skills.rest
slabgorb
slabgorbCOMMUNITY
Explore all skills by this author →
GitHub

persona-benchmark

Run predefined benchmarks comparing persona effectiveness across code-review, test-writing, and architecture tasks.

2|Updated Mar 25, 2026
Search Tags:#architecture#analysis#evaluation#benchmark#persona#code-review#test-writing
One-click install
npx skills add https://github.com/slabgorb/sidequest --skill persona-benchmark
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: persona-benchmark
Source: https://github.com/slabgorb/sidequest/tree/main/.pennyfarthing/skills/pf-persona-benchmark
Command: npx skills add https://github.com/slabgorb/sidequest --skill persona-benchmark

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Run benchmarks to compare persona effectiveness across themes. Use when testing which personas perform best on code review, test writing, or architecture tasks, or when running comparative analysis across themes.

Core Features & Use Cases

  • Benchmark multiple personas across code-review, test-writing, and architecture tasks to identify the most effective theme for your goals.
  • Automatically configure and run standardized test cases from .claude/benchmarks, then collect and compare results.
  • Generate structured outputs with both quantitative metrics and qualitative assessments to guide persona selection.

Quick Start

Run a benchmark with a specific test-case and persona to start collecting results.

Frequently Asked Questions about persona-benchmark

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

FAQPage Schema
How do I benchmark personas for code review and test writing tasks?▼

To benchmark personas, you run standardized test cases stored under .claude/benchmarks and compare persona effectiveness. This applies to code-review, test-writing, and architecture scenarios using themes configured in .claude/persona-config.yaml.

What is persona benchmarking and when do I need it?▼

Persona benchmarking analyzes and compares persona effectiveness across predefined tasks. You need it when testing which personas perform best on code review, test writing, or architecture tasks to guide persona selection.

How do I configure persona themes for benchmark analysis?▼

Persona themes are configured in the .claude/persona-config.yaml file. This configuration drives the benchmark execution across code-review, test-writing, and architecture scenarios.

Can I use this to compare architecture analysis personas across different tasks?▼

Yes, you can compare architecture analysis personas across tasks. The benchmark applies standardized test cases to evaluate performance and outputs both quantitative and qualitative metrics for comparison.

Where are benchmark results stored and what format do they use?▼

Benchmark results are output as YAML files in .claude/benchmarks/results with a timestamped filename. They include both quantitative metrics and qualitative assessments to guide persona selection.

Do I need any dependencies to run persona benchmarks?▼

No dependencies are required to run persona benchmarks. You only need predefined test cases under .claude/benchmarks and persona themes configured in .claude/persona-config.yaml to execute the comparative analysis.

Related Skills

Explore More Data & Analytics Skills→
ViniciuscarvalhoViniciuscarvalho
11

spec-workflow-init

Scaffold a spec-workflow configuration and starter templates in a project.

Community
Intermediate
sanjogkadayat-websanjogkadayat-web

python-eval

Evaluate AI-generated Python code pipelines across correctness, formatting, performance, and reliability.

Community
Advanced
giosuetedeschi-specgiosuetedeschi-spec

prompt-library

Generate role-based prompt templates for software development and technical writing tasks.

Community
Basic
chicanoandres702chicanoandres702

llm-evaluation

Evaluate LLM outputs with automated metrics, human judgments, and A/B testing.

Community
Advanced