skills.rest
knowlet
knowletCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

multi-model-reviewer

Cross-check Specification, Program, and Test mismatches with multiple AI models and output a structured JSON report.

2|Updated Dec 24, 2025
Search Tags:#specification#test#code-review#ai-models#program#multimodel-review
One-click install
npx skills add https://github.com/knowlet/pf-skills --skill multi-model-reviewer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: multi-model-reviewer
Source: https://github.com/knowlet/pf-skills/tree/main/skills/multi-model-reviewer
Command: npx skills add https://github.com/knowlet/pf-skills --skill multi-model-reviewer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires httpx, pyyaml, and includes scripts (resource) components.

What problem does it solve?

協調多個 AI 模型（ChatGPT、Gemini、Codex、QWEN、Claude）進行三角驗證，確保「Specification == Program == Test」一致性。過濾假警報後輸出報告，大幅減少人工介入時間。

Core Features & Use Cases

  • 透過多模型交叉驗證，確保規格與程式、測試之間的一致性
  • 平行執行多模型審查，並由 Claude 進行假警報過濾
  • 輸出結構化報告，便於代碼審查與 CI/CD 流程

Quick Start

在 Spec、Program 與 Test 目錄上執行多模型審查以產出一致性報告。

Frequently Asked Questions about multi-model-reviewer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check spec-program-test alignment using multiple AI models?▼

Spec-program-test alignment validates consistency across specifications, program code, and test suites. This Skill coordinates multiple AI models to cross-check domain events, invariants, and acceptance criteria, producing a structured JSON report after filtering false positives.

Can I use multi-model review for automated PR reviews in CI pipelines?▼

Yes, multi-model review applies directly to PR reviews and CI pipelines. The Skill executes parallel cross-validation across models like ChatGPT, Gemini, Codex, and QWEN to identify mismatches and output a structured JSON consistency report.

How do I reduce false positives in automated code reviews?▼

Reducing false positives in automated code reviews requires an arbiter model to validate initial findings. This Skill uses Claude to filter incorrect mismatch warnings after parallel multi-model cross-validation across specifications, programs, and tests.

What dependencies do I need to run multi-model review scripts?▼

You need httpx and pyyaml dependencies to run the multi-model review scripts. The Skill uses these libraries to coordinate parallel AI model execution and output structured JSON reports for code review validation.

Does multi-model review work for checking domain invariants and use cases?▼

Yes, multi-model review works for checking domain invariants and use cases. The Skill performs robust cross-checks for domain events, invariants, use cases, and acceptance criteria to ensure specification, program, and test alignment.

Related Skills

Explore More Software Engineering Skills→
AZANIRAZANIR
2

qa-httpx-writer

Generate pytest-compatible Python API tests from OpenAPI contracts using httpx.

Community
Intermediate
AminAlamAminAlam
26

Automated Testing in CI/CD

Automate test execution and gating in CI/CD pipelines for medical devices.

Community
Intermediate
sensei-hackersensei-hacker
4

pr-review

Review GitHub pull requests, bot comments, and CI checks.

Community
Intermediate
uphiagouphiago
1.1k

hunt-llm-ai

Identify exploitable LLM/AI vulnerabilities crossing trust boundaries with validation gates.

Community
Advanced