Cross Eval
/cs:cross-eval <memo> — Multi-model consensus on a board memo or strategy brief.
Before & after
Same prompt, same agent — the only difference is the skill.
A board memo is high-stakes, so getting feedback is smart. You could review it for clarity, structure, and logical flow. You might ask trusted colleagues for perspective. Looking for tone and message consistency would help. Different readers might catch different issues. You could check that your data supports your conclusions. Would it help if I reviewed it for one specific angle, like feasibility or financial assumptions?
CROSS-MODEL EVALUATION INITIATED Input: board memo on proposed product pivot Models evaluating: Claude, Codex LLM, Gemini Evaluation angle: strategic coherence, downside risk, financial defensibility CLAUDE REVIEW Strength: Pivot targets 15% TAM expansion Weakness: Customer retention risk during transition not quantified Question: If churn hits 8%, does pivot math still work? Recommendation: Add retention risk scenario CODEX LLM REVIEW Strength: Technical feasibility clear, timeline realistic Weakness: Competitive response not addressed Question: Competitor A ships similar pivot next quarter. How do we stay ahead? Recommendation: Detail differentiation strategy GEMINI REVIEW Strength: Financial modeling detailed with multiple scenarios Weakness: Sales team capability gap during pivot not mentioned Question: Current reps sell X. New product needs Y skills. Training plan missing. Recommendation: Add sales enablement workstream CONSENSUS FINDING Memo is strategically sound but operationally incomplete. Downside scenarios under-explored. Three critical gaps identified across independent evaluations. Threshold assessment: Ready to present if you add retention risk scenario + sales plan. Dissenting view: One model flagged feature parity risk; others consider it manageable. Board-ready assessment delivered. Go / no-go confidence: moderate-high.
About this skill
name: cross-eval description: Use when /cs:cross-eval <memo> — Multi-model consensus on a board memo or strategy brief.
Cross Eval
/cs:cross-eval <memo> — Multi-model consensus on a board memo or strategy brief. Claude + Codex + Gemini cross-review with graceful degradation. Use when a high-stakes memo needs an independent sanity check before the boardroom — e.g. a bet-the-company pivot or fundraise terms.
What you get
- Public GitHub repo (alirezarezvani/claude-skills)
- the cross-eval skill folder with SKILL.md. Part of a 337-skill / 30-agent / 70-command install.
Customize your output
- Fork the repo and adapt the skill's instructions and references to your workflow.
Example output
Activates automatically when your request matches Cross Eval; chains with the other skills, agents, and commands in the collection.
Best for
Creators, builders, and teams using Claude Code.
SKILL.md preview
---
name: cross-eval
description: Use when a high-stakes board memo or strategy brief needs an independent multi-model consensus check before it reaches the boardroom.
version: 1.0.0
category: Business & Ops / Executive Advisory
author: AgentVolt
license: proprietary
tags:
- business-ops
- executive-advisory
---
# Cross Eval
Runs a multi-model consensus review, invoked as `/cs:cross-eval <memo>`, cross-checking Claude's review against other models with graceful degradation.
## When to use
… (sign up to view the full skill)More business & ops skills
View all Business & Ops skills →Gc Review
/cs:gc-review <plan> — General Counsel interrogation of contracts, IP, regulatory, term sheets, and employment-law surface.
Caio Review
/cs:caio-review <plan> — Eval-demanding Chief AI Officer interrogation of any plan that involves AI: model selection, risk classification, cost economics, or AI hiring.
Boardroom
/cs:boardroom <brief> — 6-phase multi-role deliberation across the C-suite with Phase 2 isolation, critic pre-screen, and synthesis.
Context Engine
Loads and manages company context for all C-suite advisor skills.