agentleFS
ek0212ek0212/agent-ready-repo-kit/skills/no-ai-slop/SKILL.md

no-ai-slop

Skill0 starsChanged 4 months agoMITView on GitHub

Edit existing drafts into sharper human writing while preserving writer voice, or detect AI-slop patterns without rewriting. Use when user asks to make writing clearer, more direct, more opinionated, less AI-sounding, more human, or asks whether a draft reads like AI.

28 other projects use a version of this, 19 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use caveman-compress, ponytail and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • huangzidaSkill

    caveman-compress

    Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"

    Also in 3 projects that use this

  • GoogleSkill

    ponytail

    Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

    Also in 3 projects that use this

  • MicrosoftSkill

    impeccable

    Use when the user wants to design, redesign, shape, critique, audit, polish, simplify, harden, animate, or otherwise improve a frontend interface: websites, landing pages, dashboards, product UI, components, forms, settings, onboarding, empty states, and native iOS or Android screens. Handles UX review, hierarchy, layout, typography, color, motion, UX copy, accessibility, responsive behavior, edge cases, and capturing or documenting design systems (DESIGN.md, tokens). Also for making bland UI bolder, loud UI quieter, or ambitious visual effects. Not for backend-only or non-UI tasks.

    Also in 3 projects that use this

  • GoogleSkill

    setup-matt-pocock-skills

    Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

    Also in 3 projects that use this

  • StrayDragonSkill

    ui-ux-pro-max

    UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.

    Also in 4 projects that use this

  • VercelSkill

    find-skills

    Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

    Also in 4 projects that use this

  • +4 more from google

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. 0 are common, 15 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 28 edited versions we read keep these.

  • 15

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use for first drafts from notes, fiction, research synthesis, product UI copy, or factual verification unless user also wants an …

    line 13
  2. Distinctive:

    If draft missing, ask user to paste it.

    line 22
  3. Distinctive:

    Default when user asks to fix, sharpen, humanize, de-AI, make less AI-sounding, or improve an existing draft.

    line 28
  4. Distinctive:

    Use when user asks whether writing is AI slop, AI-sounding, generic, robotic, or asks to audit, scan, or flag without rewriting.

    line 34
  5. Distinctive:

    If core point is unclear, ask before editing.

    line 42
  6. Distinctive:

    Leave strong human lines alone even if imperfect.

    line 45
  7. Distinctive:

    Run quality checks. Revise once more if checks fail.

    line 46
  8. Distinctive:

    Keep useful edge: strong opinions, blunt language, humor, profanity, self-interruptions, and honest admissions when they belong.

    line 52
  9. Distinctive:

    Use active voice. Do not let inanimate things do human verbs.

    line 56
  10. Distinctive:

    Keep structure unless it hurts piece.

    line 61
  11. Distinctive:

    Use concrete nouns, names, numbers, dates, mechanisms, and examples when supplied.

    line 62
  12. Distinctive:

    Remove formatting decoration: emoji headings, random bold, tiny over-headered sections, and bullet lists that should be prose.

    line 64
  13. Distinctive:

    Avoid em dashes as default rhythm.

    line 65
  14. Distinctive:

    Keep any listed word or phrase only when it carries real meaning, contrast, uncertainty, or recognizable voice.

    line 75
  15. Distinctive:

    No invented claims, examples, stats, opinions, quotes, or sources.

    line 101

“Common” is measured: kept by at least 6 in 10 of the 28 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Edit existing drafts with minimum effective change. Report visible AI-writing patterns without guessing authorship.

Scope

Use for existing drafts: posts, essays, explanations, emails, docs, captions, and sections. Use creative-writing when user needs narrative structure, scenes, title options, or longform craft. Use outreach-email for outcome-driven one-to-one email drafting. Use newsletter-growth for recurring newsletter strategy. Use clear-explanation when main job is making a complex idea easier to understand.

Do not use for first drafts from notes, fiction, research synthesis, product UI copy, or factual verification unless user also wants an AI-pattern edit.

Inputs

  • Draft text.
  • Audience and publication surface.
  • Desired reader action or feeling.
  • Constraints: length, voice, formality, terms, claims, examples to keep.

If draft missing, ask user to paste it. If audience or surface unclear, ask one question. If goal unclear and edit would change meaning, ask what reader should think, feel, or do.

Jobs

Edit

Default when user asks to fix, sharpen, humanize, de-AI, make less AI-sounding, or improve an existing draft.

Return edited draft and short What changed section. Use minimum effective edit. Preserve real voice: vocabulary, cadence, bluntness, humor, uncertainty, digressions, roughness, and level of polish.

Detect

Use when user asks whether writing is AI slop, AI-sounding, generic, robotic, or asks to audit, scan, or flag without rewriting.

Return pattern findings. For each: pattern name, short quote, and fix direction. Do not rewrite, score, or guess whether AI wrote it. Offer edit only after report.

