An agent skill that detects and rewrites AI-generated text tells to make writing sound human.
deslop is easy to set up with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
npx skills add ozdemircili/deslopRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
Deslop is a skill for AI coding agents that helps remove common phrases and patterns that make text sound like it was written by AI. It includes a linter that scores your text and points out specific tells with suggested fixes. The goal is to make your writing read naturally, not to bypass AI detectors.
Deslop is an Agent Skill designed to strip the tells out of AI-written text. LLM prose often has an accent — phrases like "it's worth noting that", "let's delve into", "it's not just X, it's Y", hype verbs, and emojis on every bullet. Readers now spot these instantly and stop trusting the text. Deslop teaches your AI agent to find those tells and rewrite them away without flattening the writing or losing meaning. It is a skill, not an MCP server or an agent: a SKILL.md of editing principles plus a zero-dependency Python linter that scores a draft and points at every tell with a line number and a fix. The linter, slopcheck.py, can be run standalone on any text or markdown file. It provides a weighted score per 1,000 words with a plain-English verdict, locates every tell by line, category, and severity, and offers a one-line fix for each. The SKILL.md principles guide the agent to rewrite the underlying sentence, not blindly delete phrases, ensuring cleaner prose. Deslop knows when to stop: it keeps domain terms, quotes, hedged uncertainty, and the author's voice. Em-dashes are flagged by density, not banned. Deslop follows the open Agent Skills (SKILL.md) spec, so it runs anywhere that format is supported — Claude Code, Claude API, Codex, Cursor, Gemini CLI, and others. Installation is simple via git clone or GitHub CLI. The linter requires Python 3.8+ and no pip installs, API keys, or network access.
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 51 days ago.
0 GitHub stars indicate community interest.
0 open issues signal maintenance load.
No license detected; review before production use.
Make a blog post sound less AI-generated before publishing.
Clean up AI-written email drafts to sound more personal.
Edit README files or documentation to remove robotic phrasing.
Review and improve marketing copy that was initially drafted by an LLM.
Integrate into a CI pipeline to automatically check for AI tells in commits.
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing.
Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
The linter is pure stdlib and makes no network calls, but always audit community skills before installing.
Deslop does not guarantee bypassing AI detectors; its goal is to make text read human by removing real tells.
0
Stars
0
Forks
0
Issues
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
An agent skill that detects and rewrites AI-generated text tells to make writing sound human.
Content writers who use AI assistants and want human-sounding output., Developers who write documentation with AI help and need natural prose., Technical writers editing AI-generated drafts for clarity and authenticity.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing. Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
Similar or complementary options to evaluate include anthropic-skills, bug-hunter, hyperframes.
Jun 7, 2026
4 security/trust notes recorded.
Setup difficulty is 2/5.
An open-source framework to turn HTML, CSS, and animations into deterministic MP4 videos.