noxlie/PR Slop Filter

Detect AI-generated slop PRs before they waste maintainers time

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
thresholdSlop score threshold (0-100) — PRs above this are flaggedno70
fail-on-slopFail the action if the slop score exceeds the thresholdnotrue
formatOutput format: text, json, or github-annotationnogithub-annotation
llm-providerLLM provider for enhanced detection (openai, anthropic, local)no""
llm-api-keyAPI key for the LLM providerno""
llm-modelLLM model name (e.g. gpt-4o-mini, claude-3-haiku)no""
namedescription
slop-scoreThe overall slop score (0-100)
verdictVerdict: human, uncertain, likely-slop, or slop
summaryHuman-readable summary of the slop analysis