xoai/browser-check
core/capabilities/verification/browser-check/SKILL.md
Quick browser smoke test via Lightpanda MCP. Checks if the primary affected route renders, has no JS errors, and contains expected elements. Advisory only — never blocks. Invisible when Lightpanda is not available or no frontend files in diff.
$ install --global
skillsauthnpx skillsauth add xoai/sage browser-checkInstall 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 25, 2026, 2:00 PM151.1s1 file scanned
SKILL.md
- name:
- browser-check
- description:
- >
- version:
- 1.0.0
- modes:
- [build, fix]
<!-- sage-metadata
cost-tier: sonnet
activation: auto
tags: [verification, browser, qa, smoke-test]
inputs: [url, diff]
outputs: [pass-fail]
requires: []
-->
Browser Check (Light Mode)
Quick smoke test within quality-gates. Catches catastrophic failures: page doesn't load, JS errors, blank screen, missing key elements.
Availability Check
FIRST: Check if Lightpanda MCP tools are in the agent's tool list.
If Lightpanda MCP is NOT available:
- Return immediately
- No output, no warning, INVISIBLE
- Do NOT suggest installing Lightpanda
- Do NOT mention this gate was skipped
If the change does NOT touch frontend/user-facing code:
- Return immediately, invisible
If no running URL is known:
- Ask once: "What URL should I check? (e.g., localhost:3000)"
- If user declines or URL is unreachable, skip invisibly
When All Conditions Met
Time budget: 30 seconds max. One page load, three tool calls.
Step 1: Navigate
Use goto to load the primary affected route.
If Lightpanda doesn't respond within 10 seconds, skip with timeout note.
Step 2: Check for Catastrophic Failures
evaluate: check for JS console errors (uncaught exceptions)markdown: verify page has non-empty content (not blank/error)semantic_tree: verify expected key elements exist (based on spec)
Step 3: Report
If catastrophic failure detected:
⚠ Browser check: FAIL
Route: /[path]
Issue: [what's wrong — JS error, blank page, missing elements]
Console: [relevant error output]
Recommend: Run /qa for full assessment, or /fix for this issue.
If pass:
✓ Browser check: PASS
Route: /[path] — renders, no JS errors, key elements present.
Enforcement
- Advisory ONLY — never blocks the build
- A failure produces a warning and recommendation, NOT a gate failure
- Do NOT fabricate browser findings (if you didn't load the page, don't claim you did)
- Do NOT test routes that weren't affected by the current change
Related Skills
xoai/sage-self-learning
tools
VerifiedTrustedCommunity
Captures agent mistakes, corrections, and discovered gotchas so they are not repeated. Use when: (1) a command or operation fails unexpectedly, (2) the user corrects the agent, (3) the agent discovers non-obvious behavior through debugging, (4) an API or tool behaves differently than expected, (5) a better approach is found for a recurring task. Also searches past learnings before starting tasks to avoid known pitfalls. Activate alongside the sage-memory skill — they share the same MCP backend but serve different purposes (sage-memory = codebase knowledge, sage-self-learning = agent mistakes and gotchas).
17SKILL.mdUpdated May 20, 2026
xoai/sage-ontology
development
VerifiedTrustedCommunity
Typed knowledge graph stored in sage-memory. Use when creating or querying structured entities (Person, Project, Task, Event, Document), linking related objects, checking dependencies, planning multi-step actions as graph transformations, or when skills need to share structured state. Trigger on "remember that X is Y", "what do I know about", "link X to Y", "show dependencies", "what blocks X", entity CRUD, cross-skill data access, or any request involving structured relationships between things.
17SKILL.mdUpdated May 20, 2026
xoai/sage-memory
tools
VerifiedTrustedCommunity
Integrates sage-memory into Sage workflows. Teaches the agent when to remember (store findings during work), when to recall (search memory at session start and task start), and how to learn (structured knowledge capture via sage learn). Use when the user mentions memory, remember, recall, learn, capture knowledge, onboard to codebase, or when starting any session where sage-memory MCP tools are available.
17SKILL.mdUpdated May 20, 2026
xoai/sage-self-learning
tools
VerifiedTrustedCommunity
Captures agent mistakes, corrections, and discovered gotchas so they are not repeated. Use when: (1) a command or operation fails unexpectedly, (2) the user corrects the agent, (3) the agent discovers non-obvious behavior through debugging, (4) an API or tool behaves differently than expected, (5) a better approach is found for a recurring task. Also searches past learnings before starting tasks to avoid known pitfalls. Activate alongside the sage-memory skill — they share the same MCP backend but serve different purposes (sage-memory = codebase knowledge, sage-self-learning = agent mistakes and gotchas).
17SKILL.mdUpdated May 20, 2026