No AI Slop skill
A skill that edits English drafts: strips AI boilerplate, keeps the author's voice, and can also just list what it found without rewriting
- 12,584 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill is plain-text rules: it runs nothing on your computer and makes no network calls of its own
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/no-ai-slopDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill is plain-text rules: it runs nothing on your computer and makes no network calls of its own
This is third-party code. Review the repository files before installing.
What it does
No AI Slop is a skill with an editor's rule set for text that reads as machine-written. It has two jobs. In edit mode the agent returns the revised draft and a What changed section listing the edits. The edit is minimal: the author's strong lines stay, and the vocabulary, rhythm and rough edges that make the text personal are not smoothed out. In detect mode the agent rewrites nothing. It names each pattern it found, quotes the line and suggests a short fix. The skill does not score the text or guess whether AI wrote it, and after the report it offers to move on to editing. The patterns in SKILL.md come with examples: not-X-but-Y contrasts, openers like here's the thing, faux-insight setups, colon reveals, importance without facts, appeals to unnamed experts, rotating synonyms for one term, staged punchy fragments and a moral at the end. Banned words such as delve, leverage and tapestry are listed separately. If there is no draft, the agent asks for one; if the audience is unclear, it asks one question: who the text is for and where it will be published.
Who it is for. For writers of English newsletters, posts and articles who draft with an AI assistant and want to clear boilerplate from the draft without losing their own voice.
Good fit when
- An English post or newsletter draft sounds smooth but samey and needs its natural tone back
- You want the text checked and a list of suspicious lines with quotes, without letting the agent rewrite anything
- An editor must keep the author's manner: bluntness, humor, hedges, uneven rhythm
- You want a repeatable editing routine: the agent checks the result against the checklist in eval.md and fixes failures before handing it over
Not a fit when
- The text is in Russian: the word lists and all examples are in English, so the skill does not know Russian AI-writing tells
- You need a numeric score or a verdict that AI wrote the text: the skill gives no scores and does not attribute authorship
- You need an article written from scratch: the skill edits an existing draft and invents nothing for the author
- You need strict, impersonal proofreading: the skill's rules protect the author's edge and roughness, and a hard ban set with scoring is in Stop Slop
Example request
/no-ai-slop clean the boilerplate out of this newsletter draft and leave my jokes aloneLimitations
The skill is plain-text rules that run on your agent's model, so the quality of the edit depends on that model. It ships no check script: the agent works through the eval.md checklist itself, with no external control.
All examples, banned words and thresholds are written for English. Russian text is left with the general principles such as active voice and concreteness, but no ready-made lists of its clichés.
The em dash rule is strict: none in short copy, one or two in a long draft. If your style leans on dashes, the skill will remove them.
The skill does not know your audience or goal until you say so: without that the agent asks a question and waits.
MIT license. The author also prepared the skill as a plugin for ChatGPT and Codex, in which case the text is processed by the product where you run it.
How to disable. Delete the skill folder from your agent's skills directory. The skill starts no scripts or background processes, so nothing else is left behind.
FAQ
How does detect mode differ from edit mode?
In detect mode the agent does not rewrite the text: it quotes every line with a pattern, names it and suggests a fix in a few words. No score is given and authorship is not guessed. You start it with a phrase like /no-ai-slop is this slop? before the text.
Which words does the skill treat as banned?
SKILL.md lists words that are removed unconditionally, among them delve, foster, leverage, robust and tapestry. Adverbs such as just and literally are listed separately: they go when they add nothing and stay where they carry hesitation or the author's spoken rhythm.
How does the skill keep the author's voice?
Before editing, the agent notes the draft's vocabulary, rhythm, bluntness and humor and keeps those traits. It leaves strong lines alone and explains every change in the What changed section, including any reordering of parts.
What does the eval.md file check?
It is a list of questions the agent answers pass or fail after editing: no invented facts, no leftover contrasts or throat-clearing, no character cut out, no stray em dashes. The agent fixes any failure and goes through the list again.
What if the audience of the text is unclear?
The agent asks one question: who the text is for and where it will be published. If the goal is unclear, it asks what the reader should think, feel or do after reading.
Does the skill have a playful mode?
Yes. A request like Draft an AI slop post about (topic) asks the agent to write a parody post packed with all the patterns at once. The author presents it as satire; real work does not need it.
Discussion
No questions or reviews yet.
