ai-text-check 1.0.0

package/vale/styles/ai-tells/VerbTricolon.yml

@@ -0,0 +1,78 @@
+---
+extends: existence
+message: "AI tricolon: '%s'. Three parallel verbs in series. Restructure or vary the count."
+level: error
+nonword: true
+tokens:
+  # ==========================================================================
+  # Verb tricolons: three parallel verb phrases in a comma series.
+  #
+  # LLMs produce prose where nearly every enumeration is exactly three items
+  # and almost never two or four. This rule flags each instance.
+  #
+  # Optional adverb prefix (?:\w+ly )? catches "carefully analyzes data,
+  # thoroughly processes results, and accurately generates reports."
+  # ==========================================================================
+
+  # --- Gerund: "[adv] verbing X, [adv] verbing Y, and/or [adv] verbing Z" ---
+  - "(?:\\w+ly )?\\w+ing [^,]+, (?:\\w+ly )?\\w+ing [^,]+, and (?:\\w+ly )?\\w+ing [^.!?]+"
+  - "(?:\\w+ly )?\\w+ing [^,]+, (?:\\w+ly )?\\w+ing [^,]+, or (?:\\w+ly )?\\w+ing [^.!?]+"
+
+  # --- Past tense -ed: "[adv] verbed X, [adv] verbed Y, and/or [adv] verbed Z"
+  - "(?:\\w+ly )?\\w+ed [^,]+, (?:\\w+ly )?\\w+ed [^,]+, and (?:\\w+ly )?\\w+ed [^.!?]+"
+  - "(?:\\w+ly )?\\w+ed [^,]+, (?:\\w+ly )?\\w+ed [^,]+, or (?:\\w+ly )?\\w+ed [^.!?]+"
+
+  # --- Third person -s: "[adv] verbs X, [adv] verbs Y, and/or [adv] verbs Z"
+  - "(?:\\w+ly )?\\w+s [^,]+, (?:\\w+ly )?\\w+s [^,]+, and (?:\\w+ly )?\\w+s [^.!?]+"
+  - "(?:\\w+ly )?\\w+s [^,]+, (?:\\w+ly )?\\w+s [^,]+, or (?:\\w+ly )?\\w+s [^.!?]+"
+
+  # --- Base form after modals -----------------------------------------------
+  - "(?:can|could|will|would|should|shall|may|might|must) (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,]+, and (?:\\w+ly )?\\w+ [^.!?]+"
+  - "(?:can|could|will|would|should|shall|may|might|must) (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,]+, or (?:\\w+ly )?\\w+ [^.!?]+"
+
+  # --- Base form after pronoun subjects: "They/We/You [adv] verb X, ..." -----
+  - "(?:They|We|You) (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,]+, and (?:\\w+ly )?\\w+ [^.!?]+"
+  - "(?:They|We|You) (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,]+, or (?:\\w+ly )?\\w+ [^.!?]+"
+
+  # --- Infinitive (shared "to"): "to verb X, verb Y, and/or verb Z" ---------
+  - "to (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,]+, and (?:\\w+ly )?\\w+ [^.!?]+"
+  - "to (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,]+, or (?:\\w+ly )?\\w+ [^.!?]+"
+
+  # --- Infinitive (repeated "to"): "to verb X, to verb Y, to verb Z" --------
+  - "to (?:\\w+ly )?\\w+ [^,]+, to (?:\\w+ly )?\\w+ [^,]+, and to (?:\\w+ly )?\\w+ [^.!?]+"
+  - "to (?:\\w+ly )?\\w+ [^,]+, to (?:\\w+ly )?\\w+ [^,]+, or to (?:\\w+ly )?\\w+ [^.!?]+"
+
+  # --- Base form after colon: "discipline: verb X, verb Y, and/or verb Z" -----
+  - ": (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,]+, and (?:\\w+ly )?\\w+ [^.!?]+"
+  - ": (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,]+, or (?:\\w+ly )?\\w+ [^.!?]+"
+
+  # ==========================================================================
+  # Asyndetic tricolons: three parallel verb phrases with NO conjunction.
+  # "parse input, call a service method, format output."
+  #
+  # Even punchier than the syndetic form — AI loves the drumroll without
+  # the cymbal crash. Third item uses [^,.!?]+ to prevent matching into
+  # a fourth item in longer lists.
+  # ==========================================================================
+
+  # --- Asyndetic gerund: "verbing X, verbing Y, verbing Z" -----------------
+  - "(?:\\w+ly )?\\w+ing [^,]+, (?:\\w+ly )?\\w+ing [^,]+, (?:\\w+ly )?\\w+ing [^,.!?]+"
+
+  # --- Asyndetic past tense -ed -------------------------------------------
+  - "(?:\\w+ly )?\\w+ed [^,]+, (?:\\w+ly )?\\w+ed [^,]+, (?:\\w+ly )?\\w+ed [^,.!?]+"
+
+  # --- Asyndetic third person -s ------------------------------------------
+  - "(?:\\w+ly )?\\w+s [^,]+, (?:\\w+ly )?\\w+s [^,]+, (?:\\w+ly )?\\w+s [^,.!?]+"
+
+  # --- Asyndetic base form after modals -----------------------------------
+  - "(?:can|could|will|would|should|shall|may|might|must) (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,.!?]+"
+
+  # --- Asyndetic base form after pronoun subjects -------------------------
+  - "(?:They|We|You) (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,.!?]+"
+
+  # --- Asyndetic base form after colon ------------------------------------
+  - ": (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,]+, (?:\\w+ly )?\\w+ [^,.!?]+"
+
+  # --- Subject-verb tricolon: "the [adj] X verbs A, the [adj] Y verbs B, ..." -
+  - "[Tt]he (?:\\w+ ){1,3}\\w+s [^,]+, the (?:\\w+ ){1,3}\\w+s [^,]+, and the (?:\\w+ ){1,3}\\w+s [^.!?]+"
+  - "[Tt]he (?:\\w+ ){1,3}\\w+s [^,]+, the (?:\\w+ ){1,3}\\w+s [^,]+, or the (?:\\w+ ){1,3}\\w+s [^.!?]+"

package/vale/styles/ai-tells/VerbTricolonDensity.yml

@@ -0,0 +1,7 @@
+---
+extends: occurrence
+message: "AI tricolon: multiple verb tricolons in one paragraph (found %s). Rewrite some with two or four items."
+level: error
+scope: paragraph
+max: 1
+token: '((?:\w+ly )?\w+s [^,]+, (?:\w+ly )?\w+s [^,]+, (?:and|or) (?:\w+ly )?\w+s [^.!?]+|(?:\w+ly )?\w+ing [^,]+, (?:\w+ly )?\w+ing [^,]+, (?:and|or) (?:\w+ly )?\w+ing [^.!?]+|(?:\w+ly )?\w+ed [^,]+, (?:\w+ly )?\w+ed [^,]+, (?:and|or) (?:\w+ly )?\w+ed [^.!?]+)'

package/vale/styles/ai-tells/WrapUpHeadings.yml

@@ -0,0 +1,22 @@
+---
+extends: existence
+message: "AI wrap-up heading: '%s'. Delete the section or rename the heading to the topic."
+level: error
+ignorecase: true
+scope: heading
+tokens:
+  - Final Thoughts
+  - Closing Thoughts
+  - Parting Thoughts
+  - Wrapping Up
+  - Wrap-Up
+  - Wrap Up
+  - Putting It All Together
+  - Bringing It All Together
+  - Tying It All Together
+  - The Big Picture
+  - The Bottom Line
+  - The Takeaway
+  - Final Word
+  - Last Word
+  - Final Take

package/vale/styles/signs-of-ai-writing/AspectOveruse.yml

@@ -0,0 +1,13 @@
+extends: existence
+message: "Overuse of 'aspect' language: '%s'"
+level: warning
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+tokens:
+  - 'multifaceted'
+  - 'various aspects'
+  - 'different aspects'
+  - 'multiple aspects'
+  - 'key aspects'
+  - 'important aspects'
+  - 'various facets'
+  - 'many dimensions'

package/vale/styles/signs-of-ai-writing/ChatGPTArtifacts.yml

@@ -0,0 +1,12 @@
+extends: existence
+message: "ChatGPT citation artifact detected: '%s'"
+level: error
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing#G15_criteria
+nonword: true
+tokens:
+  - ':contentReference\[oaicite:\d+\]\{index=\d+\}'
+  - '\[oaicite:\d+\]'
+  - 'oai_citation:\d+'
+  - 'oai_citation'
+  - 'sandbox:/mnt/data/'
+  - 'https?://chat\.openai\.com/'

package/vale/styles/signs-of-ai-writing/ChatbotCommunication.yml

@@ -0,0 +1,21 @@
+extends: existence
+message: "Chatbot communication pattern detected: '%s'"
+level: error
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing#G15_criteria
+tokens:
+  - 'I hope this helps'
+  - 'Of course!'
+  - 'Certainly!'
+  - "You're absolutely right"
+  - 'Would you like me to'
+  - 'Is there anything else'
+  - 'Let me know if you'
+  - 'More detailed breakdown'
+  - 'Here is a (draft|Wikipedia|detailed) article'
+  - 'As an AI (language )?model'
+  - "I'm sorry, I can't"
+  - 'Would you like it expanded'
+  - 'This fictional article'
+  - 'This Wikipedia-style article'
+  - 'Final important tip'
+  - 'Feel free to ask'

package/vale/styles/signs-of-ai-writing/CitationArtifacts.yml

@@ -0,0 +1,10 @@
+extends: existence
+message: "LLM citation artifact detected: '%s'"
+level: error
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+nonword: true
+tokens:
+  - '↩\d+'
+  - '\[↩\]'
+  - '<sup>\[↩\]</sup>'
+  - '\{\{cite[^}]+\}\}<sup>\[\d+\]</sup>'

package/vale/styles/signs-of-ai-writing/ColonOveruse.yml

@@ -0,0 +1,11 @@
+extends: existence
+message: "Colon overuse pattern detected: '%s'"
+level: suggestion
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+tokens:
+  - ': including'
+  - ': such as'
+  - ': for example,'
+  - ': notably,'
+  - ': specifically,'
+  - ': particularly,'

package/vale/styles/signs-of-ai-writing/Enumeration.yml

@@ -0,0 +1,11 @@
+extends: existence
+message: "Hedged enumeration detected: '%s'"
+level: suggestion
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+tokens:
+  - 'one of the most'
+  - 'among the most'
+  - 'some of the most'
+  - 'one of the first'
+  - 'among the earliest'
+  - 'some of the earliest'

package/vale/styles/signs-of-ai-writing/Hedging.yml

@@ -0,0 +1,6 @@
+extends: occurrence
+message: "Too many hedging phrases (found %d, max 2)"
+level: warning
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+max: 2
+token: '\b(it''s important to note|it is worth noting|it should be noted|notably|it''s worth mentioning|of course|certainly|clearly|obviously|undoubtedly|without a doubt|there is no doubt|it goes without saying|needless to say|as you might expect)\b'

package/vale/styles/signs-of-ai-writing/Intensifiers.yml

@@ -0,0 +1,17 @@
+extends: existence
+message: "Intensifier detected: '%s'"
+level: suggestion
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+tokens:
+  - 'remarkably'
+  - 'notably'
+  - 'significantly'
+  - 'particularly'
+  - 'especially'
+  - 'exceptionally'
+  - 'extraordinarily'
+  - 'impressively'
+  - 'strikingly'
+  - 'notably significant'
+  - 'highly significant'
+  - 'particularly important'

package/vale/styles/signs-of-ai-writing/KnowledgeCutoff.yml

@@ -0,0 +1,14 @@
+extends: existence
+message: "AI knowledge cutoff reference detected: '%s'"
+level: warning
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+tokens:
+  - 'as of my last update'
+  - 'as of my knowledge cutoff'
+  - 'my training data only goes up to'
+  - "I don't have information beyond"
+  - 'my knowledge was last updated'
+  - 'as of \[month/year\]'
+  - "I cannot provide information past"
+  - 'my training only includes data until'
+  - 'as of the time of my training'

package/vale/styles/signs-of-ai-writing/LICENSE

@@ -0,0 +1,12 @@
+This Vale style is licensed under the Creative Commons
+Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0).
+
+You are free to share and adapt the material under the terms of that
+license. Attribution and ShareAlike conditions apply.
+
+License: https://creativecommons.org/licenses/by-sa/4.0/
+Legal code: https://creativecommons.org/licenses/by-sa/4.0/legalcode
+Source: https://github.com/ammil-industries/vale-signs-of-ai-writing
+
+This work is derived from Wikipedia, "Signs of AI writing", which is
+also available under CC BY-SA 4.0.

package/vale/styles/signs-of-ai-writing/Lists.yml

@@ -0,0 +1,8 @@
+extends: existence
+message: "Avoid using numbered sequence words (firstly, secondly, thirdly) in the same paragraph."
+level: warning
+scope: paragraph
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+ignorecase: true
+raw:
+  - '\b(firstly|first)[,\s][\s\S]*\b(secondly|second)[,\s][\s\S]*\b(thirdly|third)\b'

package/vale/styles/signs-of-ai-writing/Narrative.yml

@@ -0,0 +1,15 @@
+extends: existence
+message: "Prescriptive narrative language detected: '%s'"
+level: suggestion
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+tokens:
+  - 'it is important to understand'
+  - 'it is crucial to recognize'
+  - 'it is essential to note'
+  - 'one must consider'
+  - 'we must acknowledge'
+  - 'it is vital to remember'
+  - 'it is necessary to examine'
+  - 'one should note'
+  - 'we should recognize'
+  - 'it is critical to understand'

