CtrlK
BlogDocsLog inGet started
Tessl Logo

juliusbrussee/caveman

Compressed caveman-style prose for AI coding agents — cuts ~65% output tokens while keeping full technical accuracy

96

1.00x
Quality

100%

Does it follow best practices?

Impact

96%

1.00x

Average score across 38 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-19/

{
  "context": "Tests whether the response provides balanced, technically accurate guidance on the monolith-to-microservices decision.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Mentions operational complexity increase",
      "description": "Warns that microservices add operational overhead: deployment, monitoring, networking, service discovery",
      "max_score": 12
    },
    {
      "name": "Suggests profiling first",
      "description": "Recommends identifying the actual bottleneck before splitting — the slowness might be fixable within the monolith",
      "max_score": 12
    },
    {
      "name": "Mentions data consistency challenges",
      "description": "Notes that splitting introduces distributed data problems: transactions across services, eventual consistency",
      "max_score": 10
    },
    {
      "name": "Mentions team structure consideration",
      "description": "References team size or organization as a factor (Conway's law or similar reasoning)",
      "max_score": 10
    },
    {
      "name": "Does not unconditionally recommend microservices",
      "description": "Response is balanced — does not simply say 'yes, switch to microservices' without caveats",
      "max_score": 12
    },
    {
      "name": "No incorrect information",
      "description": "Response does not contain factually wrong statements about microservices architecture or Django",
      "max_score": 10
    }
  ]
}

evals

README.md

SKILL.md

tile.json