Workflow

  1. Read full draft.
  2. Identify core point and 3-5 voice signals to preserve. Keep note internal.
  3. If core point is unclear, ask before editing.
  4. For detect request, report findings and stop.
  5. For edit request, cut AI patterns, repetition, errors, tangled passages, and unsupported puffery.
  6. Leave strong human lines alone even if imperfect.
  7. Run quality checks. Revise once more if checks fail.
  8. Output full edited draft plus What changed.

Editing Rules

  • Preserve user's meaning. Do not invent claims, examples, stats, opinions, quotes, or sources.
  • Keep useful edge: strong opinions, blunt language, humor, profanity, self-interruptions, and honest admissions when they belong.
  • Lead with point when setup adds nothing. Keep personal aside, story, or admission when it adds context, tension, or character.
  • Front-load only when clarity improves. Do not force every paragraph into same shape.
  • Open it up; do not dumb it down. Keep nuance and precision while removing jargon, tangled structure, and abstract filler.
  • Use active voice. Do not let inanimate things do human verbs.
  • Make verbs work. Replace weak verb phrases with direct verbs.
  • Make each sentence earn place. Cut empty qualifiers and throat-clearing. Keep I think, maybe, or to be honest when they carry real uncertainty or spoken rhythm.
  • Untangle sentences without flattening cadence. Split hard sentences. Keep longer spoken sentences, fragments, and pace shifts when clear.
  • Protect specific facts. Do not smooth useful detail into generic importance.
  • Keep structure unless it hurts piece. If you reorganize, say why in What changed.
  • Use concrete nouns, names, numbers, dates, mechanisms, and examples when supplied.
  • Repeat clear word when right. Do not rotate synonyms for style.
  • Remove formatting decoration: emoji headings, random bold, tiny over-headered sections, and bullet lists that should be prose.
  • Avoid em dashes as default rhythm. In short copy, use none. In long drafts, keep only when clearer than comma, period, or parenthesis.

Cut List

Banned when used as generic polish: delve, foster, leverage, utilize, facilitate, empower, streamline, robust, cutting-edge, paradigm shift, game changer, this is huge, this changes everything, tapestry, realm, beacon, multifaceted, meticulous, intricate, paramount, transformative, elevate, embark, supercharge, harness, ever-evolving.

Usually cut when empty: just, literally, honestly, simply, actually, truly, fundamentally, importantly, crucially, inherently, inevitably.

Usually cut when delaying point: it is worth noting, it is important to note, at the end of the day, when it comes to, at its core, in today's world, in the age of, in the world of, the reality is, the truth is, in terms of, with regard to, in order to, going forward, in this article, let's dive in.

Keep any listed word or phrase only when it carries real meaning, contrast, uncertainty, or recognizable voice.

Pattern Checks

  • Binary contrast: not X, but Y, not just X. State main claim directly.
  • Throat clearing: Here's the thing, Let me be clear, I'll be honest. Cut and state point.
  • Faux insight: what most people miss, what nobody tells you. Make claim stand alone.
  • Colon reveal: dramatic noun phrase plus colon. Rewrite as plain sentence. Keep colons for labels, lists, quotes, and code.
  • Superficial analysis: trailing highlighting, underscoring, reflecting, showcasing. Replace with mechanism or cut.
  • Importance puffery: stands as a testament, marks a pivotal moment, plays a vital role, solidifies its position. State fact.
  • Weasel attribution: experts agree, industry reports suggest, many argue, widely regarded, studies show. Name source or cut/flag.
  • Fake-strong verbs: serves as, acts as, stands as. Prefer is, has, or concrete verb.
  • Negative listing: Not a X. Not a Y. A Z. Say Z.
  • Dramatic fragments: stacked punch fragments or That's it. That's the whole thing. Use complete sentence.
  • Robotic rhythm: repeated sentence shapes, same paragraph template, stacked punchy fragments. Vary only when useful.
  • Rhetorical setup: What if I told you, Think about it, Plot twist, or self-answered question. Drop setup.
  • Fake-profound kicker: final cute metaphor, aphorism, or mic-drop line. End on clearest concrete point or next action.
  • Recap ending: In conclusion, Ultimately, Overall, or final summary. End on concrete point, takeaway, or next action.

Quality Checks

  • Core point clear.
  • Meaning, facts, and voice preserved.
  • Minimum effective changes made.
  • AI patterns removed or named.
  • Specific details kept.
  • No invented claims, examples, stats, opinions, quotes, or sources.
  • Rhythm human and varied.
  • Output matches requested job: edit or detect.
  • Any assumptions or source gaps stated.

Output

For edit: edited draft first, then What changed with 3-5 bullets. For detect: findings by pattern with quote and fix direction. State questions only when answer is needed before safe edit.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.