - Testing web applications - End-to-end test execution
$ install --global
skillsauthnpx skillsauth add mikeparcewski/wicked-garden agent-browserInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 19, 2026, 4:09 AM16.4s5 files scanned
SKILL.md
- name:
- agent-browser
- description:
- |
- portability:
- portable
Browser Automation
Detects and uses the best available browser automation CLI in your environment.
CLI Discovery
Before executing browser automation, detect which tool is available:
# Priority order: playwright > puppeteer > cypress > selenium-webdriver
for tool in playwright puppeteer cypress selenium-webdriver; do
if command -v "$tool" > /dev/null 2>&1; then
echo "Using: $tool"
break
fi
# Check via npx for Node-based tools
if command -v npx > /dev/null 2>&1; then
if npx "$tool" --version > /dev/null 2>&1; then
echo "Using: npx $tool"
break
fi
fi
done
Stake level: Medium — inform the user which tool was selected.
If none found: Recommend Playwright installation (see below).
Pattern: This follows the integration-discovery CLI detection pattern. See integration-discovery refs/cli-detection.md for the full decision policy.
Priority Order
| Priority | Tool | Why | |----------|------|-----| | 1 | Playwright | Best AI-agent support, cross-browser, built-in waiting | | 2 | Puppeteer | Mature API, Chrome-focused, wide adoption | | 3 | Cypress | Test-focused, good DX, component testing | | 4 | Selenium WebDriver | Legacy support, multi-language |
Installation (None Found)
# Playwright (recommended)
npm i -D playwright
npx playwright install
# Or with uv (Python)
uv add playwright
python -m playwright install
Quick Command Reference
| Scenario | Playwright | Puppeteer | Cypress |
|----------|------------|-----------|---------|
| Run tests | npx playwright test | node script | npx cypress run |
| Open UI | npx playwright test --ui | - | npx cypress open |
| Record test | npx playwright codegen URL | - | - |
| Screenshot | page.screenshot() | page.screenshot() | cy.screenshot() |
| Navigate | page.goto(URL) | page.goto(URL) | cy.visit(URL) |
| Click | page.click(sel) | page.click(sel) | cy.get(sel).click() |
| Fill input | page.fill(sel, val) | page.type(sel, val) | cy.get(sel).type(val) |
| Wait | page.waitForSelector() | page.waitForSelector() | built-in |
Common Patterns
Screenshot a Page
# Playwright
npx playwright screenshot --browser chromium https://example.com out.png
Run Existing Tests
# Playwright
npx playwright test
# Cypress
npx cypress run
# Puppeteer (node script)
node tests/puppeteer.js
Record a New Test (Playwright only)
npx playwright codegen https://example.com
# Opens browser + code recorder, paste generated test into your test file
Accessibility Audit
# Playwright + axe-core
npx playwright test --grep @a11y
# agent-browser CLI (legacy)
agent-browser open https://example.com
agent-browser a11y
Legacy: agent-browser CLI
If agent-browser is installed (older projects), it provides a simpler command interface:
agent-browser open https://example.com
agent-browser screenshot --output page.png
agent-browser snapshot # accessibility tree + content
agent-browser click "button.submit"
agent-browser fill "input[name=email]" "[email protected]"
agent-browser a11y # accessibility violations
References
- Playwright - Full Playwright usage patterns
- Puppeteer - Puppeteer API and patterns
- Cypress - Cypress test runner guide
- Selenium - Selenium WebDriver patterns
Related Skills
mikeparcewski/wicked-garden-engineering-conformance-reviewer
development
VerifiedTrustedCommunity
Pattern-conformance agent-half: evaluates a produced artifact or diff against a set of architectural/design pattern rules from the conformance-rule store (wicked_governance schema). Returns structured findings with rule ID, severity, and rationale — the deterministic half (mechanical rule recall) is done by the guard pipeline; this is the semantic evaluation step. Triggered by: the guard_pipeline `outgov_pattern` check (session-close), or explicitly by an engineering review when WICKED_OUTGOV_RULES_DIR is populated. NOT a replacement for the full `engineering` review skill — focuses only on conformance to stored Pattern rules; architecture and code-quality checks live in the `engineering` skill. Semantic evaluation reuses `wicked-garden-qe-semantic-reviewer` as the designated agent-half evaluator (per garden#983 spec). This skill is the orchestrating wrapper that loads applicable Pattern rules and delegates the per-rule semantic judgment to qe-semantic-reviewer.
8SKILL.mdUpdated Jul 22, 2026
mikeparcewski/wicked-garden-domain
tools
VerifiedTrustedCommunity
The FOUNDATIONAL domain-model capability: extract a codebase's domain — testable business rules (with confidence + provenance), entities, requirements — as a schema-conformant model on the estate graph. The workers annotate the store; wicked-core reads it and builds the requirements graph, coverage-gating fail-closed. Steers three fork workers. A shared substrate, not a modernization tool. The `modernize` archetype DERIVES from it; build / migrate / review / specify / explore consume the SAME domain model — none OWN it. Understanding a codebase's domain is upstream of almost everything else garden does. Use when: "extract the business rules / domain model from this codebase", "build a requirements graph from the code", "what does this system actually require", "reverse-engineer the domain before we build/port/migrate". Works on ANY codebase (modern or legacy) — the value is the domain model, not the porting. NOT the code transform itself (that is the archetype consuming this model). This skill produces the DOMAIN MODEL, not new code.
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-modeler
development
VerifiedTrustedCommunity
Domain-graph fork worker for the modernize archetype. Groups the estate's Louvain communities into business domains, attaches each requirement to its cluster (advisory cluster_id provenance), and invokes wicked-core's domain-graph build (which reads the annotated estate store, recomputes coverage fail-closed, and builds the requirements graph) — then validates core's output against the vendored schema. Use when: dispatched by wicked-garden-domain after rule extraction to turn a flat rule set into cluster-keyed domains; "group these into domains", "build the requirements graph", "translate clusters into a domain model". NOT for mining the rules themselves (that is domain-extractor) or threat-modeling (that is domain-coverage).
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-extractor
tools
VerifiedTrustedCommunity
Rule-extraction fork worker for the FOUNDATIONAL domain-model capability. Mines testable business rules from a codebase — each with a numeric confidence and a provenance{source, ref, source_kinds} — and annotates them into the estate store so wicked-core can build the domain-model requirements graph (coverage-gated). This is a substrate, not a modernization tool: the `modernize` archetype DERIVES from it, and build / migrate / review / specify / explore can consume the same domain model — none OWN it. Use when: dispatched by wicked-garden-domain to mine the business_rules of a codebase (or a module); "extract the domain rules", "what does this system require", building the requirements half of a domain model. NOT for grouping into domains (that is domain-modeler) or judging coverage (that is domain-coverage — a seat-distinct evaluator).
8SKILL.mdUpdated Jul 15, 2026