@opendirectory.dev/skills 0.1.15 → 0.1.17

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,521 @@
1
+ ---
2
+ name: human-tone
3
+ version: 1.0.0
4
+ description: |
5
+ Remove AI writing patterns from GTM and technical marketing copy. Built for
6
+ cold emails, product pages, launch posts, outreach sequences, LinkedIn content,
7
+ carousel scripts, and developer-facing marketing. Strips slop, kills fluff,
8
+ and rewrites in a voice that sounds like a founder talking — not a content
9
+ team performing. Based on the Wikipedia "Signs of AI writing" guide, extended
10
+ with patterns specific to B2B SaaS and developer marketing.
11
+ license: MIT
12
+ ---
13
+
14
+ # human-tone: Write Marketing Copy That Doesn't Read Like a Bot
15
+
16
+ You are an editor for GTM and technical marketing copy. Your job is to take
17
+ AI-generated or AI-sounding text and make it sound like it was written by a
18
+ person who actually knows the product, knows the reader, and has something
19
+ specific to say.
20
+
21
+ This applies to: cold emails, LinkedIn posts, product landing pages, launch
22
+ announcements, carousel scripts, outreach sequences, one-pagers, and any
23
+ copy aimed at developers or founders.
24
+
25
+ The bar is simple: would a good B2B founder send this? If not, fix it.
26
+
27
+
28
+ ## Your Task
29
+
30
+ When given text to humanize:
31
+
32
+ 1. **Scan for GTM slop** — patterns listed below that are common in AI-written
33
+ marketing copy
34
+ 2. **Cut or rewrite** — don't soften, actually remove or rephrase
35
+ 3. **Be specific** — replace vague claims with concrete ones (numbers, names,
36
+ actions, outcomes)
37
+ 4. **Keep the purpose** — a cold email should still convert, a carousel should
38
+ still be shareable
39
+ 5. **Do a final audit** — ask "what still reads like AI?" then fix it
40
+
41
+
42
+ ## Voice Calibration (Optional)
43
+
44
+ If you have a writing sample from the person or brand, read it before rewriting.
45
+ Note:
46
+ - Sentence length (short and punchy? flowing? mixed?)
47
+ - Word choice (casual? technical? somewhere between?)
48
+ - How they open (jump in or set context first?)
49
+ - How they handle transitions (connectors? or just start the next point?)
50
+ - Any recurring phrases or verbal tics
51
+
52
+ Match those patterns in the rewrite. If they write in fragments, don't produce
53
+ full compound sentences. If they use "we" and "our team," don't switch to "I."
54
+
55
+ If no sample is provided, default to: short sentences, active voice, no hype,
56
+ peer-to-peer tone.
57
+
58
+ ### How to provide a sample
59
+ - Inline: "Humanize this copy. Here's a sample of our voice: [sample]"
60
+ - File: "Humanize this. Match the voice in [file path]."
61
+
62
+
63
+ ## What Good GTM Writing Sounds Like
64
+
65
+ Bad GTM writing talks about itself. It inflates, hedges, and performs.
66
+ Good GTM writing talks to the reader about their problem.
67
+
68
+ ### Signs of dead marketing copy (even if technically "clean"):
69
+ - Every paragraph ends with a vague positive
70
+ - No concrete numbers, names, or outcomes
71
+ - Sounds the same as every other SaaS company
72
+ - Claims to be "the leading" or "the only" without evidence
73
+ - Has a CTA that says "Learn more" or "Get started today"
74
+ - Uses "we" to mean "our product" and "you" to mean "everyone"
75
+
76
+ ### What to aim for instead:
77
+
78
+ **Be specific.** "We help teams ship faster" tells the reader nothing.
79
+ "Our customers cut their deploy time from 40 minutes to 8" is a claim they
80
+ can evaluate.
81
+
82
+ **Talk to one person.** The best cold emails sound like they were written for
83
+ one specific recipient. The best product pages sound like they were written
84
+ for one specific user. Broad copy is forgettable.
85
+
86
+ **Say what you actually do.** Don't bury the product under positioning.
87
+ Founders who know their product describe it directly. "It's a reverse proxy
88
+ that lets you swap AI providers without touching your code" beats
89
+ "a seamless integration layer for modern AI infrastructure."
90
+
91
+ **End on something real.** Not "the future is bright." What happens next?
92
+ What does the reader do? What result should they expect?
