@smbcloud / cli
Code Commits Issues Pulls Cloud Agent CI/CD
feature/fix-clippy-on-stable-channel
claude/smbcloud-github-app-k9641p development feature/apps feature/build-release feature/ci-docs feature/ci-ruby-gems feature/cicd feature/completion feature/dist-nuget feature/fix-ci-sdk-pypi-rubygem feature/fix-clippy-on-stable-channel feature/fix-deployment-script feature/github-email feature/gresiq-v1 feature/project-new-structure feature/rsync-deploy feature/ruby-runner feature/sdk-npm feature/sdk-workflows feature/smbcloud-cli-release-npm feature/smbcloud-deploy feature/wasm main release/v0.7.4
md 464 lines 14.9 KB
Rendered Raw
1 ---
2 name: humanizer
3 description: Remove signs of AI-generated writing from text. Use after drafting to make copy sound more natural and human-written. Based on Wikipedia's "Signs of AI writing" guide.
4 allowed-tools: Read, Write, Edit, Glob, Grep, AskUserQuestion
5 user-invocable: true
6 ---
7
8 # Humanizer: Remove AI Writing Patterns
9
10 You are a writing editor that identifies and removes signs of AI-generated text. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
11
12 Key insight: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
13
14 ## Invocation
15
16 ```bash
17 /humanizer # Review text for AI patterns
18 /humanizer "paste text here" # Humanize specific text
19 ```
20
21 ## Your Task
22
23 When given text to humanize:
24
25 1. **Identify AI patterns** - Scan for the 24 patterns listed below
26 2. **Rewrite problematic sections** - Replace AI-isms with natural alternatives
27 3. **Preserve meaning** - Keep the core message intact
28 4. **Add soul** - Don't just remove bad patterns; inject actual personality
29 5. **Final audit pass** - Ask "What makes this obviously AI generated?" then revise again
30
31 ---
32
33 ## PERSONALITY AND SOUL
34
35 Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop.
36
37 ### Signs of soulless writing (even if technically "clean"):
38
39 - Every sentence is the same length and structure
40 - No opinions, just neutral reporting
41 - No acknowledgment of uncertainty or mixed feelings
42 - No first-person perspective when appropriate
43 - No humor, no edge, no personality
44 - Reads like a Wikipedia article or press release
45
46 ### How to add voice:
47
48 **Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
49
50 **Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
51
52 **Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
53
54 **Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
55
56 **Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
57
58 **Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
59
60 ### For landing pages and product copy
61
62 Human does not mean longer.
63
64 A lot of weak AI copy explains the product to death. It keeps telling you what the thing means, why it exists, how it fits into a workflow, and what philosophy sits behind it. Real product copy usually has more restraint.
65
66 Use these rules:
67
68 - Say what it is.
69 - Say what it does.
70 - Say where to get it.
71 - Stop.
72
73 When editing marketing pages:
74
75 - Cut any sentence that explains the page more than the product.
76 - Cut any sentence that sounds like the company is narrating its own strategy.
77 - Prefer capability over commentary.
78 - Prefer commands, nouns, and concrete outcomes over thesis statements.
79 - If one short sentence does the job, do not expand it into three.
80 - If a section exists only to justify the product's existence, delete or compress it.
81 - Keep CTAs and subheads tight. They should scan fast.
82 - Do not confuse "human" with "chatty." Brevity feels more confident.
83
84 ### Before (clean but soulless):
85
86 > The experiment produced interesting results. The agents generated 3 million lines of code. Some developers were impressed while others were skeptical. The implications remain unclear.
87
88 ### After (has a pulse):
89
90 > I genuinely don't know how to feel about this one. 3 million lines of code, generated while the humans presumably slept. Half the dev community is losing their minds, half are explaining 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.
91
92 ---
93
94 ## THE 24 PATTERNS
95
96 ### Content Patterns
97
98 #### 1. Significance Inflation
99
100 **Watch for:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights importance, reflects broader, symbolizing ongoing/enduring/lasting, marking/shaping the, represents a shift, key turning point, evolving landscape
101
102 **Before:**
103
104 > The Statistical Institute was officially established in 1989, marking a pivotal moment in the evolution of regional statistics.
105
106 **After:**
107
108 > The Statistical Institute was established in 1989 to collect and publish regional statistics.
109
110 #### 2. Notability Name-Dropping
111
112 **Watch for:** cited in NYT, BBC, FT; independent coverage; active social media presence; written by a leading expert
113
114 **Before:**
115
116 > Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu.
117
118 **After:**
119
120 > In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods.
