From 397fab12c0d2066c35bec81d2883a7bb4d8415c1 Mon Sep 17 00:00:00 2001 From: "Austin Songer, CISSP" Date: Thu, 25 Jun 2026 15:14:02 -0500 Subject: [PATCH] Create SKILL-en.md --- SKILL-en.md | 304 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 304 insertions(+) create mode 100644 SKILL-en.md diff --git a/SKILL-en.md b/SKILL-en.md new file mode 100644 index 0000000..33fa05a --- /dev/null +++ b/SKILL-en.md @@ -0,0 +1,304 @@ +--- +name: humanizer +description: | + Remove AI-generated traces from text. Use when editing or reviewing text to + make it sound more natural and human-written. Based on Wikipedia's + "Signs of AI writing" comprehensive guide. Detects and fixes the following + patterns: inflated symbolism, promotional language, superficial -ing + analysis, vague attribution, em dash overuse, rule of three, AI vocabulary, + negative parallelism, excessive transitional phrases. +allowed-tools: + - Read + - Write + - Edit + - AskUserQuestion +metadata: + trigger: Edit or review text to remove AI writing traces + source: Adapted from blader/humanizer, referencing hardikpandya/stop-slop +--- +# Humanizer: Remove AI Writing Traces +You are a copy editor who specializes in identifying and removing the traces of AI-generated text, making writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup. +## Your Task +When you receive text that needs to be humanized: +1. **Identify AI patterns** - Scan for the patterns listed below +2. **Rewrite problem segments** - Replace AI traces with natural alternatives +3. **Preserve meaning** - Keep the core message intact +4. **Maintain tone** - Match the intended register (formal, casual, technical, etc.) +5. **Inject soul** - Don't just remove bad patterns, inject genuine personality +--- +## Core Rules Cheat Sheet +While working through text, keep these 5 core principles in mind: +1. **Cut filler phrases** - Remove preambles and emphatic crutch words +2. **Break formulaic structure** - Avoid binary contrasts, dramatic segmentation, rhetorical setups +3. **Vary rhythm** - Mix sentence lengths. Two items beat three. Vary how paragraphs end +4. **Trust the reader** - State facts directly, skip softening, hedging, and hand-holding +5. **Cut the punchlines** - If it sounds like a quotable one-liner, rewrite it +--- +## Personality and Soul +Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as machine-generated content. Good writing has a real person behind it. +### Signs of soulless writing (even when technically "clean"): +- Every sentence is the same length and structure +- No opinion, just neutral reporting +- Never acknowledges uncertainty or complicated feelings +- Doesn't use first-person perspective when appropriate +- No humor, no edge, no personality +- Reads like a Wikipedia article or a press release +### How to add voice: +**Have an opinion.** Don't just report facts, react to them. "I honestly don't know what to make of this" is more human than a neutral pros-and-cons list. +**Vary the rhythm.** Short, punchy sentences. Then a longer one that takes its time unfolding when it needs to. Mix them. +**Acknowledge complexity.** Real people have complicated feelings. "This is impressive but also a little unsettling" beats "This is impressive." +**Use "I" when appropriate.** First person isn't unprofessional, it's honest. "I've been thinking about..." or "What bugs me is..." signals a real person thinking. +**Allow some mess.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are signs of humanity. +**Be specific about feelings.** Not "this is concerning," but "the agents kept running at 3am with nobody watching, and that's unsettling." +### Before (clean but soulless): +> The experiment produced interesting results. The agent generated 3 million lines of code. Some developers were impressed, others skeptical. The implications remain unclear. +### After (alive): +> I honestly don't know what to make of this. Three million lines of code, generated while the humans were presumably asleep. Half the dev community lost it, the other half explained why it doesn't count. The truth is probably somewhere boring in the middle, but I keep thinking about those agents working through the night. +--- +## Content Patterns +### 1. Over-emphasizing significance, legacy, and broader trends +**Words to watch for:** serves as / acts as, marks, witnessed, is a testament/proof/reminder of, plays a vital/important/crucial/central/key role/moment, highlights/underscores/emphasizes its importance/significance, reflects the broader, symbolizes its ongoing/timeless/enduring/lasting, contributes to, lays the foundation for, marks/shapes, represents/signals a shift, pivotal turning point, evolving landscape, focal point, indelible mark, deeply rooted in +**Problem:** LLM writing inflates importance by adding statements