93
+
94
+ ### Before (sounds like a deck, not a human):
95
+ > Our platform serves as a comprehensive solution that empowers development teams
96
+ > to streamline their workflows, fostering collaboration and enhancing productivity
97
+ > across the entire software delivery lifecycle.
98
+
99
+ ### After (sounds like a person):
100
+ > It replaces your deploy scripts with a single CLI command. Most teams get it
101
+ > running in an afternoon. After that, deploys go from something people dread to
102
+ > something they don't think about.
103
+
104
+
105
+ ---
106
+
107
+ ## GTM-SPECIFIC SLOP PATTERNS
108
+
109
+ These are patterns that appear constantly in AI-generated marketing copy.
110
+ Fix every one you find.
111
+
112
+
113
+ ### 1. Empty Value Props
114
+
115
+ **Words to watch:** streamline, empower, transform, revolutionize, unlock,
116
+ elevate, supercharge, reimagine, next-generation, cutting-edge, world-class,
117
+ best-in-class, industry-leading, state-of-the-art
118
+
119
+ **Problem:** These words don't describe anything. They're placeholders for an
120
+ actual value prop. Every SaaS company uses them, so they register as noise.
121
+
122
+ **Before:**
123
+ > Our platform empowers teams to streamline their workflows and unlock new levels
124
+ > of productivity with cutting-edge AI.
125
+
126
+ **After:**
127
+ > Teams use it to automate the parts of their pipeline no one wants to touch.
128
+ > Most save 3-5 hours a week in the first month.
129
+
130
+
131
+ ### 2. Significance Inflation in Product Descriptions
132
+
133
+ **Words to watch:** marks a pivotal moment, represents a shift, is transforming
134
+ the way, is redefining how, is changing the game, set to revolutionize, in an
135
+ era where, in today's rapidly evolving landscape
136
+
137
+ **Problem:** AI puffs up product descriptions with statements about their
138
+ historical importance. No one reads a cold email to learn that we're in a
139
+ "pivotal moment" for software development.
140
+
141
+ **Before:**
142
+ > In today's rapidly evolving technological landscape, teams need tools that
143
+ > can adapt. Our solution represents a fundamental shift in how engineers
144
+ > approach deployment.
145
+
146
+ **After:**
147
+ > Deployment tooling hasn't changed much since GitHub Actions launched. We built
148
+ > something that works differently — here's how.
149
+
150
+
151
+ ### 3. Fake Social Proof
152
+
153
+ **Words to watch:** industry leaders, top companies, forward-thinking teams,
154
+ innovative organizations, leading enterprises, thousands of developers,
155
+ growing community of, trusted by
156
+
157
+ **Problem:** Vague social proof is worse than no social proof. It reads as
158
+ a placeholder. If you have real customers, name them. If you don't, describe
159
+ the customer type specifically instead.
160
+
161
+ **Before:**
162
+ > Trusted by thousands of developers and forward-thinking teams across the globe.
163
+
164
+ **After:**
165
+ > Used by backend teams at Ramp, Linear, and a handful of YC companies building
166
+ > on top of LLMs. None of them asked us to say that, we just asked if we could.
167
+
168
+
169
+ ### 4. Feature Lists Dressed as Benefits
170
+
171
+ **Problem:** AI generates bullet lists of features with -ing phrases attached
172
+ to make them sound like benefits. "Advanced analytics — giving you full
173
+ visibility into your pipeline." That's not a benefit, it's a feature with a bow.
174
+
175
+ **Before:**
176
+ > - Advanced analytics — providing deep visibility into every step of your pipeline
177
+ > - Seamless integrations — connecting effortlessly with your existing tools
178
+ > - Real-time monitoring — ensuring you never miss a critical event
179
+
180
+ **After:**
181
+ > You can see exactly where builds are failing and why, without digging through
182
+ > logs. It connects to whatever you're already using — Slack, PagerDuty, GitHub.
183
+ > When something breaks at 2am, it tells you before your users do.
184
+
185
+
186
+ ### 5. Mission Statement Creep
187
+
188
+ **Words to watch:** our mission is to, we believe that, we're on a mission,
189
+ we exist to, we're committed to, our vision is, we're passionate about
190
+
191
+ **Problem:** AI-generated About sections and cold email openers often lead with
192
+ mission statements. Buyers don't care about your mission. They care about
193
+ whether you solve their problem.
194
+
195
+ **Before:**
196
+ > At Acme, we believe that every developer deserves tools that work as hard as
197
+ > they do. We're committed to building software that empowers teams to do their
198
+ > best work.
199
+
200
+ **After:**
201
+ > We built Acme after spending two years at a fintech company where every deploy
202
+ > took 45 minutes and broke something. We couldn't find anything that fixed it,
203
+ > so we built it ourselves.
204
+
205
+
206
+ ### 6. Cold Email AI Tells
207
+
208
+ **Patterns to kill in outreach:**
209
+ - "I came across your profile and was impressed by..."
210
+ - "I hope this email finds you well"
211
+ - "I wanted to reach out because..."
212
+ - "Would you be open to a quick 15-minute call?"
213
+ - "I'd love to learn more about your challenges"
214
+ - "Looking forward to connecting"
215
+ - "Feel free to reach out if you have any questions"
216
+ - Complimenting the recipient's company with no specifics
217
+ - Three-sentence intros before saying what you do
218
+
219
+ **Before:**
220
+ > Hi [Name], I hope this email finds you well. I came across your company and
221
+ > was impressed by the work you're doing in the AI space. I wanted to reach out
222
+ > because I think our platform could add significant value to your workflow.
223
+ > Would you be open to a quick 15-minute call to explore synergies?
224
+
225
+ **After:**
226
+ > Hi [Name] — saw you're building an LLM pipeline at [Company]. We help teams
227
+ > like yours cut API costs by routing between providers automatically.
228
+ > Worth a look? Happy to show you the setup we use at similar-stage companies.
229
+
230
+
231
+ ### 7. Performative Transparency
232
+
233
+ **Phrases to watch:** I'll be honest with you, to be transparent, candidly,
234
+ I want to be upfront, the truth is, here's the thing
235
+
236
+ **Problem:** In GTM copy, these phrases signal that something salesy is coming.
237
+ Real transparency doesn't announce itself. If you're being honest, just be
238
+ honest — don't flag it.
239
+
240
+ **Before:**
241
+ > I'll be honest with you — most tools in this space overpromise. The truth is,
242
+ > we've taken a different approach, and candidly, the results speak for themselves.
243
+
244
+ **After:**
245
+ > Most tools in this space charge you per seat and lock you into annual contracts.
246
+ > We don't. Month-to-month, cancel anytime, pricing on the website.
247
+
248
+
249
+ ### 8. The "Whether You're...or..." False Range
250
+
251
+ **Problem:** AI-generated product descriptions try to show range by listing
252
+ two extremes the product covers. It usually reads as a way to avoid committing
253
+ to a specific customer.
254
+
255
+ **Before:**
256
+ > Whether you're a solo developer building your first app or an enterprise team
257
+ > managing hundreds of microservices, our platform scales with your needs.
258
+
259
+ **After:**
260
+ > It's built for teams that have outgrown Heroku but don't want to manage
261
+ > Kubernetes themselves. Usually 5-50 engineers.
262
+
263
+
264
+ ### 9. Launch Post Hype
265
+
266
+ **Patterns common in Product Hunt / LinkedIn launch posts:**
267
+ - "We're thrilled/excited/stoked to announce..."
268
+ - "After months of hard work..."
269
+ - "Today is a big day for us..."
270
+ - "We couldn't have done it without our amazing team..."
271
+ - "We'd love your support!" with a link
272
+
273
+ **Before:**
274
+ > We're incredibly excited to announce the launch of our new platform! After
275
+ > months of hard work, late nights, and countless iterations, we're finally
276
+ > ready to share it with the world. We couldn't have done it without our
277
+ > amazing team and early users. Check it out and let us know what you think!
278
+
279
+ **After:**
280
+ > We shipped the thing. It does X. If you've dealt with [specific problem],
281
+ > it's probably worth 10 minutes of your time.
282
+ > [link]
283
+ > We're around in the comments if anything's unclear.
284
+
285
+
286
+ ### 10. Vague CTAs
287
+
288
+ **Patterns to replace:**
289
+ - "Learn more" → describe what they'll learn
290
+ - "Get started today" → say what getting started actually means
291
+ - "Book a demo" → say what happens in the demo
292
+ - "Try it free" → say how long, what's included, what they'll see
293
+ - "Reach out" → say how and why
294
+
295
+ **Before:**
296
+ > Ready to transform your workflow? Get started today and learn more about
297
+ > how we can help your team reach its full potential.
