Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

cross-model-review

bởi don-gbot

Git & GitHub
431Lượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Adversarial plan review using two different AI models.

Mô tả

Kỹ năng này làm gì

Runs adversarial plan review using two AI models from different providers. In alternating mode, each model swaps between writing and reviewing each round, with the loop running fully autonomously until both converge on an approved plan. Intended for plans touching auth, payments, or data models, or any implementation expected to take over an hour.

Unlike single-model review, each model must rewrite based on its own critique, so issues get resolved rather than just listed.

Khi nào nên dùng

  • Reviewing an OAuth integration plan before writing any code
  • Stress-testing a payments flow design against a second model
  • Catching schema migration risks before a database refactor
  • Running autonomous adversarial review before dispatching a coding agent
  • Validating a multi-step feature plan where two engineers would normally disagree

Quy trình ví dụ

ĐẦU VÀO

User asks: Review this plan for adding OAuth2 login to our app

AGENT
  1. 1

    Initialize a review workspace with the plan file, alternating mode, and two models from different providers

  2. 2

    Call next-step to get the first action, then spawn Model B as a reviewer sub-agent with the generated prompt

  3. 3

    Parse the reviewer response into the workspace issue tracker using parse-round

  4. 4

    Spawn Model B as a writer to revise the plan based on its own review, then call save-plan to store the new version

  5. 5

    Continue the loop, swapping roles each round, until a reviewer responds APPROVED with no open critical blockers, then call finalize

ĐẦU RA

plan-final.md with a changelog, rubric scores per round, and a summary of all issues found and resolved

Yêu cầu

  • Anthropic API key for Claude models
  • OpenAI API key for OpenAI models

Cài đặt

clawhub install don-gbot/cross-model-review

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết