Anti Slop Writing
CheckedWrite text that avoids all known AI writing patterns and passes human detection. Use when writing articles, essays, blog posts, social media copy, or any content that must read as authentically human. Triggers on requests to write naturally, avoid AI slop, avoid AI detection, humanize writing, write like a human, or make text sound authentic.
Install on your platform
Showing OpenClaw.
- 1
Run this in your terminal
terminal$ openclaw skills install anti-slop-writing
What we know about this skill
Publisher
adenaufal
Taken from the source listing. We haven't verified who controls this account.
Install target
Pinned to d6221ff8
Installs fetch a stored snapshot of that commit, so the code can't change after the fact.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned adenaufal/anti-slop-writing at 104fae8cf6.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 104fae8cf6
- Manifest
- english/SKILL.md
- Scanned
- 10 files, 2,148 lines
About this skill
What it does
This skill helps AI agents produce more human-sounding writing, avoiding the typical hallmarks of AI-generated text. It focuses on creating output that is more specific, less rigid, and generally avoids generic phrasing. The skill draws inspiration from research into AI text detection and guidelines for identifying signs of AI writing.
When to use it
- Rewriting formal content: Transform overly formal or verbose passages into more approachable language.
- Avoiding robotic tone: Inject personality and naturalness into AI-generated responses.
- Improving clarity: Produce concise and direct text that cuts out unnecessary jargon or filler phrases.
- Generating engaging descriptions: Craft vivid and specific details to make content more compelling (e.g., describing a festival with stall details and sold-out items).
Key capabilities
- Transforms formal writing into more natural language.
- Reduces the "AI feel" in generated text.
- Promotes specificity and detail in output.
- Supports various AI tools including Claude.ai, Claude Code, Copilot, Cursor, Windsurf, Gemini CLI, and Codex CLI.
Example prompts
- “Please rewrite this to sound more human.”
- "Make this writing not look like it was written by an AI."
- "No slop, get straight to the point."
Tips & gotchas
- The skill requires cloning the repository for tools other than Claude.ai.
- To quickly test if the skill is active, use a prompt requesting two versions of text: one formal and concise, the other casual and natural, avoiding AI templates.