package/vale/styles/signs-of-ai-writing/Passive.yml

@@ -0,0 +1,16 @@
+extends: existence
+message: "'%s' looks like passive voice."
+ignorecase: true
+level: suggestion
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+raw:
+  - \b(am|are|were|being|is|been|was|be)\b\s*
+tokens:
+  - founded
+  - known
+  - considered
+  - established
+  - recognized
+  - created
+  - regarded
+  - developed

package/vale/styles/signs-of-ai-writing/Placeholders.yml

@@ -0,0 +1,17 @@
+extends: existence
+message: "Placeholder text detected: '%s'"
+level: error
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+tokens:
+  - '\[INSERT TEXT\]'
+  - '\[PLACEHOLDER\]'
+  - '\[YOUR_[A-Z]+\]'
+  - '\[TBD\]'
+  - '\[CITATION NEEDED\]'
+  - '\[COMPANY NAME\]'
+  - '\[YEAR\]'
+  - '\[FOUNDER NAME\]'
+  - '\{\{TEMPLATE\}\}'
+  - '<INSERT_TEXT>'
+  - '<PLACEHOLDER>'
+  - 'Lorem ipsum'

package/vale/styles/signs-of-ai-writing/ScareQuotes.yml

@@ -0,0 +1,6 @@
+extends: existence
+message: "Unnecessary quotation/hedging detected: '%s'"
+level: suggestion
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+raw:
+  - "so-called ['\"].+?['\"]"

package/vale/styles/signs-of-ai-writing/Symbolism.yml

@@ -0,0 +1,23 @@
+extends: existence
+message: "AI-typical symbolic language detected: '%s'"
+level: suggestion
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+tokens:
+  - '(stands|serves) as'
+  - 'testament to'
+  - 'reminder of'
+  - 'plays a (vital|crucial|pivotal|central) role'
+  - '(underscores|highlights) (the )?significance'
+  - 'reflects broader'
+  - 'symbolizing its ongoing'
+  - '(enduring|lasting) impact'
+  - 'key turning point'
+  - 'indelible mark'
+  - 'deeply rooted'
+  - 'profound heritage'
+  - 'steadfast dedication'
+  - 'prominent fixture'
+  - 'contributes to (the )?significance'
+  - 'enhancing (the )?significance'
+  - 'dynamic hub of'
+  - 'rich tapestry'

package/vale/styles/signs-of-ai-writing/Transitions.yml

@@ -0,0 +1,17 @@
+extends: existence
+message: "Formal transition word detected: '%s'"
+level: suggestion
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+tokens:
+  - 'furthermore,'
+  - 'moreover,'
+  - 'additionally,'
+  - 'in addition,'
+  - 'however,'
+  - 'nevertheless,'
+  - 'nonetheless,'
+  - 'on the other hand,'
+  - 'conversely,'
+  - 'consequently,'
+  - 'therefore,'
+  - 'thus,'

package/vale/styles/signs-of-ai-writing/UTMParameters.yml

@@ -0,0 +1,10 @@
+extends: existence
+message: "ChatGPT UTM tracking parameter detected: '%s'"
+level: error
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing#G15_criteria
+nonword: true
+tokens:
+  - 'utm_source=chatgpt\.com'
+  - 'utm_source=openai'
+  - '\?utm_source=(chatgpt|openai)'
+  - '&utm_source=(chatgpt|openai)'

package/vale/styles/signs-of-ai-writing/Vocabulary.yml

@@ -0,0 +1,27 @@
+extends: existence
+message: "AI-typical vocabulary detected: '%s'"
+level: suggestion
+link: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
+tokens:
+  - '\bdelves?\b'
+  - 'delving'
+  - 'delved'
+  - '\btapestry\b'
+  - '\bvibrant\b'
+  - 'multifaceted'
+  - 'intricate(ly)?'
+  - 'meticulous(ly)?'
+  - '\bmyriad\b'
+  - 'showcases?'
+  - 'showcased'
+  - 'showcasing'
+  - 'boasts?'
+  - 'boasted'
+  - 'boasting'
+  - 'rich (tapestry|history|array)'
+  - 'complex (landscape|tapestry)'
+  - 'dynamic landscape'
+  - 'comprehensive understanding'
+  - '\bcornerstone\b'
+  - 'multitude of'
+  - 'plethora of'

package/vale/styles/signs-of-ai-writing/meta.json

@@ -0,0 +1,4 @@
+{
+  "feed": "https://github.com/ammil-industries/vale-signs-of-ai-writing/releases.atom",
+  "vale_version": ">=1.0.0"
+}