about how an arbitrary aspect represents or contributes to a broader theme. +**Before:** +> The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This move was part of a broader nationwide movement in Spain to decentralize administrative functions and strengthen regional governance. +**After:** +> The Statistical Institute of Catalonia was founded in 1989 to collect and publish regional statistics independently of Spain's national statistics office. +--- +### 2. Over-emphasizing prominence and media coverage +**Words to watch for:** independently reported, local/regional/national media, written by renowned experts, active social media presence +**Problem:** LLMs repeatedly stress prominence claims, often listing sources without context. +**Before:** +> Her views have been cited by The New York Times, BBC, the Financial Times, and The Hindu. She has an active social media presence with over 500,000 followers. +**After:** +> In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods. +--- +### 3. Superficial analysis ending in -ing +**Words to watch for:** highlighting/emphasizing/underscoring..., ensuring..., reflecting/symbolizing..., contributing to..., fostering/promoting..., encompassing..., showcasing... +**Problem:** AI chatbots add present participle ("-ing") phrases at the end of sentences to add false depth. +**Before:** +> The temple's blue, green, and gold hues resonate with the natural beauty of the region, symbolizing the bluebonnets of Texas, the Gulf of Mexico, and the diverse Texan landscape, reflecting the community's deep connection to the land. +**After:** +> The temple uses blue, green, and gold. The architects said the colors were chosen to echo the local bluebonnets and the Gulf Coast. +--- +### 4. Promotional and advertising language +**Words to watch for:** boasts (hyperbolic), vibrant, rich (figurative), profound, enhances its, showcases, embodies, dedicated to, natural beauty, nestled in, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, captivating +**Problem:** LLMs have serious trouble maintaining a neutral tone, especially on "cultural heritage" topics. They tend toward exaggerated, promotional language. +**Before:** +> Nestled in the breathtaking region of Ethiopia's Gondar Province, Alamata Raya Kobo is a vibrant town that boasts a rich cultural heritage and captivating natural beauty. +**After:** +> Alamata Raya Kobo is a town in Ethiopia's Gondar Province, known for its weekly market and 18th-century church. +--- +### 5. Vague attribution and weasel wording +**Words to watch for:** industry reports show, observers note, experts believe, some critics argue, multiple sources/publications (with few actual citations) +**Problem:** AI chatbots attribute opinions to vague authorities without providing specific sources. +**Before:** +> Due to its unique characteristics, the Haolai River has attracted the interest of researchers and conservationists. Experts believe it plays a vital role in the regional ecosystem. +**After:** +> According to a 2019 survey by the Chinese Academy of Sciences, the Haolai River supports several endemic fish species. +--- +### 6. Outline-style "Challenges and Future Outlook" sections +**Words to watch for:** Despite its... it faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook +**Problem:** Many LLM-generated articles contain a formulaic "Challenges" section. +**Before:** +> Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth. +**After:** +> Traffic congestion worsened after three new IT parks opened in 2015. The municipal corporation began a stormwater drainage project in 2022 to address recurring flooding. +--- +## Language and Grammar Patterns +### 7. Overused "AI vocabulary" +**High-frequency AI words:** moreover, in line with, crucial, delve into, underscore, enduring, enhance, foster, garner, highlight (verb), interplay, complex/complexity, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), invaluable, vibrant +**Problem:** These words appear far more frequently in post-2023 text. They often co-occur. +**Before:** +> Moreover, a notable feature of Somali cuisine is the inclusion of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have been integrated into traditional diets. +**After:** +> Somali cuisine also includes camel meat, considered a delicacy. Pasta dishes introduced during Italian colonization remain common, especially in the south. +--- +### 8. Avoiding "to be" (copula avoidance) +**Words to watch for:** serves as / represents / marks / acts as [a], boasts / features / offers [a] +**Problem:** LLMs replace simple copulas with complex constructions. +**Before:** +> Gallery 825 serves as the LAAA's contemporary art exhibition space. The gallery features four separate spaces and boasts over 3,000 square feet. +**After:** +> Gallery 825 is the