Brazil Benchmark Organization
Official@brazil-bench · United States of America
Benchmark agents by asking them to build an MCP server for Brazilian football. Use this project to develop purpose driven automation patterns.
Agent Skills by Brazil Benchmark Organization
Showing 8 vetted skills indexed across 1 GitHub repositories.
brazil-benchcodebase-summary
Analyze repositories to generate structured documentation with Mermaid diagrams.
brazil-benchevaluate-attempt
Evaluates Brazil-bench attempts and generates structured reports on conformance, tests and timeline for Python/Swift-iOS projects.
brazil-benchfile-issues
Parse evaluation reports and file GitHub issues for each identified shortcoming.
brazil-benchcompare-attempts
Compare brazil-bench evaluation reports and generate a ranked Markdown leaderboard.
brazil-benchre-evaluate
Detect new commits and closed issues, then re-run evaluations and update reports.
brazil-benchcode-assist
Guide teams through TDD-based Explore, Plan, Code, and Commit workflows.
brazil-benchpdd
Transform rough ideas into design and implementation plans with structured prompts.
brazil-benchcode-task-generator
Convert rough descriptions and PDD plans into structured .code-task.md files.
Frequently Asked Questions About Brazil Benchmark Organization
FAQPage SchemaWhat specific tasks can be performed using Brazil Benchmark Organization's capabilities?▼
These capabilities enable repository documentation generation using Mermaid diagrams, evaluation of project conformance for Swift-iOS and other environments, automated GitHub issue filing based on report findings, and the creation of ranked leaderboards to track development progress.
Which personas benefit most from these evaluation and planning capabilities?▼
Engineering managers, technical leads, and quality assurance teams benefit most. These personas utilize the organization's functions to standardize TDD-based development, monitor project health through structured reports, and maintain objective performance rankings across multiple development attempts.
What are the prerequisites for running these evaluation and planning functions?▼
Users require an active GitHub repository containing either Swift-iOS or general project codebases. The system relies on structured input files, such as .code-task.md, to initiate the planning and evaluation cycles, ensuring that all reports and leaderboards remain grounded in specific project requirements.