Skip to content

mikeng-io/agent-skills / skills/deep-verify

deep-verify

Verified

Generic multi-agent verification framework with balanced expert analysis. Model-agnostic and domain-agnostic - verify any work through expert analysis.

validators/output-validator.md

View on GitHub
# Output Validator: deep-verify

This document defines the validation procedure for deep-verify output artifacts.
Sub-agents spawned for output validation should follow these steps.

## Required Fields Check

Verify the verification report contains all required fields:

- `skill`: must be "deep-verify"
- `verdict`: must be one of PASS | CONCERNS | FAIL
- `timestamp`: must be valid ISO-8601
- `domains`: must be a non-empty array
- `findings`: must be present (may be empty array for PASS)
- `review_id` or `session_id`: must be present

## Verdict Consistency Check

1. If verdict = FAIL: at least one finding must have severity CRITICAL or HIGH
2. If verdict = CONCERNS: findings should include at least one MEDIUM or higher
3. If verdict = PASS: no CRITICAL or HIGH findings should be present

Report inconsistencies as validation warnings, not hard failures.

## Finding Schema Check

Each finding in the `findings` array must have:
- `id`: string (e.g., "F001")
- `severity`: one of CRITICAL | HIGH | MEDIUM | LOW | INFO
- `title`: non-empty string
- `description`: non-empty string

Optional but expected: `evidence`, `recommendation`, `domains`

## Output

Return a validation summary:
```json
{
  "valid": true | false,
  "warnings": ["list of non-blocking issues"],
  "errors": ["list of blocking issues — these mean the report is invalid"]
}
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall