AgriciDaniel/anti-slop ? reverse-engineered prompt
Reverse engineered prompt
Build me this anti slop project so it can scan writing, code, docs, and agent output for substance problems and report clear findings without ever guessing who wrote something.
I want the repo to work end to end, including the Claude Code plugin and the Obsidian knowledge base that backs it, with the scanners, adapters, and tests all wired up so I can run checks locally. Please make sure the tool only flags real, mechanical issues, like missing citations, broken references, placeholders, residue, or claims that do not hold up when tested, and that any repair step uses the findings instead of re judging the text. If something in the docs or setup is outdated, fix it too, and look up current docs online if you need to.
Please keep the output practical and inspectable, with good error messages and a clean workflow for review and repair.
Are you gonna build this?
make sure you review the code using coderabbit