unslop-file

Rewrite memory files to remove AI tells while preserving code blocks, URLs, paths, commands, and headings.

91|2|Updated Apr 19, 2026

Search Tags:#markdown #llm #deterministic #memory-files #code-preservation #ai-tell-removal

Ready to run

npx skills add https://github.com/MohamedAbdallah-14/unslop --skill unslop-file

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: unslop-file
Source: https://github.com/MohamedAbdallah-14/unslop/tree/main/unslop
Command: npx skills add https://github.com/MohamedAbdallah-14/unslop --skill unslop-file

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, transformers, huggingface_hub, safetensors, anthropic, and includes scripts (resource) components.

What problem does it solve?

Rewrite memory documents that have AI-style prose into human-written text while preserving every technical detail (code blocks, URLs, file paths, commands, and headings) exactly as-is.

Core Features & Use Cases

Preserves code blocks, URLs, paths, commands, and headings while removing AI tells
Supports both deterministic regex-based rewriting and full LLM-based rewrites via Claude
Creates a <stem>.original.md backup before overwriting, enabling safe reversions
Works on common memory file types like CLAUDE.md, AGENTS.md, todos, preferences, and docs

Quick Start

Run: unslop-file <filepath> to rewrite the file and create a <stem>.original.md backup

Frequently Asked Questions about unslop-file

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I remove AI-generated text from markdown files without breaking code blocks and URLs?▼

To remove AI tells from markdown files while preserving code blocks, URLs, paths, commands, and headings, run a script-driven pipeline that rewrites AI-style prose into human text. It executes a two-pass audit and creates a backup before overwriting.

Can I humanize CLAUDE.md and AGENTS.md memory files deterministically without using an LLM?▼

Yes, you can humanize memory files like CLAUDE.md and AGENTS.md deterministically using a regex-based rewriting pass, which avoids LLM usage entirely while enforcing a safe backup and validation step.

Does rewriting markdown files with Claude preserve YAML frontmatter and technical paths?▼

Rewriting markdown files with Claude preserves YAML frontmatter, file paths, commands, and headings exactly as-is. It targets AI-style prose for rewriting while leaving technical details untouched during the two-pass audit.

What is the best way to batch process multiple markdown docs to remove AI tells?▼

The best way to batch process multiple markdown docs is using a script-driven pipeline that rewrites AI-style prose across multiple files. It creates a backup for each file and validates results to ensure technical details remain intact.

How do I revert a markdown file if the AI text removal alters my technical content?▼

To revert a markdown file after AI text removal, use the generated backup file. The pipeline creates a backup before overwriting the original document, ensuring you can safely restore the exact prior state if needed.

Do I need Anthropic and Hugging Face dependencies installed to humanize memory files?▼

You need Anthropic dependencies only for LLM-based rewrites via Claude. For deterministic humanization of memory files, the regex pass works independently, though Hugging Face and Torch dependencies power the broader script pipeline.