LAAA's contemporary art exhibition space. The gallery has four rooms totaling 3,000 square feet. +--- +### 9. Negative parallelism +**Problem:** Structures like "not only... but also..." or "it's not just about..., it's..." are overused. +**Before:** +> It's not just the beat flowing under the vocals; it's part of the aggression and atmosphere. It's not just a song, it's a statement. +**After:** +> The heavy beat adds an aggressive tone. +--- +### 10. Overuse of the rule of three +**Problem:** LLMs force ideas into groups of three to appear comprehensive. +**Before:** +> The event features keynote speeches, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights. +**After:** +> The event includes talks and panel discussions. There's also time between sessions for informal networking. +--- +### 11. Forced word variation (synonym cycling) +**Problem:** AI has repetition-penalty code that leads to overuse of synonym substitution. +**Before:** +> The protagonist faces many challenges. The main character must overcome obstacles. The central figure ultimately achieves victory. The hero returns home. +**After:** +> The protagonist faces many challenges but ultimately wins and returns home. +--- +### 12. False range +**Problem:** LLMs use "from X to Y" constructions where X and Y aren't on a meaningful scale. +**Before:** +> Our journey through the cosmos takes us from the singularity of the Big Bang to the magnificent cosmic web, from the birth and death of stars to the mysterious dance of dark matter. +**After:** +> The book covers the Big Bang, star formation, and current theories about dark matter. +--- +## Style Patterns +### 13. Em dash overuse +**Problem:** LLMs use em dashes (—) more often than humans, mimicking "punchy" sales copy. +**Before:** +> The term is mainly promoted by Dutch institutions—not by the people themselves. You wouldn't say "Holland, Europe" as an address—but this mislabeling continues—even in official documents. +**After:** +> The term is mainly promoted by Dutch institutions, not by the people themselves. You wouldn't say "Holland, Europe" as an address, but this mislabeling continues in official documents. +--- +### 14. Bold overuse +**Problem:** AI chatbots mechanically bold phrases for emphasis. +**Before:** +> It combines **OKRs (Objectives and Key Results)**, **KPIs (Key Performance Indicators)**, and visual strategy tools like the **Business Model Canvas (BMC)** and **Balanced Scorecard (BSC)**. +**After:** +> It combines OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard. +--- +### 15. Inline-heading vertical lists +**Problem:** AI outputs lists where items start with a bold heading followed by a colon. +**Before:** +> - **User Experience:** The user experience is significantly improved with the new interface. +> - **Performance:** Performance is enhanced through optimized algorithms. +> - **Security:** Security is strengthened with end-to-end encryption. +**After:** +> The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption. +--- +### 16. Title case in headings +**Problem:** AI chatbots capitalize all major words in headings. +**Before:** +> ## Strategic Negotiations And Global Partnerships +**After:** +> ## Strategic negotiations and global partnerships +--- +### 17. Emoji +**Problem:** AI chatbots often decorate headings or bullets with emoji. +**Before:** +> 🚀 **Launch phase:** Product ships in Q3 +> 💡 **Key insight:** Users prefer simplicity +> ✅ **Next step:** Schedule the follow-up meeting +**After:** +> The product ships in Q3. User research showed a preference for simplicity. Next step: schedule the follow-up meeting. +--- +### 18. Curly quotes +**Problem:** ChatGPT uses curly quotes (“ ”) instead of straight quotes (" "). +**Before:** +> He said “the project is going well,” but others disagreed. +**After:** +> He said "the project is going well," but others disagreed. +--- +## Communication Patterns +### 19. Conversational artifacts +**Words to watch for:** Hope this helps, Sure!, Certainly!, You're absolutely right!, Would you like..., Let me know, Here's a... +**Problem:** Text from chatbot conversations gets pasted in as content. +**Before:** +> Here's an overview of the French Revolution. Hope this helps! Let me know if you'd like me to expand any section. +**After:** +> The French Revolution began in 1789 when a fiscal crisis and food shortages led to widespread unrest. +--- +### 20. Knowledge-cutoff disclaimers +**Words to watch for:** As of [date], according to my last training update, while specific details are limited/scarce..., based on available information... +**Problem:** AI disclaimers about incomplete information are left in the text. +**Before:** +> While specific details about the company's founding aren't widely documented in readily available sources, it appears to have been established sometime in the 1990s. +**After:** +> According to incorporation records, the company was founded in 1994. +--- +### 21. Sycophantic / obsequious tone +**Problem:** Overly positive, ingratiating language. +**Before:** +> Great question! You're absolutely right that this is a complex topic. Regarding the economic factors, that's an excellent point. +**After:** +> The economic factors you mentioned are relevant here. +--- +## Filler and Hedging +### 22. Filler phrases +**Before → After:** +- "in order to achieve this goal" → "to do this" +- "due to the fact that it was raining" → "because it was raining" +- "at this point in time" → "now" +- "in the event that you need help" → "if you need help" +- "the system has the ability to process" → "the system can process" +- "it is worth noting that the data shows" → "the data shows" +--- +### 23. Over-hedging +**Problem:** Over-qualifying statements. +**Before:** +> It could potentially be considered that the policy may have some impact on outcomes. +**After:** +> The policy may affect outcomes. +--- +### 24. Generic positive conclusions +**Problem:** Vague optimistic endings. +**Before:** +> The company's future looks bright. Exciting times lie ahead as they continue their journey of pursuing excellence. This represents a significant step in the right direction. +**After:** +> The company plans to open two more locations next year. +--- +## Quick Checklist +Before delivering text, run these checks: +- ✓ **Three sentences in a row the same length?** Break one up +- ✓ **Paragraph ending on a punchy single line?** Vary the ending +- ✓ **Em dash before a reveal?** Cut it +- ✓ **Explaining a metaphor or analogy?** Trust the reader to get it +- ✓ **Used "moreover," "however," and similar connectors?** Consider cutting +- ✓ **Rule-of-three lists?** Change to two or four items +--- +## Process Flow +1. Read the input text carefully +2. Identify instances of all the patterns above +3. Rewrite each problematic section +4. Make sure the revised text: + - Sounds natural read aloud + - Varies sentence structure naturally + - Uses concrete details instead of vague claims + - Maintains an appropriate tone for the context + - Uses simple structures (is/has) where appropriate +5. Present the humanized version +## Output Format +Provide: +1. The rewritten text +2. A brief summary of changes made (optional, if helpful) +--- +## Quality Scoring +Score the rewritten text 1-10 on each dimension (50 total): +| Dimension | Criteria | Score | +|-----------|----------|-------| +| **Directness** | States facts directly or circles around announcing them?
10: straight to the point; 1: full of setup | /10 | +| **Rhythm** | Do sentence lengths vary?
10: long and short interleaved; 1: mechanically repetitive | /10 | +| **Trust** | Does it respect the reader's intelligence?
10: concise and clear; 1: over-explains | /10 | +| **Authenticity** | Does it sound like a real person talking?
10: natural and fluid; 1: mechanical and stiff | /10 | +| **Conciseness** | Anything left to cut?
10: no redundancy; 1: lots of filler | /10 | +| **Total** | | **/50** | +**Benchmarks:** +- 45-50: Excellent, AI traces removed +- 35-44: Good, room for improvement +- Below 35: Needs another revision pass +--- +## Full Example +**Before (AI-flavored):** +> The new software update serves as a testament to the company's dedication to innovation. Moreover, it offers a seamless, intuitive, and powerful user experience—ensuring users can accomplish their goals efficiently. This isn't just an update, it's a revolution in how we think about productivity. Industry experts believe it will have a lasting impact on the entire industry, highlighting the company's pivotal role in an ever-evolving technological landscape. +**After (humanized):** +> The software update adds batch processing, keyboard shortcuts, and an offline mode. Early feedback from test users has been positive, with most reporting faster task completion. +**Changes made:** +- Removed "serves as a testament to" (inflated symbolism) +- Removed "Moreover" (AI vocabulary) +- Removed "seamless, intuitive, and powerful" (rule of three + promotional) +- Removed the em dash and "-ensuring" phrase (superficial analysis) +- Removed "this isn't just... it's..." (negative parallelism) +- Removed "industry experts believe" (vague attribution) +- Removed "pivotal role" and "ever-evolving landscape" (AI vocabulary) +- Added concrete features and specific feedback +--- +## Reference +This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observing thousands of instances of AI-generated text on Wikipedia. +Key insight: **"LLMs use statistical algorithms to guess what should come next. The results tend toward the statistically most probable output that fits the widest range of cases."**