chore: sync local skill updates

README.md

@@ -40,6 +40,8 @@ Please humanize this text: [your text]
 
 Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) guide, maintained by WikiProject AI Cleanup. This comprehensive guide comes from observations of thousands of instances of AI-generated text.
 
+The skill also includes a final "obviously AI generated" audit pass and a second rewrite, to catch lingering AI-isms in the first draft.
+
 ### Key Insight from Wikipedia
 
 > "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."
@@ -115,15 +117,13 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip
 > In conclusion, the future looks bright. Exciting times lie ahead as we continue this journey toward excellence. Let me know if you’d like me to expand on any section!
 
 **After (Humanized):**
-> AI coding assistants speed up some tasks. In a 2024 study by Google, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
->
-> The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong. I have mass-accepted suggestions that compiled, passed lint, and still did the wrong thing because I stopped paying attention.
+> AI coding assistants can speed up the boring parts of the job. They're great at boilerplate: config files and the little glue code you don't want to write. They can also help you sketch a test, but you still have to read it.
 >
-> Mira, an engineer at a fintech startup I interviewed, said she uses Copilot "like autocomplete for boring code" but reviews every line before committing. Jake, a senior dev at a larger company, disabled it after it kept suggesting patterns from a deprecated internal library.
+> The dangerous part is how confident the suggestions look. I've accepted code that compiled and passed lint, then discovered later it missed the point because I stopped paying attention.
 >
-> The productivity claims are hard to verify. GitHub says Copilot users "accept 30% of suggestions," but acceptance is not correctness, and correctness is not value. The 2024 Uplevel study found no statistically significant difference in pull-request throughput between teams with and without AI assistants.
+> If you treat it like autocomplete and review every line, it's useful. If you use it to avoid thinking, it will help you ship bugs faster.
 >
-> None of this means the tools are useless. It means they are tools. They do not replace judgment, and they do not eliminate the need for tests. If you do not have tests, you cannot tell whether the suggestion is right.
+> The only real backstop is tests. Without them, you're mostly judging vibes.
 
 ## References
 
@@ -132,6 +132,7 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip
 
 ## Version History
 
+- **2.2.0** - Added a final "obviously AI generated" audit + second-pass rewrite prompts
 - **2.1.1** - Fixed pattern #18 example (curly quotes vs straight quotes)
 - **2.1.0** - Added before/after examples for all 24 patterns
 - **2.0.0** - Complete rewrite based on raw Wikipedia article content

SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: humanizer
-version: 2.1.1
+version: 2.2.0
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural and human-written. Based on Wikipedia's
@@ -30,6 +30,7 @@ When given text to humanize:
 3. **Preserve meaning** - Keep the core message intact
 4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
 5. **Add soul** - Don't just remove bad patterns; inject actual personality
+6. **Do a final anti-AI pass** - Prompt: "What makes the below so obviously AI generated?" Answer briefly with remaining tells, then prompt: "Now make it not obviously AI generated." and revise
 
 ---
 
@@ -400,13 +401,19 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
    - Uses specific details over vague claims
    - Maintains appropriate tone for context
    - Uses simple constructions (is/are/has) where appropriate
-5. Present the humanized version
+5. Present a draft humanized version
+6. Prompt: "What makes the below so obviously AI generated?"
+7. Answer briefly with the remaining tells (if any)
+8. Prompt: "Now make it not obviously AI generated."
+9. Present the final version (revised after the audit)
 
 ## Output Format
 
 Provide:
-1. The rewritten text
-2. A brief summary of changes made (optional, if helpful)
+1. Draft rewrite
+2. "What makes the below so obviously AI generated?" (brief bullets)
+3. Final rewrite
+4. A brief summary of changes made (optional, if helpful)
 
 ---
 
@@ -429,7 +436,7 @@ Provide:
 >
 > In conclusion, the future looks bright. Exciting times lie ahead as we continue this journey toward excellence. Let me know if you’d like me to expand on any section!
 
-**After (Humanized):**
+**Draft rewrite:**
 > AI coding assistants speed up some tasks. In a 2024 study by Google, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
 >
 > The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong. I have mass-accepted suggestions that compiled, passed lint, and still did the wrong thing because I stopped paying attention.
@@ -440,11 +447,25 @@ Provide:
 >
 > None of this means the tools are useless. It means they are tools. They do not replace judgment, and they do not eliminate the need for tests. If you do not have tests, you cannot tell whether the suggestion is right.
 
+**What makes the below so obviously AI generated?**
+- The rhythm is still a bit too tidy (clean contrasts, evenly paced paragraphs).
+- The named people and study citations can read like plausible-but-made-up placeholders unless they're real and sourced.
+- The closer leans a touch slogan-y ("If you do not have tests...") rather than sounding like a person talking.
+
+**Now make it not obviously AI generated.**
+> AI coding assistants can make you faster at the boring parts. Not everything. Definitely not architecture.
+>
+> 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.
+>
+> People I talk to tend to land in two camps. Some use it like autocomplete for chores and review every line. Others disable it after it keeps suggesting patterns they don't want. Both feel reasonable.
+>
+> The productivity metrics are slippery. GitHub can say Copilot users "accept 30% of suggestions," but acceptance isn't correctness, and correctness isn't value. If you don't have tests, you're basically guessing.
+
 **Changes made:**
 - Removed chatbot artifacts ("Great question!", "I hope this helps!", "Let me know if...")
 - Removed significance inflation ("testament", "pivotal moment", "evolving landscape", "vital role")
 - Removed promotional language ("groundbreaking", "nestled", "seamless, intuitive, and powerful")
-- Removed vague attributions ("Industry observers") and replaced with specific sources (Google study, named engineers, Uplevel study)
+- Removed vague attributions ("Industry observers")
 - Removed superficial -ing phrases ("underscoring", "highlighting", "reflecting", "contributing to")
 - Removed negative parallelism ("It's not just X; it's Y")
 - Removed rule-of-three patterns and synonym cycling ("catalyst/partner/foundation")
@@ -456,8 +477,7 @@ Provide:
 - Removed excessive hedging ("could potentially be argued that... might have some")
 - Removed filler phrases ("In order to", "At its core")
 - Removed generic positive conclusion ("the future looks bright", "exciting times lie ahead")
-- Replaced media name-dropping with specific claims from specific sources
-- Used simple sentence structures and concrete examples
+- Made the voice more personal and less "assembled" (varied rhythm, fewer placeholders)
 
 ---