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-28/

{
  "context": "Tests whether the response correctly identifies the read-then-write race condition and provides a valid database-level fix.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Identifies read-then-write as the problem",
      "description": "Explains that separate SELECT then UPDATE creates a race window where concurrent requests read the same value before either writes",
      "max_score": 15
    },
    {
      "name": "Recommends atomic UPDATE RETURNING",
      "description": "Suggests using UPDATE ... SET counter = counter + 1 RETURNING counter (or equivalent atomic single-statement approach)",
      "max_score": 15
    },
    {
      "name": "Mentions alternative: transactions with row locking",
      "description": "Mentions SELECT FOR UPDATE or serializable isolation as an alternative approach",
      "max_score": 10
    },
    {
      "name": "No incorrect information",
      "description": "Response does not contain factually wrong statements about PostgreSQL concurrency, transactions, or locking",
      "max_score": 12
    }
  ]
}

evals

README.md

SKILL.md

tile.json