Edit blog posts, documentation, marketing copy, and PR descriptions to remove formulaic AI writing patterns. Replace filler, vague claims, and staged emphasis with plain statements while preserving concrete details and the writer's voice.
Remove AI writing patterns from prose so it reads like a person wrote it. Use when writing, editing, or reviewing user-facing text (blog posts, docs, marketing copy, PR descriptions), or when asked to "deslop", "de-AI", or "make it sound human".
Review the instructions the agent will receive before you install.
Make prose sound like a specific person wrote it. Fix each tell by stating the underlying claim plainly, not by swapping in a new flourish.
Specifics (names, numbers, examples), "you" for the reader in blog posts, varied sentence length, and short plain lines that carry information. Keep bullet points and numbered steps for actions and instructions; don't fold them back into paragraphs. When editing someone else's writing, keep their voice.
Before: "Here's the thing: most pipelines break in production. Not because the code is bad. Because the data is bad. Let that sink in."
After: "Most pipelines break in production. The code runs fine. The data doesn't match the assumptions baked into it."
Adapted from stephenturner/skill-deslop (MIT, see LICENSE).
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Research questions about a market, examine recorded ChatGPT answers and cited websites, and identify themes where a brand appears or is missing. Receive ranked prompt groups and suggested questions for future tracking.
Audit how a brand appears in AI answers by examining mentions, website citations, competitors, and cited pages. Receive one to three evidence-based priorities, such as improving a page, seeking inclusion in a relevant source, or fixing access barriers.
Compare several competitors to see which sites lead a search market, what content earns rankings, and where opportunities remain. The report covers keyword reach, links from other sites, and practical next steps.
Analyze a named competitor's unpaid search traffic, ranking keywords, content themes, and links from other websites. Identify strengths, weaknesses, and relevant opportunities, with an optional comparison to your own site and a report of recommended actions.
Create or update skills using OpenSEO's repository conventions. Keep one canonical source, distinguish internal and public workflows, maintain Claude Code links, and register public skills in documentation, the in-app agent, and plugin bundles.
Evaluate changes to OpenSEO skills by running fresh Codex sessions against a local backend. Compare saved reports using weighted criteria, then inspect tool logs to understand failures and check whether revised instructions improve output.