Claude Skills by robertoecf

Cross-host adversarial review of implementation plans, code/diffs/configs, or prompts/skill definitions. Classifies the artifact, routes the heavy critique to the agent that is NOT the host, cross-validates against independent host-side analysis, and returns material findings with severity and a verdict. Plan/code reviews include a mandatory over-engineering, YAGNI, and in-repo reuse counterfactual. Prompts are analyzed host-side across 6 dimensions. Provider routing includes OpenCode Go Deep...

Cross-host adversarial review of an implementation plan. Routes the review to the agent that is NOT the host — Codex if you are running in Claude Code, Claude Opus if you are running in Codex. Cross-validates against your own independent analysis, returns a revised plan with critics and a verdict. Falls back to Gemini cascade, then degraded host-self with an explicit warning.

Cross-host adversarial red-team review of code, configs, and diffs. Routes the review to the agent that is NOT the host — Codex if you are running in Claude Code, Claude Opus if you are running in Codex. Cross-validates against your own independent analysis and returns unified security/robustness critics with severity ratings. Falls back to Gemini cascade, then degraded host-self with explicit warning.

Analyze and optimize prompts (system prompts, agent instructions, skill definitions). Finds clarity issues, token waste, instruction conflicts, and structural problems. Returns improved version with diff and reasoning.

Lightweight router that classifies input (plan, code, prompt) and tells the main session which adversarial-review skill to invoke. Does NOT review the content itself.