auto-verify

Auto-Verify Skill

Attempt automated verification of criteria that would otherwise require manual review. This skill parses criterion text for automation hints, checks tool availability, and executes verification commands before marking items as truly manual.

When This Skill Runs

• Invoked by /verify-task when processing MANUAL and MANUAL:DEFER type criteria
• Invoked by /phase-checkpoint for Manual Local Verification items
• Invoked by code-verification skill before browser fallback
• Invoked by browser-verification skill for HTTP-first optimization

Workflow Overview

Copy this checklist and track progress:

Auto-Verify Progress:
- [ ] Step 1: Parse criterion for automation hints
- [ ] Step 2: Check tool availability
- [ ] Step 3: Select tool and generate command
- [ ] Step 4: Execute with timeout
- [ ] Step 5: Interpret result
- [ ] Step 6: Return structured output

Step 1: Pattern Detection

Analyze criterion text and optional Verify: line for automation keywords. Patterns are checked in priority order — first match wins.

Pattern Matching

See PATTERNS.md for the full pattern matching table and command templates.

Key pattern categories:

• HTTP patterns (curl): API endpoints, status codes, redirects, health checks
• Browser patterns: DOM elements, visual checks, console logs
• File patterns (bash): File/directory existence, content checks
• Environment patterns: Environment variable checks
• Truly manual: Subjective criteria (UX, brand, tone)

Step 2: Tool Availability Check

Always Available

These tools are always present and can be used without checking:

Conditionally Available

Check availability before use:

Availability Matrix

TOOL_AVAILABILITY = {
  "curl": ALWAYS,
  "bash": ALWAYS,
  "file_ops": ALWAYS,
  "browser": CHECK_REQUIRED
}

Step 3: Command Generation

Based on detected pattern, generate the appropriate verification command. See PATTERNS.md for complete command templates.

Quick reference:

• HTTP patterns: Use curl for status, content, redirect, health checks
• File patterns: Use bash test/grep for existence and content checks
• Browser patterns: Delegate to browser-verification skill with fallback chain

Step 4: Execution Protocol

Timeouts

Execution Steps

1. Generate command from detected pattern
2. Set timeout based on tool
3. Execute via Bash tool (for curl/bash patterns)
4. Parse output for PASS/FAIL prefix
5. Capture full output for evidence
6. Handle errors (timeout, connection refused, etc.)

Error Handling

Step 5: Result Interpretation

Return a structured result for each criterion:

AUTO-VERIFY RESULT
------------------
Criterion: "{original criterion text}"
Pattern Detected: {pattern name or "none"}
Tool Used: {curl | bash | browser | none}
Command: {executed command or "N/A"}
Status: PASS | FAIL | MANUAL
Duration: {execution time in ms}
Output: {captured output, truncated if >500 chars}
Suggested Fix: {if FAIL, provide actionable suggestion}
Reason: {if MANUAL, explain why automation not possible}

Status Definitions

Step 6: Integration Examples

See references/integration-examples.md for 4 detailed examples covering:

• API endpoint verification (curl, PASS)
• Page load check (HTTP-first optimization, PASS)
• Truly manual criterion (subjective judgment, MANUAL)
• Failed automation (connection refused, FAIL)

URL and Path Extraction

See PATTERNS.md for URL and path extraction patterns.

Configuration

This skill respects settings from .claude/verification-config.json:

{
  "devServer": {
    "url": "http://localhost:3000"
  },
  "autoVerify": {
    "enabled": true,
    "httpTimeout": 5000,
    "fileTimeout": 2000,
    "browserTimeout": 30000,
    "httpFirst": true
  }
}

URL resolution: Use devServer.url for all HTTP checks. Ensure the dev server is running before verification.

If autoVerify.enabled is false, skip automation attempts and return MANUAL for all criteria.