mikeng-io/agent-skills / skills/deep-verify
deep-verify
VerifiedGeneric multi-agent verification framework with balanced expert analysis. Model-agnostic and domain-agnostic - verify any work through expert analysis.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 7.0 KB |
| SKILL.md | skill md | 16.4 KB |
| config/README.md | markdown | 4.6 KB |
| examples/basic-config.yaml | config | 715 B |
| examples/security-focus.yaml | config | 553 B |
| examples/weights-security.yaml | config | 585 B |
| examples/weights.yaml | config | 812 B |
| schemas/README.md | markdown | 2.7 KB |
| schemas/verification-report-schema.json | config | 6.8 KB |
| validators/output-validator.md | markdown | 1.3 KB |
schemas/verification-report-schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://deep-verify.dev/schemas/verification-report.json",
"title": "Deep Verify Report Schema",
"description": "JSON Schema for deep-verify output validation",
"type": "object",
"required": [
"verdict",
"generated",
"domains_analyzed",
"experts_consulted",
"summary",
"risk_assessment",
"domain_findings",
"integration_impact",
"third_party_perspective"
],
"properties": {
"verdict": {
"type": "string",
"enum": ["PASS", "PASS_WITH_CONCERNS", "FAIL"],
"description": "Overall verification verdict"
},
"generated": {
"type": "string",
"format": "date-time",
"description": "ISO 8601 timestamp of report generation"
},
"domains_analyzed": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"description": "List of domains that were analyzed"
},
"experts_consulted": {
"type": "integer",
"minimum": 3,
"description": "Number of expert agents consulted (minimum 3: Devil's Advocate, Integration Checker, Third-Party)"
},
"summary": {
"type": "object",
"required": ["domain_correctness", "risk_assessment", "integration_impact"],
"properties": {
"domain_correctness": {
"type": "object",
"required": ["status", "details"],
"properties": {
"status": {
"type": "string",
"enum": ["PASS", "CONCERNS"]
},
"details": {
"type": "string"
}
}
},
"risk_assessment": {
"type": "object",
"required": ["status", "details"],
"properties": {
"status": {
"type": "string",
"enum": ["PASS", "CONCERNS", "FAIL"]
},
"details": {
"type": "string"
}
}
},
"integration_impact": {
"type": "object",
"required": ["status", "details"],
"properties": {
"status": {
"type": "string",
"enum": ["PASS", "CONCERNS"]
},
"details": {
"type": "string"
}
}
}
}
},
"risk_assessment": {
"type": "object",
"required": ["scenarios", "hidden_assumptions"],
"properties": {
"scenarios": {
"type": "array",
"items": {
"type": "object",
"required": ["scenario", "likelihood", "impact", "evidence", "mitigation"],
"properties": {
"scenario": {
"type": "string",
"description": "Description of what went wrong in the pre-mortem"
},
"likelihood": {
"type": "string",
"enum": ["LOW", "MEDIUM", "HIGH"]
},
"impact": {
"type": "string",
"enum": ["LOW", "MEDIUM", "HIGH", "CRITICAL"]
},
"evidence": {
"type": "string",
"description": "What suggests this could happen"
},
"mitigation": {
"type": "string",
"description": "How to prevent this scenario"
}
}
},
"minItems": 1
},
"hidden_assumptions": {
"type": "array",
"items": {
"type": "object",
"required": ["assumption", "risk_if_false"],
"properties": {
"assumption": {
"type": "string",
"description": "What we're assuming"
},
"risk_if_false": {
"type": "string",
"description": "What happens if assumption is wrong"
}
}
}
}
}
},
"domain_findings": {
"type": "array",
"items": {
"type": "object",
"required": ["domain", "findings"],
"properties": {
"domain": {
"type": "string",
"description": "Domain name"
},
"findings": {
"type": "array",
"items": {
"type": "object",
"required": ["severity", "description", "evidence"],
"properties": {
"severity": {
"type": "string",
"enum": ["CRITICAL", "HIGH", "MEDIUM", "LOW"]
},
"description": {
"type": "string",
"description": "Issue or observation"
},
"evidence": {
"type": "string",
"description": "Reference to specific content"
},
"fix": {
"type": "string",
"description": "Recommendation if applicable"
}
}
}
}
}
}
},
"integration_impact": {
"type": "object",
"required": ["affected_components", "dependencies", "coordination_required", "risks"],
"properties": {
"affected_components": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of affected components/systems"
},
"dependencies": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of dependencies"
},
"coordination_required": {
"type": "array",
"items": {
"type": "string"
},
"description": "What needs to be coordinated"
},
"risks": {
"type": "array",
"items": {
"type": "object",
"required": ["area", "risk"],
"properties": {
"area": {
"type": "string",
"description": "Affected area"
},
"risk": {
"type": "string",
"description": "Risk description"
}
}
}
}
}
},
"third_party_perspective": {
"type": "object",
"required": ["clarity_score", "questions", "suggestions"],
"properties": {
"clarity_score": {
"type": "string",
"enum": ["HIGH", "MEDIUM", "LOW"]
},
"questions": {
"type": "array",
"items": {
"type": "string"
},
"description": "Questions a newcomer would ask"
},
"suggestions": {
"type": "array",
"items": {
"type": "string"
},
"description": "Constructive suggestions"
}
}
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |