claude-intel-monitor

Detect Claude/GPT model quality degradation with 30 benchmark questions across Math, Reasoning, and Code. Track scores over time, compare providers (Anthropic, OpenAI, DeepSeek), and get alerted when models get dumber.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "claude-intel-monitor" with this command: npx skills add minirr890112-byte/claude-intel-monitor

Claude Intel Monitor

Track LLM intelligence degradation over time. Run 30 benchmark questions daily and detect when models get dumber. Supports Anthropic Claude, OpenAI GPT, and DeepSeek.

When to Use

  • Claude or GPT seems worse today than yesterday
  • You suspect a silent model downgrade
  • You want proof before switching providers
  • You need a baseline for comparing models (DeepSeek scored 91.1%)

Quick Start

# Run full benchmark suite (30 questions)
claude-intel-monitor run --provider anthropic

# Compare against historical baselines
claude-intel-monitor compare --baseline 2026-04-15

# Show score trend over time
claude-intel-monitor trend --days 30

# Alert if score drops below threshold
claude-intel-monitor alert --threshold 80

Benchmark Categories

CategoryQuestionsExample
Math10Calculus, probability, number theory
Reasoning10Logic puzzles, formal deduction
Code10Algorithm design, debugging, refactoring

Baseline Results

ModelScoreDate
DeepSeek V391.1% (27/30)2026-04-17
Claude 3.5 Sonnet93.3% (28/30)2026-03-01
GPT-4o90.0% (27/30)2026-03-01

Install

git clone https://github.com/minirr890112-byte/claude-intel-monitor.git
cd claude-intel-monitor
pip install -e .

Source

github.com/minirr890112-byte/claude-intel-monitor

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Prompt Engineering Mastery

Convert vague instructions into clear AI prompts using structures, techniques, and templates for reliable, precise, and measurable outputs.

Registry SourceRecently Updated
7480Profile unavailable
General

Prompt Engineering Mastery

Comprehensive system for designing, testing, optimizing, and managing clear, role-aware, actionable, focused, and testable prompts for AI models.

Registry SourceRecently Updated
3680Profile unavailable
Coding

Superpowers (OpenClaw)

提供系统化的 AI 编程工作流支持,包括测试驱动开发、代码审查、重构、文档生成和自动化验收测试。

Registry SourceRecently Updated
1.4K2Profile unavailable
Coding

Claude Delegate

Delegate various coding tasks to Claude Code. Use this skill when you need assistance with code generation, bug fixing, feature implementation, code review,...

Registry SourceRecently Updated
4550Profile unavailable