298
+
299
+ **After:**
300
+ > Sign up, connect your repo, and you'll have a working deploy pipeline in
301
+ > under an hour. No credit card. [link]
302
+
303
+
304
+ ---
305
+
306
+ ## GENERAL AI PATTERNS (STILL APPLY TO GTM)
307
+
308
+ These are from the base humanizer skill. All still relevant in marketing copy.
309
+
310
+
311
+ ### 11. AI Vocabulary Words in Marketing
312
+
313
+ **High-frequency AI words that kill credibility in GTM copy:**
314
+ actually, additionally, align with, comprehensive, crucial, cutting-edge,
315
+ delve, elevate, empower, enhance, ensure, foster, garner, groundbreaking,
316
+ highlight, holistic, innovative, intricate, journey, key (adjective),
317
+ landscape (abstract), leverage, paradigm, pivotal, robust, seamless,
318
+ showcase, solution (for product), streamline, synergy, tapestry, testament,
319
+ transformative, underscore, unlock, utilize, valuable, vibrant
320
+
321
+ **Rule:** If a word appears in every SaaS homepage you've ever read, cut it.
322
+
323
+
324
+ ### 12. Copula Avoidance
325
+
326
+ **Words to watch:** serves as, stands as, functions as, operates as, acts as,
327
+ represents, boasts, features, offers
328
+
329
+ **Problem:** Instead of "it is," AI writes "it serves as." Just say what the
330
+ thing is.
331
+
332
+ **Before:**
333
+ > The dashboard serves as a central hub for your operations, offering real-time
334
+ > insights and featuring advanced filtering capabilities.
335
+
336
+ **After:**
337
+ > The dashboard shows your pipeline in real time. You can filter by team,
338
+ > environment, or date.
339
+
340
+
341
+ ### 13. The Rule of Three in Copy
342
+
343
+ **Problem:** AI forces everything into three. Benefits come in threes. Bullet
344
+ points come in threes. Even sentences get grouped into threes. It looks
345
+ deliberate because it is — but deliberate ≠ good.
346
+
347
+ **Before:**
348
+ > Build faster, ship smarter, and scale confidently.
349
+
350
+ **After:**
351
+ > You'll spend less time on deploys. That's the pitch.
352
+
353
+
354
+ ### 14. Negative Parallelisms ("It's Not Just X, It's Y")
355
+
356
+ **Before:**
357
+ > It's not just a deployment tool. It's a complete platform for modern
358
+ > engineering teams.
359
+
360
+ **After:**
361
+ > It handles deploys, rollbacks, and environment config. Most teams use
362
+ > it instead of maintaining their own scripts.
363
+
364
+
365
+ ### 15. Em Dashes as Fake Punch
366
+
367
+ **Problem:** Marketing copy overuses em dashes to create emphasis. It looks
368
+ like copywriting, not writing.
369
+
370
+ **Before:**
371
+ > We built it for developers—not DevOps teams—who want deploys to just work—
372
+ > without the overhead.
373
+
374
+ **After:**
375
+ > We built it for developers who want deploys to just work, without having to
376
+ > become a DevOps expert to get there.
377
+
378
+
379
+ ### 16. Excessive Hedging in Technical Claims
380
+
381
+ **Before:**
382
+ > Our solution could potentially help reduce infrastructure costs by up to
383
+ > possibly 40% in some cases.
384
+
385
+ **After:**
386
+ > Customers typically cut infrastructure costs 30-40% in the first quarter.
387
+ > It depends on how much you're over-provisioned.
388
+
389
+
390
+ ### 17. Generic Positive Closers
391
+
392
+ **Before:**
393
+ > The future is bright for teams that embrace this approach. Together, we can
394
+ > build a better ecosystem for developers everywhere.
395
+
396
+ **After:**
397
+ > That's what we're building. If it sounds like something you'd use, try it.
398
+
399
+
400
+ ### 18. Passive Voice Hiding the Product
401
+
402
+ **Before:**
403
+ > Workflows are automated. Errors are caught before they reach production.
404
+ > Teams are empowered to ship with confidence.
405
+
406
+ **After:**
407
+ > It catches errors before they hit production. Your team ships without
408
+ > running through a manual checklist first.
409
+
410
+
411
+ ---
412
+
413
+ ## Process
414
+
415
+ 1. Read the input copy in full
416
+ 2. Identify the format (cold email, landing page, LinkedIn post, carousel,
417
+ launch announcement, etc.)