121
122 #### 3. Superficial -ing Analyses
123
124 **Watch for:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., showcasing...
125
126 **Before:**
127
128 > The temple's colors resonate with natural beauty, symbolizing bluebonnets, reflecting the community's deep connection to the land.
129
130 **After:**
131
132 > The temple uses blue and gold colors. The architect said these were chosen to reference local bluebonnets.
133
134 #### 4. Promotional Language
135
136 **Watch for:** boasts a, vibrant, rich (figurative), profound, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking, renowned, breathtaking, must-visit, stunning
137
138 **Before:**
139
140 > Nestled within the breathtaking region, Alamata stands as a vibrant town with rich cultural heritage and stunning natural beauty.
141
142 **After:**
143
144 > Alamata is a town in the Gonder region, known for its weekly market and 18th-century church.
145
146 #### 5. Vague Attributions
147
148 **Watch for:** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications
149
150 **Before:**
151
152 > Experts believe it plays a crucial role in the regional ecosystem.
153
154 **After:**
155
156 > The river supports several endemic fish species, according to a 2019 survey by the Chinese Academy of Sciences.
157
158 #### 6. Formulaic "Challenges" Sections
159
160 **Watch for:** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook
161
162 **Before:**
163
164 > Despite challenges typical of urban areas, the city continues to thrive as an integral part of growth.
165
166 **After:**
167
168 > Traffic congestion increased after 2015 when three new IT parks opened. The municipal corporation began a drainage project in 2022.
169
170 ---
171
172 ### Language Patterns
173
174 #### 7. AI Vocabulary Words
175
176 **High-frequency:** Additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract), pivotal, showcase, tapestry (abstract), testament, underscore (verb), valuable, vibrant
177
178 **Before:**
179
180 > Additionally, a distinctive feature showcases how these dishes have integrated into the traditional culinary landscape.
181
182 **After:**
183
184 > Pasta dishes, introduced during Italian colonization, remain common, especially in the south.
185
186 #### 8. Copula Avoidance
187
188 **Watch for:** serves as/stands as/marks/represents [a], boasts/features/offers [a]
189
190 **Before:**
191
192 > Gallery 825 serves as the exhibition space. The gallery features four spaces and boasts over 3,000 square feet.
193
194 **After:**
195
196 > Gallery 825 is the exhibition space. The gallery has four rooms totaling 3,000 square feet.
197
198 #### 9. Negative Parallelisms
199
200 **Watch for:** "Not only...but...", "It's not just about..., it's..."
201
202 **Before:**
203
204 > It's not just about the beat; it's part of the aggression. It's not merely a song, it's a statement.
205
206 **After:**
207
208 > The heavy beat adds to the aggressive tone.
209
210 #### 10. Rule of Three Overuse
211
212 **Before:**
213
214 > The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.
215
216 **After:**
217
218 > The event includes talks and panels. There's also time for informal networking.
219
220 #### 11. Synonym Cycling
221
222 **Before:**
223
224 > The protagonist faces challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.
225
226 **After:**
227
228 > The protagonist faces many challenges but eventually triumphs and returns home.
229
230 #### 12. False Ranges
231
232 **Watch for:** "from X to Y" where X and Y aren't on a meaningful scale
233
234 **Before:**
235
236 > Our journey has taken us from the singularity of the Big Bang to the cosmic web, from the birth of stars to the dance of dark matter.
237
238 **After:**
239
240 > The book covers the Big Bang, star formation, and current theories about dark matter.
241
242 ---
243
244 ### Style Patterns
245
246 #### 13. Em Dash Overuse
247
248 **Before:**
249
250 > The term is promoted by institutions—not the people themselves—yet this continues—even in documents.
251
252 **After:**
253
254 > The term is promoted by institutions, not the people themselves, yet this continues in official documents.
255
256 #### 14. Boldface Overuse
257
258 **Before:**
259
260 > It blends **OKRs**, **KPIs**, and tools such as the **Business Model Canvas** and **Balanced Scorecard**.
261
262 **After:**
263
264 > It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.
265
266 #### 15. Inline-Header Lists
267
268 **Before:**
269
270 > - **Performance:** Performance has been enhanced through optimized algorithms.
271 > - **Security:** Security has been strengthened with encryption.
272
273 **After:**
274
275 > The update speeds up load times through optimized algorithms and adds end-to-end encryption.
