Docs / source reviewed
slop-grader
Flag lines and grade documents against custom writing rules
How this project uses Jev
- Input
- Numbered text plus line-level and document-level rules defined in Markdown or JSON
- Jev decides
- Whether each line violates a rule and where the document falls on a stated rubric
- Code executes
- The CLI batches Jev questions by rule and reports line references, findings and document scores for a writer or another agent to act on
Evidence and limitations
This is configurable style and quality checking, not AI-authorship detection. People or other models perform rewrites; offline check mode validates rule syntax only. Language judgments and false-positive rates were not tested here.
This project has not been run independently here. Author-reported results are not independently verified results.
Original sources
- https://github.com/lukstei/slop-grader/blob/6984c9793eaab446483f54fed055251eb6c4efb9/README.md ↗
- https://github.com/lukstei/slop-grader/blob/6984c9793eaab446483f54fed055251eb6c4efb9/src/grader.ts ↗
- https://github.com/lukstei/slop-grader/blob/6984c9793eaab446483f54fed055251eb6c4efb9/src/providers/jev.ts ↗