Model Evaluation Benchmark
This automates the full cycle of running model comparison benchmarks following the Benchmark Suite V3 reference implementation. It executes tasks across different Claude models (Opus vs Sonnet), spins up reviewer agents to score code quality, tracks metrics like duration and tool calls, then generates a comprehensive report as a GitHub issue with archived artifacts. The mandatory cleanup phase closes all test PRs and issues, which is honestly the kind of housekeeping that's easy to forget when you're running benchmarks manually. Best for systematic model evaluations where you need reproducible results and proper documentation, not one-off performance checks.
- skills.sh installs
- 160
- GitHub stars
- 76
- last updated
- Aug 21, 2026
Install
$ npx -y skills add rysweet/amplihack --skill model-evaluation-benchmark --agent claude-codeInstalls into .claude/skills of the current project.
Files
Model Evaluation Benchmark Skill
Purpose: Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3 reference implementation.
Auto-activates when: User requests model benchmarking, comparison evaluation, or performance testing between AI models in agentic workflows.
Skill Description
This skill orchestrates end-to-end model evaluation benchmarks that measure:
- Efficiency: Duration, turns, cost, tool calls
- Quality: Code quality scores via reviewer agents
- Workflow Adherence: Subagent calls, skills used, workflow step compliance
- Artifacts: GitHub issues, PRs, documentation generated
The skill automates the entire benchmark workflow from execution through cleanup, following the v3 reference implementation.
When to Use
✅ Use when:
- Comparing AI models (Opus vs Sonnet, etc.)
- Measuring workflow adherence
- Generating comprehensive benchmark reports
- Need reproducible benchmarking
❌ Don't use when:
- Simple code reviews (use
reviewer) - Performance profiling (use
optimizer) - Architecture decisions (use
architect)
Execution Instructions
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/rysweet/amplihack
- Categories
- Testing & QA, Debugging, Automation & Workflows
- First seen
- Jun 3, 2026
More from rysweet/amplihack
All 58- Goal Seeking Agent Pattern157
- Poet Analyst156
- Azure Devops154
- Email Drafter154
- Ethicist Analyst152
- Lsp Setup151
- Session Learning151
- Anthropologist Analyst148
- Mcp Manager146
- Indigenous Leader Analyst141
- Dynamic Debugger140
- Multi Repo137
- Philosophy Compliance Workflow136
- N Version Workflow134
- Outside In Testing134
- Xlsx
- Cybersecurity Analyst1.5K
- Lawyer Analyst690
- Psychologist Analyst456
- Mermaid Diagram Generator429
- Pptx422
- Economist Analyst382
- Design Patterns Expert359
- Learning Path Builder342
Recommended
More Testing & QA
code-interpreteraws-samples/sample-strands-agent-with-agentcoreTest and prototype code in a sandboxed environment. Use for debugging, verifying logic, or installing packages.159skills.sh installs
model-evaluationawslabs/agent-pluginsGenerates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model"140skills.sh installs
agent-browsersundial-org/awesome-openclaw-skillsA fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured comma129skills.sh installs
skill-creatorcherryhq/cherry-studioCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an e0skills.sh installs
perf-theory-testercomposiohq/awesome-claude-pluginsThis is for when you're doing performance testing and need to stay disciplined about changing one variable at a time.0skills.sh installs
skill-creatorcountbot-ai/countbotCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an e0skills.sh installs