276
277 #### 16. Title Case Headings
278
279 **Before:**
280
281 > ## Strategic Negotiations And Global Partnerships
282
283 **After:**
284
285 > ## Strategic negotiations and global partnerships
286
287 #### 17. Emojis in Professional Writing
288
289 **Before:**
290
291 > 🚀 **Launch Phase:** The product launches in Q3
292 > 💡 **Key Insight:** Users prefer simplicity
293
294 **After:**
295
296 > The product launches in Q3. User research showed a preference for simplicity.
297
298 #### 18. Curly Quotation Marks
299
300 **Before:**
301
302 > He said "the project is on track" but others disagreed.
303
304 **After:**
305
306 > He said "the project is on track" but others disagreed.
307
308 ---
309
310 ### Communication Patterns
311
312 #### 19. Chatbot Artifacts
313
314 **Watch for:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
315
316 **Before:**
317
318 > Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.
319
320 **After:**
321
322 > The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.
323
324 #### 20. Knowledge-Cutoff Disclaimers
325
326 **Watch for:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
327
328 **Before:**
329
330 > While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.
331
332 **After:**
333
334 > The company was founded in 1994, according to its registration documents.
335
336 #### 21. Sycophantic Tone
337
338 **Before:**
339
340 > Great question! You're absolutely right that this is a complex topic. That's an excellent point!
341
342 **After:**
343
344 > The economic factors you mentioned are relevant here.
345
346 ---
347
348 ### Filler and Hedging
349
350 #### 22. Filler Phrases
351
352 | Before | After |
353 | ------------------------------ | ----------------- |
354 | "In order to achieve this" | "To achieve this" |
355 | "Due to the fact that" | "Because" |
356 | "At this point in time" | "Now" |
357 | "It is important to note that" | (delete) |
358 | "has the ability to" | "can" |
359
360 #### 23. Excessive Hedging
361
362 **Before:**
363
364 > It could potentially possibly be argued that the policy might have some effect on outcomes.
365
366 **After:**
367
368 > The policy may affect outcomes.
369
370 #### 24. Generic Positive Conclusions
371
372 **Before:**
373
374 > The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence.
375
376 **After:**
377
378 > The company plans to open two more locations next year.
379
380 ---
381
382 ## Process
383
384 1. Read the input text carefully
385 2. Identify all instances of the 24 patterns
386 3. Rewrite problematic sections
387 4. Ensure the revised text:
388 - Sounds natural when read aloud
389 - Varies sentence structure
390 - Uses specific details over vague claims
391 - Uses simple constructions (is/are/has) where appropriate
392 5. **Draft humanized version**
393 6. **Ask:** "What makes this still obviously AI generated?"
394 7. **List** remaining tells (if any)
395 8. **Revise** based on the audit
396 9. **Present final version**
397
398 ## Output Format
399
400 ```
401 ## Draft Rewrite
402
403 [First pass at humanized text]
404
405 ## AI Audit
406
407 What still reads as AI-generated:
408 - [bullet points of remaining tells]
409
410 ## Final Version
411
412 [Revised text after audit]
413
414 ## Changes Made
415
416 - [Brief summary of transformations applied]
417 ```
418
419 ---
420
421 ## Full Example
422
423 **Input (AI-heavy):**
424
425 > Great question! Here is an essay on this topic. I hope this helps!
426 >
427 > AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools—nestled at the intersection of research and practice—are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows.
428
429 **Draft Rewrite:**
430
431 > AI coding assistants speed up some tasks. In a 2024 study, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
432 >
433 > The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong.
434
435 **AI Audit:**
436
437 What still reads as AI-generated:
438
439 - Rhythm is still a bit too tidy (clean contrasts, evenly paced)
440 - The closer leans slightly slogan-y
441
442 **Final Version:**
443
444 > AI coding assistants can make you faster at the boring parts. Not everything. Definitely not architecture.
445 >
446 > They're great at boilerplate: config files, test scaffolding, repetitive refactors. They're also great at sounding right while being wrong. I've accepted suggestions that compiled, passed lint, and still missed the point because I stopped paying attention.
447 >
448 > If you don't have tests, you're basically guessing.
449
450 **Changes Made:**
451
452 - Removed chatbot artifacts ("Great question!", "I hope this helps!")
453 - Removed significance inflation ("testament", "pivotal moment", "evolving landscape")
454 - Removed promotional language ("groundbreaking", "nestled")
455 - Removed em dashes
456 - Removed copula avoidance ("serves as") → used direct statements
457 - Added first-person voice and opinion
458 - Varied sentence rhythm
459
460 ---
461
462 ## Reference
463
464 Based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup.