FeedHive published an open-source AI Slop Detector cataloging 120 writing patterns that make text read as AI-generated, organized into 9 categories with explanations, bad examples, and rewrites. It ships as an agent skill for Claude Code and Codex, a browser-based checker, and structured JSON for custom tooling. The tool targets style cleanup rather than authorship detection, which matters for practitioners trying to keep AI-assisted output readable.
Desloppy analyzes a draft and marks specific lines that read as machine-made, explaining why and suggesting rewrites. Users paste text or upload .docx, .pptx, or .pdf files and get per-line feedback plus an overall probability score. It targets people who write with AI and want to avoid the 'this sounds like ChatGPT' reaction.
Desloppy analyzes a draft and marks specific lines that read as machine-made, explaining why and suggesting rewrites. Users paste text or upload .docx, .pptx, or .pdf files and get per-line feedback plus an overall probability score. It targets people who write with AI and want to avoid the 'this sounds like ChatGPT' reaction.
An open-source skill that detects and rewrites AI writing slop — cliché words, phrases, formatting tells — across a four-stage pipeline. LLM agents review the original versus rewrite and loop on failures, with an optional second model providing cross-review scoring. It targets people using AI agents who want natural-sounding output.
An open-source skill that detects and rewrites AI writing slop — cliché words, phrases, formatting tells — across a four-stage pipeline. LLM agents review the original versus rewrite and loop on failures, with an optional second model providing cross-review scoring. It targets people using AI agents who want natural-sounding output.
The open-source quiron skill, installable via the skills CLI for coding agents like Claude Code, Codex and Cursor, rewrites AI-generated prose to remove machine-writing tells and then measures the result against human writing baselines. It requires no API key and runs on the agent's existing model.
The open-source quiron skill, installable via the skills CLI for coding agents like Claude Code, Codex and Cursor, rewrites AI-generated prose to remove machine-writing tells and then measures the result against human writing baselines. It requires no API key and runs on the agent's existing model.
A Claude skill containing 24 rules that detect AI-typical writing patterns in a finished draft, flagging each occurrence with its line and a suggested fix. The rule list grew from the author's own human-written posts being flagged by AI detectors. It targets writers whose genuine text gets caught by detectors.
A Claude skill containing 24 rules that detect AI-typical writing patterns in a finished draft, flagging each occurrence with its line and a suggested fix. The rule list grew from the author's own human-written posts being flagged by AI detectors. It targets writers whose genuine text gets caught by detectors.
A developer released a custom skill, claudish, on GitHub to curb recurring AI writing tropes in technical documentation. It targets habits like overly literary prose and contrastive framing, with goals similar to tropes.fyi. The author built it iteratively by adding corrections to a do-not-do list and invites pull requests.
A developer released a custom skill, claudish, on GitHub to curb recurring AI writing tropes in technical documentation. It targets habits like overly literary prose and contrastive framing, with goals similar to tropes.fyi. The author built it iteratively by adding corrections to a do-not-do list and invites pull requests.