stablyai/agent-skills/stably-verify

Claude Code and agent skill by stablyai/agent-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

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

npx vskill@latest install stablyai/agent-skills/stably-verify

SKILL.md

The same SKILL.md was published earlier as stablyai/agent-skills/stably-verify.

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.

bash
stably --version
echo "STABLY_API_KEY: ${STABLY_API_KEY:+set}"
echo "STABLY_PROJECT_ID: ${STABLY_PROJECT_ID:+set}"

Usage

bash
# 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
OptionDescription
-u, --url <url>Starting URL (auto-detected from localhost if omitted)
--max-budget <dollars>Budget cap in USD (default: 5)
--no-interactiveSkip preflight prompts
--browser <type>Browser type: local or cloud (default: local). Also settable via STABLY_CLOUD_BROWSER=1
Exit Codes
CodeVerdictMeaning
0PASSAll requirements verified
1FAILOne or more requirements not met
2INCONCLUSIVECannot determine (app unreachable, auth wall, etc.)

Iteration Loop

After making code changes, use stably verify to check the feature:

  1. Run verify — stably verify "description of expected behavior"
  2. If FAIL — Read the failure reason and evidence from the output
  3. Fix code — Modify your application code based on the failure
  4. Re-verify — Run the same stably verify command again
  5. 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

bash
# 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.

AgentConfiguration
Claude Codetimeout: 600000 on Bash tool
Cursorblock_until_ms: 900000

Links

Docs · Verify Guide · CLI Quickstart · Dashboard

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/stablyai/agent-skills/stably-verify/badge)](https://verified-skill.com/skills/stablyai/agent-skills/stably-verify)

Something wrong with this skill or its page? Tell us.