Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/cross-model-review
跨模型第二意见技能，融合 gstack 的 cross-model second opinion 能力。 当检测到高风险改动时，可选触发不同模型提供独立审查意见， 作为 multi-perspective-review 的可选叠加层。
Passed 21 of 21 test cases with the skill, and 14 of 21 without it.
and 6 more in the full report
7 fixed15 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
I just modified our authentication token verification logic in `src/auth/jwt.ts`. Before we merge this security patch into main, I want an independent second-model code review. Please run a cross-model review on this diff, evaluating potential edge cases, logic flaws, and security oversights without biasing the second evaluator with previous findings. Show me the comparison of what both models agree on, what each model individually spotted, and any conflicting assessments.
| Checked | Without skill | With skill |
|---|---|---|
| Evaluates raw code changes without embedding the primary evaluator's review findings in the second model's prompt. | Missed | Passed |
| Groups review findings into consensus, single-model, and conflicting categories. | Missed | Passed |
The instructions your model reads when the skill loads.
multi-perspective-review 或 code-reviewer 之上。以下条件命中时，建议 cross-model review（不强制）：
| 检测条件 | 风险原因 |
|---|---|
改动涉及 auth/permission/security 路径 | 鉴权逻辑错误可能导致越权 |
改动涉及 payment/billing/transaction 路径 | 资金相关错误代价极高 |
| 改动涉及数据库 migration 或 schema 变更 | 不可逆的数据结构变更 |
| 改动涉及 API 契约的 breaking change | 影响所有下游消费方 |
| 单次改动超过 500 行 | 大范围变更的审查覆盖率下降 |
| 代码审查中发现 CRITICAL 级别问题 | 需要独立确认修复的正确性 |
检测到时输出：
💡 检测到高风险改动：{原因}
建议启用 cross-model review 获取第二意见。
是否启用？[Y/n]
从当前改动中提取：
test cases passed, vs 14 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.