auto-verify
Attempt automated verification of criteria before falling back to manual. Parses criterion text for automation hints and executes appropriate tool (curl, browser, file check). Invoked by verify-task and phase-checkpoint for MANUAL and MANUAL:DEFER criteria.
Install
mkdir -p .claude/skills/auto-verify && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13321" && unzip -o skill.zip -d .claude/skills/auto-verify && rm skill.zipInstalls to .claude/skills/auto-verify
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Attempt automated verification of criteria before falling back to manual. Parses criterion text for automation hints and executes appropriate tool (curl, browser, file check). Invoked by verify-task and phase-checkpoint for MANUAL and MANUAL:DEFER criteria.About this skill
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-taskwhen processing MANUAL and MANUAL:DEFER type criteria - Invoked by
/phase-checkpointfor Manual Local Verification items - Invoked by
code-verificationskill before browser fallback - Invoked by
browser-verificationskill 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:
| Tool | Capabilities |
|---|---|
| Bash | curl, grep, jq, test, file operations, environment checks |
| Read | File content inspection |
| Glob | File pattern matching |
| Grep | Content search |
Conditionally Available
Check availability before use:
| Tool | Check Method | Fallback |
|---|---|---|
| ExecuteAutomation Playwright | mcp__playwright__* or mcp__executeautomation__* tools exist | Browser MCP |
| Browser MCP | mcp__browsermcp__* tools exist | Microsoft Playwright |
| Microsoft Playwright MCP | mcp__playwright__* tools exist | Chrome DevTools |
| Chrome DevTools MCP | mcp__chrome-devtools__list_pages responds | Manual |
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
| Tool | Timeout | Rationale |
|---|---|---|
| curl | 5 seconds | Network requests should be fast |
| bash (file ops) | 2 seconds | Local operations are quick |
| browser | 30 seconds | Page loading and interaction take time |
Execution Steps
- Generate command from detected pattern
- Set timeout based on tool
- Execute via Bash tool (for curl/bash patterns)
- Parse output for PASS/FAIL prefix
- Capture full output for evidence
- Handle errors (timeout, connection refused, etc.)
Error Handling
| Error Type | Action |
|---|---|
| Timeout | Mark as FAIL with "timeout after {N}s" |
| Connection refused | Mark as FAIL with "connection refused - is server running?" |
| Command not found | Mark as FAIL with "tool not available" |
| Unexpected output | Mark as FAIL with captured output |
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
| Status | Meaning | Next Action |
|---|---|---|
| PASS | Criterion verified automatically | No human review needed |
| FAIL | Automation attempted but failed | Show error, suggest fix, allow human override |
| MANUAL | No automation possible | List for human review with reason |
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.