Benchmark Suite Manager
Testing & Qualitybenchmark-suite-managerBenchmark Suite Manager is an Agent Skill for testing & quality published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Manage benchmarks for algorithm engineering experiments and evaluations
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/domains/science/computer-science/skills/benchmark-suite-manager/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/benchmark-suite-manager, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Benchmark Suite Manager
Purpose
Provides expert guidance on managing benchmark suites for algorithm engineering and experimental evaluation.
Capabilities
- Standard benchmark suite access (DIMACS, TSPLIB, etc.)
- Instance generation for specific problem classes
- Statistical analysis of results
- Performance comparison tables
- Visualization of scaling behavior
- Reproducibility support
Usage Guidelines
- Suite Selection: Choose appropriate benchmark suite
- Instance Selection: Select representative instances
- Execution: Run experiments systematically
- Analysis: Perform statistical analysis
- Reporting: Generate comparison tables and plots
Tools/Libraries
- DIMACS
- TSPLIB
- SuiteSparse Matrix Collection
- Statistical tools