no-ai-slop
Skill6 starsChanged 9 days agoMITView on GitHub
Write like a sharp human professional, not a chatbot. Use whenever drafting or editing text someone will send or publish as their own — resumes, CVs, cover letters, LinkedIn posts, emails, bios, application answers, reports. Strips generic filler, buzzwords, inflated claims and tell-tale AI phrasing, and keeps only content that is specific, true and relevant to the reader.
28 other projects use a version of this.
Adopted by
Most recently taken up by
- nicolas-diez/personal-ostheir own version, first seen Nov 8, 2026
- rivardoad9-source/hermes-skillstheir own version, first seen Nov 8, 2026
- ethosagent/ethostheir own version, first seen Nov 3, 2026
- dglogan42/Claude-Skillstheir own version, first seen Oct 26, 2026
- mannyandrs45/agentic-skill-librarytheir own version, first seen Oct 15, 2026
- pmarreck/llm_skillstheir own version, first seen Oct 15, 2026
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.
huangzidaSkillcaveman-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
GoogleSkillponytail
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
MicrosoftSkillimpeccable
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
GoogleSkillsetup-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
StrayDragonSkillui-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
VercelSkillfind-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
Other versions28 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 28
- petergyang/no-ai-slop★ 12ksame name
- huytieu/COG-second-brain★ 1.3ksame name
- realrossmanngroup/no_ai_slop_writing_rules★ 668same name
- kv0906/cc-skills★ 42same name
- ethosagent/ethos★ 22same name
- shortcuts/dotfiles★ 18same name
- YuliangXiu/de-ai-router★ 9same name
- SoftMissT/tudo-sobre-vibe-coding★ 8same name
- coolxeo/grok-bot-skills★ 7same name
- nicolas-diez/personal-os★ 4same name
18 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- job-radarSkill
- tailored-cvSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
19 rules. 0 are common, 19 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 28 edited versions we read keep these.
19
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
- Distinctive: line 12
Before writing, list what the reader needs (for a job application: the posting's key requirements).
- Distinctive: line 21
Every claim needs a concrete anchor: a product, a client, a tool, a scope, a result.
- Distinctive: line 22
Use numbers only if they are in the source material.
- Distinctive: line 27
Do not use these (or close variants) unless quoting the job posting:
- Distinctive: line 36
No rule-of-three lists for rhythm ("innovative, scalable and robust").
- Distinctive: line 37
No em-dash chains or dramatic dashes.
- Distinctive: line 38
No rhetorical questions, no exclamation marks in professional text.
- Distinctive: line 39
No restating the same point in the closing paragraph.
- Distinctive: line 40
No self-praise adjectives (excellent, outstanding, strong) about the writer.
- Distinctive: line 41
No emojis, no bold-for-emphasis inside sentences, no headings in a cover letter.
- Distinctive: line 42
No hedging stacks ("I believe I could potentially help").
- Distinctive: line 43
Don't mirror every keyword from the posting.
- Distinctive: line 47
Never add experience, tools, titles, dates, degrees, certifications or achievements that aren't in the source.
- Distinctive: line 53
Write the way the person would say it in an interview: direct, calm, a little understated.
- Distinctive: line 58
Search the draft for every banned word and pattern above and rewrite those lines.
- Distinctive: line 59
Delete any sentence that would fit any other candidate's letter unchanged.
- Distinctive: line 60
Delete any bullet or skill that no requirement points to.
- Distinctive: line 61
Read the opening line: if it's generic, replace it with the most specific reason this role fits.
- Distinctive: line 62
Check every fact against the source material.
“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.
Files
No AI slop
Goal: the text should read as if a competent, busy professional wrote it in their own voice. A recruiter should not be able to tell an AI touched it.
1. Relevance first
Before writing, list what the reader needs (for a job application: the posting's key requirements). Then test every sentence, bullet and skill:
- Does it answer a requirement, or prove seniority or impact the reader cares about? Keep it.
- Otherwise cut it. Don't soften it, cut it.
Shorter and specific beats longer and complete. Never pad to reach a length.
2. Specific beats generic
- Every claim needs a concrete anchor: a product, a client, a tool, a scope, a result. "Built Python/Appium automation for a car maker's Android apps" not "Leveraged cutting-edge automation to drive quality".
- Use numbers only if they are in the source material. Never invent metrics, percentages or results.
- One idea per sentence. Plain subject–verb–object.
3. Banned words and phrases
Do not use these (or close variants) unless quoting the job posting:
- leverage, utilize, spearhead, synergy, robust, seamless, cutting-edge, state-of-the-art, game-changer, best-in-class, world-class, holistic, dynamic, innovative (as filler), passionate, thrive, journey, landscape, realm, tapestry, delve, embark, elevate, empower, unlock, harness, foster, navigate (figuratively), pivotal, crucial, paramount, meticulous, testament, showcase, ever-evolving, fast-paced
- "I am excited to apply", "I am thrilled", "I am writing to express my interest", "I believe I would be a great fit", "I am confident that", "proven track record", "results-driven", "detail-oriented team player", "hit the ground running", "wear many hats", "add value", "go above and beyond"
- "In today's …", "In the world of …", "When it comes to …", "It's worth noting", "Moreover", "Furthermore", "Additionally" (as sentence openers), "Not only … but also …", "It's not just X, it's Y"
- "I hope this finds you well", "Thank you for your time and consideration" stacked with other pleasantries — one short polite close is enough.
4. Banned patterns
- No rule-of-three lists for rhythm ("innovative, scalable and robust").
- No em-dash chains or dramatic dashes. Use a full stop or comma.
- No rhetorical questions, no exclamation marks in professional text.
- No restating the same point in the closing paragraph.
- No self-praise adjectives (excellent, outstanding, strong) about the writer. Show it with evidence instead.
- No emojis, no bold-for-emphasis inside sentences, no headings in a cover letter.
- No hedging stacks ("I believe I could potentially help").
- Don't mirror every keyword from the posting. Mirror a term only where the experience honestly matches it.
5. Truth
- Never add experience, tools, titles, dates, degrees, certifications or achievements that aren't in the source.
- For a gap, name the closest real experience plainly ("I haven't used Playwright in production; my end-to-end suites were Selenium and Appium"). Don't spin it.
6. Voice
- First person, active voice, past tense for past roles, present for current.
- Write the way the person would say it in an interview: direct, calm, a little understated.
- Vary sentence length naturally; avoid every paragraph having the same shape.
7. Final pass (always do this before delivering)
- Search the draft for every banned word and pattern above and rewrite those lines.
- Delete any sentence that would fit any other candidate's letter unchanged.
- Delete any bullet or skill that no requirement points to.
- Read the opening line: if it's generic, replace it with the most specific reason this role fits.
- Check every fact against the source material.
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
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.

