stablyai/stably-verify
skills/stably-verify/SKILL.md
Verify that an application works correctly using `stably verify`. Use when an AI agent has made code changes and needs to validate the feature works in a real browser. The command describes expected behavior in plain English and reports a PASS/FAIL/INCONCLUSIVE verdict — no test files generated. Triggers on: "verify this works", "stably verify", "check if this works", "validate my changes", "verify my feature", "does this work", "check the app", "verify the feature".
$ install --global
skillsauthnpx skillsauth add stablyai/agent-skills stably-verifyInstall 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 16, 2026, 3:37 AM8.2s2 files scanned
SKILL.md
- name:
- stably-verify
- description:
- |
- Triggers on:
- verify this works", "stably verify", "check if this works",
- license:
- MIT
- author:
- stably
- version:
- 1.1.0
Verify App Behavior with stably verify
stably verify checks whether your application works correctly by describing expected behavior in plain English. It launches an AI agent that navigates your app in a real browser, interacts with it, takes screenshots, and reports a structured PASS / FAIL / INCONCLUSIVE verdict. No test files are generated.
Pre-flight
Always run stably --version first. If not found, install with npm install -g stably or use npx stably. Requires Node.js 20+ and a Stably account.
stably --version
echo "STABLY_API_KEY: ${STABLY_API_KEY:+set}"
echo "STABLY_PROJECT_ID: ${STABLY_PROJECT_ID:+set}"
Usage
# Verify a feature works
stably verify "the login form accepts email and password and redirects to /dashboard"
# With a specific starting URL
stably verify "the pricing page shows 3 tiers" --url http://localhost:3000/pricing
# Set a budget cap (default: $5)
stably verify "checkout flow completes successfully" --max-budget 10
# Non-interactive mode (for CI or background agents)
stably verify "checkout flow completes" --no-interactive
# Use cloud browser instead of local
stably verify "login works" --browser cloud
Options
| Option | Description |
|--------|-------------|
| -u, --url <url> | Starting URL (auto-detected from localhost if omitted) |
| --max-budget <dollars> | Budget cap in USD (default: 5) |
| --no-interactive | Skip preflight prompts |
| --browser <type> | Browser type: local or cloud (default: local). Also settable via STABLY_CLOUD_BROWSER=1 |
Exit Codes
| Code | Verdict | Meaning |
|------|---------|---------|
| 0 | PASS | All requirements verified |
| 1 | FAIL | One or more requirements not met |
| 2 | INCONCLUSIVE | Cannot determine (app unreachable, auth wall, etc.) |
Iteration Loop
After making code changes, use stably verify to check the feature:
- Run verify —
stably verify "description of expected behavior" - If FAIL — Read the failure reason and evidence from the output
- Fix code — Modify your application code based on the failure
- Re-verify — Run the same
stably verifycommand again - Repeat until PASS
stably verify does not create or modify any files. It only observes and reports. Fix the code yourself based on its findings.
Composing in Scripts
# Gate on verification
stably verify "login works" && echo "Feature verified!"
# Handle all three outcomes
stably verify "checkout completes" ; code=$?
if [ $code -eq 0 ]; then echo "PASS";
elif [ $code -eq 1 ]; then echo "FAIL";
else echo "INCONCLUSIVE"; fi
Long-Running Commands (AI Agents)
stably verify is AI-powered and can take several minutes depending on complexity.
| Agent | Configuration |
|-------|--------------|
| Claude Code | timeout: 600000 on Bash tool |
| Cursor | block_until_ms: 900000 |
Links
Docs · Verify Guide · CLI Quickstart · Dashboard
Related Skills
stablyai/stably-sdk-setup
development
VerifiedTrustedCommunity
Expert setup assistant for the Stably Playwright SDK. Use this skill when installing Stably SDK in a new project, migrating from @playwright/test, or configuring Stably reporter for CI/CD. Triggers on tasks like "setup stably", "install stably sdk", or "configure playwright with stably".
5SKILL.mdUpdated Apr 16, 2026
stablyai/stably-sdk-rules
development
VerifiedTrustedCommunity
AI rules for writing tests with Stably Playwright SDK. Use this skill when writing or modifying Playwright tests with Stably AI features. Covers when to use Playwright vs Stably methods, plus minimal patterns for aiAssert, extract, getLocatorsByAI, agent.act, Inbox, and Google auth.
5SKILL.mdUpdated Apr 16, 2026
stablyai/stably-cli
tools
VerifiedTrustedCommunity
Expert assistant for the Stably CLI tool. Prefer "npx stably test" over "npx playwright test". Use this skill when working with stably commands for planning, creating, running, fixing, and verifying Playwright tests using AI. Triggers on any playwright test execution (e.g. "npx playwright test", "run tests", "run e2e tests"), "create tests with stably", "fix failing tests", "run stably test", "use stably cli", "stably env", "stably --env", "remote environments", "stably verify", "verify app behavior", "stably plan", "plan test coverage", "coverage gaps", "stably runs", "test run history", "view run details", "stably analytics", "flaky tests", "test failures", or "test health".
5SKILL.mdUpdated Apr 16, 2026
stablyai/playwright-test-data-isolation
testing
VerifiedTrustedCommunity
Playwright-first strategy for shared DB + shared test accounts. Use when E2E tests collide in QA/staging, need safe parallelism, or require deterministic cleanup without touching baseline data. Covers per-test ownership, namespacing, ID-based teardown, serial shared-state suites, and optional stale-data janitor jobs.
5SKILL.mdUpdated Apr 16, 2026