orchestrating-adversarial-reviews

SKILLWorkflowcommunity
v0.0.0telagodMITUpdated 2mo agoSource →

Multi-agent adversarial-verification orchestration for high-confidence conclusions. Fan-out finders, then verify every finding through a three-prism panel (exploitability / correctness / refutation) that defaults to disbelief, gate fixes behind load-bearing proof tests that catch agents who falsely

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
237Repo stars
1Clients
1Formats
2mo agoLast update
Skill
Authortelagod
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

Multi-agent adversarial-verification orchestration for high-confidence conclusions. Fan-out finders, then verify every finding through a three-prism panel (exploitability / correctness / refutation) that defaults to disbelief, gate fixes behind load-bearing proof tests that catch agents who falsely claim "done/fixed", and roll out behind a build-first exit-code guard. Use when a fan-out task must

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.