# AI use cases for Anti Slop (miqdadbadjuber/anti-slop) Repo: [miqdadbadjuber/anti-slop](https://github.com/miqdadbadjuber/anti-slop) | Use cases: 4 | Page: https://dedupedai.com/use-cases/miqdadbadjuber-anti-slop/ antislop is a set of rules and skills that stop an AI coding agent from shipping generic UI, filler copy, and AI-shaped code. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Build a landing page free of generic AI UI: https://dedupedai.com/use-cases/miqdadbadjuber-anti-slop/build-landing-page-without-ai-slop/ - Remove filler and fake stats from marketing copy: https://dedupedai.com/use-cases/miqdadbadjuber-anti-slop/clean-marketing-copy-of-filler-and-fake-stats/ - Audit existing code and remove AI-slop comments: https://dedupedai.com/use-cases/miqdadbadjuber-anti-slop/audit-existing-code-comments-for-ai-slop/ - Check a UI for contrast, focus, and mobile layout: https://dedupedai.com/use-cases/miqdadbadjuber-anti-slop/check-ui-for-contrast-focus-and-mobile-reflow/ ## How to build a landing page free of generic AI UI with Anti Slop Repo: [miqdadbadjuber/anti-slop](https://github.com/miqdadbadjuber/anti-slop) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Install antislop and have an agent build a UI with no invented numbers or filler decoration. **Who it is for:** A solo founder or developer using an AI coding agent to build a marketing page who wants it to look intentional, not like default AI output. **The problem:** AI-generated pages often ship with sparkle logos, beta pills, fake terminals, and invented stats that make the page look generic and untrustworthy. **The outcome:** A UI built under 38 mandatory rules, with a Delivery Gate PASS/FAIL report, and with direction supplied by your own DESIGN.md. ### Steps 1. Run `npx antislop-ai` and answer the prompts, selecting the antislop-ui skill and the agents you use. 2. Run `npx antislop-ai --mode during` to save the mode for building new work. 3. Add a DESIGN.md file to the project that states your colors, type, and layout direction. 4. Start a new agent session, so the skills load, and ask the agent to build the page. 5. Read the Delivery Gate report at the end of the session and fix any FAIL items before shipping. ### Prompt to paste into your agent ```text Using the antislop rules from the anti-slop repo (https://github.com/miqdadbadjuber/anti-slop) and the DESIGN.md in , build a landing page for . Finish with the Delivery Gate PASS/FAIL report. Verify that no statistic or testimonial appears on the page unless it is provided in the brief. ``` ### Caveat antislop removes slop but does not beautify on its own, so a plain result usually means DESIGN.md was missing or thin. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/miqdadbadjuber-anti-slop/build-landing-page-without-ai-slop/ ## How to remove filler and fake stats from marketing copy with Anti Slop Repo: [miqdadbadjuber/anti-slop](https://github.com/miqdadbadjuber/anti-slop) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Run one prompt through the copywriting rules to get clear, honest text. **Who it is for:** A marketer or founder who has an AI draft of a homepage, email, or product description with vague claims and invented numbers. **The problem:** AI-written copy often includes filler phrases, stock headlines, and statistics no one can source. **The outcome:** Copy that avoids fake stats and generic AI phrasing, checked against the copywriting rules, with a Delivery Gate report. ### Steps 1. Download the single file with `curl -o antislop.md https://raw.githubusercontent.com/miqdadbadjuber/anti-slop/main/antislop.md`, or download antislop.md from the repository page. 2. Open a new chat in your AI tool and paste the contents of antislop.md at the start. 3. Paste your draft copy below the rules and ask for a rewrite. 4. Check that every number in the new copy also appears in your original draft or source notes. 5. Read the Delivery Gate report before you publish the copy. ### Prompt to paste into your agent ```text Apply the antislop filter from the anti-slop repo (https://github.com/miqdadbadjuber/anti-slop) to the draft in . Return a rewritten version and the Delivery Gate PASS/FAIL report. Verify that no statistic in the output is absent from the draft. ``` ### Caveat The single file is a complete filter for chat use, but the full skill set with the copywriting skill is installed through the installer. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/miqdadbadjuber-anti-slop/clean-marketing-copy-of-filler-and-fake-stats/ ## How to audit existing code and remove AI-slop comments with Anti Slop Repo: [miqdadbadjuber/anti-slop](https://github.com/miqdadbadjuber/anti-slop) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Run antislop in After mode to get a numbered list of comment fixes you approve. **Who it is for:** A developer who inherited a codebase full of comments written by an AI agent and wants to remove the noise. **The problem:** Agent-written code often carries comments that restate the code, add filler, or narrate obvious steps. **The outcome:** A numbered findings list of comments to remove or keep, the fixes you approve, and a follow-up Delivery Gate report. ### Steps 1. Run `npx antislop-ai --mode after` to save After mode as the preference for audits. (inferred, check the README) 2. Run `npx antislop-ai` and select the antislop-code skill if it is not installed yet. 3. Start a new agent session in the project folder. 4. Ask the agent to audit the comments and give you the numbered findings list. 5. Approve the fixes you want, then read the follow-up report. ### Prompt to paste into your agent ```text Using the antislop-code rules from the anti-slop repo (https://github.com/miqdadbadjuber/anti-slop), audit the comments in . Return a numbered findings list, then wait for approval before editing. Verify that no approved fix changes code behavior, only comments. ``` ### Caveat The skill covers comments only, so it does not review logic, and the README does not describe how it handles every language. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/miqdadbadjuber-anti-slop/audit-existing-code-comments-for-ai-slop/ ## How to check a UI for contrast, focus, and mobile layout with Anti Slop Repo: [miqdadbadjuber/anti-slop](https://github.com/miqdadbadjuber/anti-slop) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Use the accessibility and responsive skills to review a UI before release. **Who it is for:** A developer preparing a UI for release who needs a check on contrast, keyboard focus, and layout across screen widths. **The problem:** AI-built UI often fails contrast ratios, hides focus states, and breaks or overflows on narrow screens. **The outcome:** A PASS/FAIL report covering contrast, keyboard focus, states, reflow, breakpoints, and tap targets. ### Steps 1. Run `npx antislop-ai` and select the antislop-human and antislop-layoutmobile skills. 2. Start a new agent session in the project folder, so the skills load. 3. Ask the agent to review the UI against both skills and list each finding by number. 4. Fix the FAILs it reports, then ask for a new Delivery Gate report. 5. Test the UI yourself at a narrow screen width and with the keyboard before release. ### Prompt to paste into your agent ```text Review the UI in against the antislop-human and antislop-layoutmobile skills from the anti-slop repo (https://github.com/miqdadbadjuber/anti-slop). Return a numbered list of contrast, focus, and overflow findings with the Delivery Gate report. Verify that each contrast finding names the ratio it measured. ``` ### Caveat The README describes these skills as rule checks, so they do not replace manual testing with real assistive technology or real devices. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/miqdadbadjuber-anti-slop/check-ui-for-contrast-focus-and-mobile-reflow/