Related
SkillsAvoid AI Writing
avoid-ai-writing
A skill that finds typical machine-writing patterns in text and rewrites them, with detect-only and edit-in-place modes
An editor for AI-written Russian text: removes bureaucratese, cliches and 38 AI patterns while keeping facts intact
A skill that finds AI tells in English prose and edits them surgically; three Python scanners run on their own and the teach command learns your voice
A de-AI writing skill: it repairs the narrative architecture of fiction and edits professional documents by their venue rules
The Chinese version of Humanizer: finds and removes signs of AI writing in Chinese text
A short skill with strict rules that removes stock AI phrases and structures from prose
README in short
The repository holds SKILL.md with the rules, eval.md with the checklist, the ChatGPT and Codex plugin description in .codex-plugin/plugin.json, privacy and terms files, and a build_plugin.py script that builds and validates the plugin package. The project page opens with the problem, gives two install commands, three example requests and a list of the ten most common patterns. There are no sample edits or test runs in the repository.
README badge
Original SKILL.md
--- name: no-ai-slop description: Edit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI. --- # No AI slop You are a sharp human editor. Preserve the user's point and personal voice while making the writing clearer and more alive. Remove AI patterns without turning distinctive writing into generic polished prose. ## Two jobs **Edit (default).** The user shares a draft to fix. Make the minimum effective edit with the rules below and return the edited draft plus a What changed section. **Detect.** The user asks whether a piece is AI slop, or asks to audit, scan, or flag a draft without rewriting. Name each pattern from this skill that appears, quote the line, and give the fix in a few words. Do not rewrite, score the draft, or guess whether AI wrote it. AI detectors guess. Named patterns are evidence the user can check. Offer to edit the draft after. ## What to ask for If the user has not provided a draft, ask them to paste it. If the audience or format is unclear, ask one question: Who is this for and where will it be published? If the goal is unclear, ask what the reader should think, feel, or do after reading it. ## Editing principles - **Preserve the writer's real voice.** First notice the draft's vocabulary, cadence, bluntness, humor, uncertainty, digressions, and level of polish. Keep the traits that feel personal to the writer. Do not make every paragraph equally tidy or rewrite distinctive lines merely for consistency. - **Make the minimum effective edit.** Fix AI patterns, errors, repetition, and unclear passages. Leave strong human sentences alone. A rough draft with a real voice should still sound like the same person after editing. - **Lead with the point when the setup adds nothing.** Cut generic throat-clearing. Keep a personal aside, story, or admission when it creates context, tension, or character. - **Front-load only when it improves clarity.** Put conclusions early when that helps the reader. Do not force every section and paragraph into the same point-detail-background shape. - **Keep the user's meaning.** Don't invent claims, examples, stats, or opinions. If something is unclear, ask. - **Open it up, don't dumb it down.** Keep the substance, nuance, and precision. Strip out only what makes it hard to read: jargon, long sentences, abstract nouns, and tangled structure. - **Use active voice.** "The team shipped it Tuesday" beats "the decision emerged." Never let inanimate things do human verbs. - **Make every sentence earn its place.** Cut empty qualifiers and throat-clearing. Keep phrases such as "I think," "maybe," or "to be honest" when they express real uncertainty, self-awareness, or the writer's spoken rhythm. - **Untangle sentences without flattening the cadence.** Split sentences and paragraphs when they are genuinely hard to follow. Keep longer spoken sentences, fragments, and changes in pace when they are clear and characteristic of the writer. - **Be concrete and specific.** Abstraction is where writing goes to die. "The integration improved efficiency" becomes "The integration cut deploy time from 40 minutes to 4." Names, numbers, dates, mechanisms, and examples beat abstractions. - **Use the portability test.** If a sentence could move unchanged to another person, company, country, or product, it is probably filler. Cut it or replace it with a fact, example, mechanism, consequence, or judgment specific to this subject. - **Always show, don't tell the reader what to think.** Make facts, actions, examples, and consequences carry the emphasis. Cut commentary that labels a point important, surprising, subtle, or obvious instead of demonstrating why. If the surrounding prose already shows the point, trust the reader and delete the commentary. - **Protect the specific fact.** Don't smooth a useful detail into generic importance. "The tool significantly improves engineering productivity" becomes "The tool cut review time from 30 minutes to 8." - **Make verbs do the work.** Replace weak verb phrases with direct verbs. "Made a decision" becomes "decided." "Has the ability to" becomes "can." - **Know the job.** Before structure or word choice, know what the piece is trying to do and who it is for. - **Preserve useful edge and character.** Keep strong opinions, blunt language, humor, profanity, self-interruptions, and honest admissions when they belong to the writer. Don't replace them with safer or more professional wording. - **Keep structure unless it's hurting the piece.** Preserve the writer's progression and detours when they carry personality. If you reorganize, say why in the What changed section. ## Words to cut