ai-slop
v1.2.0by charlesjones-dev · author: Charles Jones
Audits a codebase's user-facing copy, layouts and metadata for AI-written tells and factual errors, such as a privacy policy that misses the trackers the code loads, rewrites a file or pasted text to remove AI writing patterns, and prunes code comments that narrate the code or excuse a workaround
What ai-slop does, in the publisher's words
AI slop audits and rewrites for Claude Code, Codex and Cursor. Find what a codebase shows its users that reads as machine-made and what in it is wrong, or rewrite one piece of text so it reads as a person wrote it.
/slop-audit reads every surface a user sees: pages and shared layout, components and data files that carry copy, forms, emails, visible error text, legal pages, metadata, app strings and store listings, READMEs and --help output. It reports four kinds of problem:
- Copy that reads as AI-written: em dashes, "X, not Y" slogans, triplets, filler, inflated vocabulary, résumé voice
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 3
- MCP servers
- 0
- Stars
- 35
- License
- MIT
- Repo created
- 2025-10-17
- Last pushed
- 2026-10-14
- Publisher type
- User
- Version
- 1.2.0
Links
Skills · 3
- slop-audit
- Audit a codebase's user-facing copy, metadata and page layouts for AI-written tells ("AI slop") and for factual errors in that copy. Scores each area, gives a concrete fix for every finding, and ends with numbered clarifying questions. Report-only until the user answers. Use when the user runs /slo…
- slop-comments
- slop-rewrite
- Rewrite a file, or a block of text pasted after the command, to remove AI writing patterns (humanize it). Uses the same signal list as /slop-audit and adjusts to the kind of text (technical docs, README, blog post, PR or changelog) and to a light, standard or heavy rewrite.
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
ai · ai-slop · ai-detection · audit · copywriting · content · metadata · design · ui · legal · privacy-policy · fact-checking · writing · humanizer · rewriting · editing · code-comments · refactoring · skills
Related by publisher and keywords
Audits the licenses of your open-source dependencies, flags copyleft and missing-license risks, and generates NOTICE or ATTRIBUTION files
Finds technical debt and anti-patterns in code written with older AI models or vibe coding, and saves a scored report with a prioritized roadmap. Takes its settings as arguments, and --defaults skips the setup questions for quick or unattended runs
Audits a site's code for search rankings (SEO), direct answers in featured snippets and voice assistants (AEO), and citations in AI answers from ChatGPT, Perplexity, Copilot and Google AI Overviews (GEO). Catches SEO patterns LLMs still generate, applies framework-specific fixes, generates and validates JSON-LD, builds FAQ sections and question maps, and writes llms.txt
Audits code, or a live URL through Playwright MCP, for Section 508/WCAG 2.0, WCAG 2.1 or WCAG 2.2 issues and saves a report with fixes. Takes its settings as arguments for unattended runs
Audits a codebase, or one directory, for performance bottlenecks and saves a timestamped report with an impact score for each finding
Generates.gitignore files, runs typecheck, lint, format, security and test checks before you commit, and commits, pushes and opens a PR with a message in your repo's style
[](https://agentpluginsdirectory.com/plugins/ai-slop)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.