PluginPublic
testland/llm-eval-anti-patterns
Use when an LLM eval suite already gates a release, model swap or prompt change and nobody has audited how it was built. Checks eight methodology errors (too few cases, exact match on open text, no baseline, unpinned models, no adversarial cases and more) and how to validate an LLM judge.
Quality
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Securityby
Passed
No findings from the security scan
tile.json
{
"name": "testland/llm-eval-anti-patterns",
"version": "1.3.8",
"summary": "Use when an LLM eval suite already gates a release, model swap or prompt change and nobody has audited how it was built. Checks eight methodology errors (too few cases, exact match on open text, no baseline, unpinned models, no adversarial cases and more) and how to validate an LLM judge.",
"private": false,
"skills": {
"llm-eval-anti-patterns": {
"path": "SKILL.md"
}
}
}