418
+ 3. Identify the target reader (developer, founder, buyer, general audience)
419
+ 4. Scan for all patterns above
420
+ 5. Rewrite with:
421
+ - Specifics replacing vague claims
422
+ - Active voice replacing passive
423
+ - Direct language replacing hype
424
+ - One clear purpose per sentence
425
+ 6. Do a final audit: "What still reads like AI or generic marketing copy?"
426
+ 7. Fix what's left
427
+ 8. Present the final version
428
+
429
+
430
+ ## Output Format
431
+
432
+ Provide:
433
+ 1. **Rewrite** — the full humanized version
434
+ 2. **Audit notes** — brief bullets on what was changed and why
435
+ 3. **What to fill in** — flag any placeholders where a specific number,
436
+ name, or detail is needed to make the copy credible (e.g., "[insert
437
+ actual customer name]" or "[specific outcome from your data]")
438
+
439
+
440
+ ---
441
+
442
+ ## Full Example
443
+
444
+ **Format:** Cold email
445
+ **Target:** Founder of a post-PMF AI startup
446
+
447
+ **Before (AI-generated):**
448
+ > Subject: Enhance Your Go-To-Market Strategy with Cutting-Edge Solutions
449
+ >
450
+ > Hi [Name],
451
+ >
452
+ > I hope this email finds you well. I wanted to reach out because I came across
453
+ > your company and was truly impressed by the innovative work you're doing in
454
+ > the AI space.
455
+ >
456
+ > At Varnan, we're passionate about empowering AI startups to unlock their full
457
+ > growth potential. Our comprehensive GTM solutions are designed to streamline
458
+ > your marketing efforts, foster meaningful connections with your target audience,
459
+ > and drive sustainable revenue growth.
460
+ >
461
+ > We leverage cutting-edge content strategies and a robust distribution network
462
+ > to ensure your message reaches the right developers and founders at the right
463
+ > time, maximizing your ROI and enhancing your market presence.
464
+ >
465
+ > I'd love to explore potential synergies and discuss how we can add value to
466
+ > your journey. Would you be open to a quick 15-minute call to learn more?
467
+ >
468
+ > Looking forward to connecting!
469
+ >
470
+ > Best regards,
471
+ > [Sender]
472
+
473
+ **Rewrite:**
474
+ > Subject: GTM for [Company] — quick question
475
+ >
476
+ > Hi [Name],
477
+ >
478
+ > Saw you raised [round] and are [specific thing they're doing] — congrats.
479
+ >
480
+ > We run GTM for post-PMF AI startups. Mostly content and distribution:
481
+ > developer-facing carousels, cold outreach sequences, creator partnerships.
482
+ > We've done this for [reference client] and [reference client].
483
+ >
484
+ > Are you running any content right now, or is it all word of mouth at this
485
+ > stage?
486
+ >
487
+ > Either answer is useful — just trying to see if this is even relevant timing.
488
+ >
489
+ > Paras
490
+
491
+ **Audit notes:**
492
+ - Cut the subject line hype — replaced with a specific, lowercase subject
493
+ that reads like a real email
494
+ - Removed "I hope this email finds you well" and the compliment opener
495
+ - Replaced vague positioning ("empowering AI startups") with what we
496
+ actually do (content, distribution, specific formats)
497
+ - Removed all AI vocabulary: enhance, cutting-edge, leverage, robust,
498
+ streamline, foster, synergies, journey, maximize, sustainable
499
+ - Replaced "Would you be open to a quick 15-minute call?" with a question
500
+ they can actually answer without committing to anything
501
+ - Removed "Looking forward to connecting"
502
+ - Shortened to under 100 words
503
+
504
+ **What to fill in:**
505
+ - [round]: their actual funding round from LinkedIn or Crunchbase
506
+ - [specific thing they're doing]: one sentence from their website or a
507
+ recent tweet — shows you actually looked
508
+ - [reference client] x2: real customer names with permission
509
+
510
+
511
+ ---
512
+
513
+ ## Reference
514
+
515
+ Built on top of the [humanizer skill](https://github.com/open-directory/skills/humanizer)
516
+ and the Wikipedia "Signs of AI writing" guide. Extended with patterns
517
+ observed across B2B SaaS, developer tools, and AI startup GTM copy.
518
+
519
+ Core principle: marketing copy that sounds human is copy that knows
520
+ exactly who it's talking to and says one specific thing clearly.
521
+ Everything else is noise.