@houtini/voice-analyser 1.1.0 → 1.2.1

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.
Files changed (88) hide show
  1. package/LICENSE +190 -0
  2. package/README.md +147 -131
  3. package/dist/analyzers/argument-flow.d.ts +50 -0
  4. package/dist/analyzers/argument-flow.d.ts.map +1 -0
  5. package/dist/analyzers/argument-flow.js +398 -0
  6. package/dist/analyzers/argument-flow.js.map +1 -0
  7. package/dist/analyzers/paragraph-transitions.d.ts +35 -0
  8. package/dist/analyzers/paragraph-transitions.d.ts.map +1 -0
  9. package/dist/analyzers/paragraph-transitions.js +241 -0
  10. package/dist/analyzers/paragraph-transitions.js.map +1 -0
  11. package/dist/analyzers/specificity-patterns.d.ts +27 -0
  12. package/dist/analyzers/specificity-patterns.d.ts.map +1 -0
  13. package/dist/analyzers/specificity-patterns.js +171 -0
  14. package/dist/analyzers/specificity-patterns.js.map +1 -0
  15. package/dist/analyzers/voice-markers.d.ts +5 -0
  16. package/dist/analyzers/voice-markers.d.ts.map +1 -1
  17. package/dist/analyzers/voice-markers.js +28 -1
  18. package/dist/analyzers/voice-markers.js.map +1 -1
  19. package/dist/analyzers/vulnerability-patterns.d.ts +22 -0
  20. package/dist/analyzers/vulnerability-patterns.d.ts.map +1 -0
  21. package/dist/analyzers/vulnerability-patterns.js +206 -0
  22. package/dist/analyzers/vulnerability-patterns.js.map +1 -0
  23. package/dist/index.js +18 -51
  24. package/dist/index.js.map +1 -1
  25. package/dist/tools/analyze-corpus.d.ts +1 -0
  26. package/dist/tools/analyze-corpus.d.ts.map +1 -1
  27. package/dist/tools/analyze-corpus.js +21 -137
  28. package/dist/tools/analyze-corpus.js.map +1 -1
  29. package/dist/tools/collect-corpus.d.ts +1 -0
  30. package/dist/tools/collect-corpus.d.ts.map +1 -1
  31. package/dist/tools/collect-corpus.js +2 -2
  32. package/dist/tools/collect-corpus.js.map +1 -1
  33. package/dist/tools/generate-narrative-guide.d.ts +25 -0
  34. package/dist/tools/generate-narrative-guide.d.ts.map +1 -0
  35. package/dist/tools/generate-narrative-guide.js +942 -0
  36. package/dist/tools/generate-narrative-guide.js.map +1 -0
  37. package/dist/utils/advanced-statistics.d.ts.map +1 -1
  38. package/dist/utils/advanced-statistics.js +8 -9
  39. package/dist/utils/advanced-statistics.js.map +1 -1
  40. package/dist/utils/micro-rhythm.d.ts +37 -0
  41. package/dist/utils/micro-rhythm.d.ts.map +1 -0
  42. package/dist/utils/micro-rhythm.js +260 -0
  43. package/dist/utils/micro-rhythm.js.map +1 -0
  44. package/dist/utils/zscore.d.ts +2 -8
  45. package/dist/utils/zscore.d.ts.map +1 -1
  46. package/dist/utils/zscore.js +3 -19
  47. package/dist/utils/zscore.js.map +1 -1
  48. package/package.json +2 -2
  49. package/dist/analyzers/char-ngrams.d.ts +0 -54
  50. package/dist/analyzers/char-ngrams.d.ts.map +0 -1
  51. package/dist/analyzers/char-ngrams.js +0 -208
  52. package/dist/analyzers/char-ngrams.js.map +0 -1
  53. package/dist/analyzers/detection-risk.d.ts +0 -28
  54. package/dist/analyzers/detection-risk.d.ts.map +0 -1
  55. package/dist/analyzers/detection-risk.js +0 -237
  56. package/dist/analyzers/detection-risk.js.map +0 -1
  57. package/dist/analyzers/lexical-diversity.d.ts +0 -36
  58. package/dist/analyzers/lexical-diversity.d.ts.map +0 -1
  59. package/dist/analyzers/lexical-diversity.js +0 -120
  60. package/dist/analyzers/lexical-diversity.js.map +0 -1
  61. package/dist/analyzers/pos-ngrams.d.ts +0 -59
  62. package/dist/analyzers/pos-ngrams.d.ts.map +0 -1
  63. package/dist/analyzers/pos-ngrams.js +0 -249
  64. package/dist/analyzers/pos-ngrams.js.map +0 -1
  65. package/dist/analyzers/syntactic-patterns.d.ts +0 -47
  66. package/dist/analyzers/syntactic-patterns.d.ts.map +0 -1
  67. package/dist/analyzers/syntactic-patterns.js +0 -186
  68. package/dist/analyzers/syntactic-patterns.js.map +0 -1
  69. package/dist/analyzers/word-ngrams.d.ts +0 -59
  70. package/dist/analyzers/word-ngrams.d.ts.map +0 -1
  71. package/dist/analyzers/word-ngrams.js +0 -259
  72. package/dist/analyzers/word-ngrams.js.map +0 -1
  73. package/dist/tools/generate-enhanced-guide.d.ts +0 -65
  74. package/dist/tools/generate-enhanced-guide.d.ts.map +0 -1
  75. package/dist/tools/generate-enhanced-guide.js +0 -1072
  76. package/dist/tools/generate-enhanced-guide.js.map +0 -1
  77. package/dist/tools/generate-guide.d.ts +0 -16
  78. package/dist/tools/generate-guide.d.ts.map +0 -1
  79. package/dist/tools/generate-guide.js +0 -228
  80. package/dist/tools/generate-guide.js.map +0 -1
  81. package/dist/utils/delta.d.ts +0 -56
  82. package/dist/utils/delta.d.ts.map +0 -1
  83. package/dist/utils/delta.js +0 -124
  84. package/dist/utils/delta.js.map +0 -1
  85. package/dist/utils/ngrams.d.ts +0 -72
  86. package/dist/utils/ngrams.d.ts.map +0 -1
  87. package/dist/utils/ngrams.js +0 -154
  88. package/dist/utils/ngrams.js.map +0 -1
package/LICENSE ADDED
@@ -0,0 +1,190 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to the Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ Copyright 2025 Houtini Ltd
179
+
180
+ Licensed under the Apache License, Version 2.0 (the "License");
181
+ you may not use this file except in compliance with the License.
182
+ You may obtain a copy of the License at
183
+
184
+ http://www.apache.org/licenses/LICENSE-2.0
185
+
186
+ Unless required by applicable law or agreed to in writing, software
187
+ distributed under the License is distributed on an "AS IS" BASIS,
188
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
189
+ See the License for the specific language governing permissions and
190
+ limitations under the License.
package/README.md CHANGED
@@ -1,9 +1,19 @@
1
1
  # Voice Analyser
2
2
 
3
3
  [![npm version](https://img.shields.io/npm/v/@houtini/voice-analyser)](https://www.npmjs.com/package/@houtini/voice-analyser)
4
- [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
4
+ [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
5
5
 
6
- Extract statistical voice models from your published writing. Generate LLM-optimized style guides that actually replicate how you write.
6
+ > **Experimental library** for extracting statistical voice models from your published writing. Generates immersive style guides that teach LLMs to replicate how you actually write - not through rules, but through examples and rhythm patterns.
7
+
8
+ ## Why This Exists
9
+
10
+ Traditional style guides list rules: "Use short sentences. Vary paragraph length. Include personal anecdotes."
11
+
12
+ This doesn't work. Writers don't follow rules - they channel voice.
13
+
14
+ This tool extracts the statistical fingerprint of your writing and presents it as immersive examples with annotations showing *what makes each passage feel human*. The goal is voice replication through pattern recognition, not rule compliance.
15
+
16
+ **Status:** Experimental. The approach works but is under active development.
7
17
 
8
18
  ## Installation
9
19
 
@@ -33,162 +43,189 @@ Restart Claude Desktop after saving.
33
43
 
34
44
  - Node.js 20+
35
45
 
36
- ## What It Does
46
+ ## Quick Start
37
47
 
38
- Analyses your published writing to create statistical voice models. No subjective "does this sound like me?" - measure it.
48
+ ### 1. Create an Output Directory
39
49
 
40
- **Captures:**
41
- - Sentence length distributions (not averages - the full histogram)
42
- - Function word fingerprints (z-scores showing your over-use/avoidance patterns)
43
- - First-person density and hedging patterns
44
- - Punctuation habits and British/American markers
45
- - N-gram patterns at character, word, and part-of-speech levels
46
- - AI clichés already present in YOUR writing
50
+ First, create a directory where your corpus and analysis will be stored:
47
51
 
48
- **Output:** 20,000-25,000 word statistical model ready for Claude to load as context.
52
+ ```
53
+ C:\writing\voice-models\ (Windows)
54
+ ~/writing/voice-models/ (Mac/Linux)
55
+ ```
49
56
 
50
- ## Quick Start
57
+ This directory will contain:
58
+ - Collected articles (markdown)
59
+ - Analysis JSON files
60
+ - Generated voice guides
51
61
 
52
- ### 1. Collect Your Writing
62
+ ### 2. Collect Your Writing
53
63
 
54
64
  ```
55
- Collect corpus from https://yoursite.com/post-sitemap.xml as "your-name"
65
+ Collect corpus from https://yoursite.com/post-sitemap.xml
66
+ Save as "my-voice" in "C:\writing\voice-models"
56
67
  ```
57
68
 
58
- Works with XML sitemaps, RSS feeds, or individual URLs. Collects up to 100 articles by default.
59
-
60
- ### 2. Analyse Patterns
69
+ The tool needs:
70
+ - `sitemap_url` - Your XML sitemap URL
71
+ - `output_name` - A name for this corpus (e.g., "my-voice", "blog-posts")
72
+ - `output_dir` - The directory you created above
61
73
 
74
+ **Example with all parameters:**
62
75
  ```
63
- Analyse corpus "your-name"
76
+ Collect corpus from https://example.com/post-sitemap.xml
77
+ Output name: "technical-writing"
78
+ Output directory: "C:\writing\voice-models"
79
+ Maximum articles: 50
64
80
  ```
65
81
 
66
- Generates statistical analysis of vocabulary, sentence structure, voice markers, and function word usage.
67
-
68
- ### 3. Generate Voice Model
82
+ ### 3. Analyse Patterns
69
83
 
70
84
  ```
71
- Generate enhanced guide for "your-name"
85
+ Analyse corpus "my-voice" in directory "C:\writing\voice-models"
72
86
  ```
73
87
 
74
- Creates an LLM-optimized style guide with concrete targets and examples.
75
-
76
- ## Usage Examples
88
+ This runs 14 analysers covering vocabulary, sentence structure, voice markers, argument flow, and paragraph transitions.
77
89
 
78
- ### Collect from Different Sources
90
+ ### 4. Generate Voice Guide
79
91
 
80
- **XML Sitemap:**
81
92
  ```
82
- Collect corpus from https://example.com/post-sitemap.xml as "writer-name" with max 50 articles
93
+ Generate narrative guide for "my-voice" in directory "C:\writing\voice-models"
83
94
  ```
84
95
 
85
- **RSS Feed:**
86
- ```
87
- Collect corpus from https://example.com/feed/ as "writer-name"
88
- ```
96
+ Creates an immersive style guide with annotated examples at:
97
+ `C:\writing\voice-models\my-voice\writing_style_my-voice_narrative.md`
89
98
 
90
- **Filter by URL pattern:**
91
- ```
92
- Collect corpus from https://example.com/sitemap.xml as "writer-name" filtering URLs matching "blog"
93
- ```
99
+ ## Using the Voice Guide
94
100
 
95
- ### Analysis Options
101
+ Once generated, the voice guide can be loaded into any LLM conversation to help it write in your voice.
96
102
 
97
- **Full analysis (recommended):**
98
- ```
99
- Analyse corpus "writer-name" with full analysis
100
- ```
103
+ ### Loading the Guide
101
104
 
102
- **Quick iteration:**
103
105
  ```
104
- Analyse corpus "writer-name" with quick analysis
106
+ Load the file C:\writing\voice-models\my-voice\writing_style_my-voice_narrative.md
107
+ and use it as a reference for all writing in this conversation.
105
108
  ```
106
109
 
107
- ### Output Formats
110
+ ### Example Prompts for Content Generation
108
111
 
109
- **LLM-optimized (for Claude context):**
112
+ **Blog post:**
110
113
  ```
111
- Generate enhanced guide for "writer-name" in llm format
114
+ Using the voice guide as your reference, write a blog post about [topic].
115
+
116
+ Key requirements:
117
+ - Match the sentence rhythm patterns shown in the examples
118
+ - Use the conversational devices naturally (not forced)
119
+ - Include the micro-rhythms: mid-thought pivots, embedded uncertainty, present-tense immediacy
120
+ - Vary sentence length as shown in the statistical targets
121
+ - Use British/American spelling as indicated in the guide
112
122
  ```
113
123
 
114
- **Human-readable overview:**
124
+ **Technical article:**
115
125
  ```
116
- Generate enhanced guide for "writer-name" in human format
126
+ Reference the voice guide and write a technical explanation of [concept].
127
+
128
+ Channel the voice by:
129
+ - Opening with the pattern shown in "Opening Moves" section
130
+ - Using specific product/tool names, not generic references
131
+ - Including admissions of complexity or uncertainty where authentic
132
+ - Following the argument flow patterns from the guide
133
+ - Matching the punctuation habits (especially dash usage)
117
134
  ```
118
135
 
119
- **Both formats:**
136
+ **Product review:**
120
137
  ```
121
- Generate enhanced guide for "writer-name" in both formats
138
+ Using the loaded voice guide, write a review of [product].
139
+
140
+ Capture the voice by:
141
+ - Starting with personal context (why you tested this)
142
+ - Blending technical specs with practical implications
143
+ - Using the transition patterns between paragraphs
144
+ - Including the "human tells" - parenthetical asides, mid-thought corrections
145
+ - Ending with the closing patterns shown in examples
122
146
  ```
123
147
 
124
- ## What Gets Measured
125
-
126
- ### Function Word Stylometry
127
-
128
- Z-scores reveal unconscious patterns:
129
-
130
- | Z-Score | Meaning | Example |
131
- |---------|---------|---------|
132
- | +2.0+ | Highly distinctive | "whilst" +5.7 (British marker) |
133
- | +1.0 to +2.0 | Distinctive | "you" +1.75 (direct engagement) |
134
- | -1.0 to +1.0 | Normal range | Typical usage |
135
- | -2.0 to -1.0 | Avoided | "the" -1.48 (prefer specific) |
136
- | -2.0- | Highly avoided | "was" -2.46 (avoid passive) |
137
-
138
- These patterns are invisible whilst writing but obvious when absent. That's why AI content feels "off" even when grammatically correct.
139
-
140
- ### Sentence Patterns
148
+ **Email/communication:**
149
+ ```
150
+ Write an email about [subject] using the voice patterns from the guide.
141
151
 
142
- - Length distribution with variance (not just average)
143
- - Sentence openers frequency ("I", "The", "But", etc.)
144
- - Syntactic structures and modifications
152
+ Focus on:
153
+ - Conversational markers appearing naturally
154
+ - Sentence length variation (some punchy, some complex)
155
+ - The hedging/confidence balance shown in statistics
156
+ - First-person usage matching the corpus frequency
157
+ ```
145
158
 
146
- ### Voice Markers
159
+ ### Validation After Writing
147
160
 
148
- - First-person density (0.6 per 100 words typical for authority voice)
149
- - Hedging language frequency ("I think", "seems to")
150
- - Equipment specificity ("my Simucube 2 Pro" vs "a wheelbase")
161
+ The guide includes statistical targets. After writing, check:
151
162
 
152
- ### N-Gram Analysis
163
+ ```
164
+ Review what you just wrote against the voice guide metrics:
165
+ - Does sentence length variation match the target standard deviation?
166
+ - Is first-person frequency within the expected range?
167
+ - Are conversational markers present but not overused?
168
+ - Does the rhythm feel like the extended examples?
169
+ ```
153
170
 
154
- **Word patterns:**
155
- - "but I" (contrast marker)
156
- - "in my" (authority phrase)
157
- - Transitional phrases
171
+ ## What Gets Analysed
158
172
 
159
- **POS patterns:**
160
- - DET NOUN (the metrics)
161
- - ADJ NOUN (international markets)
162
- - Syntactic DNA
173
+ ### Core Voice Patterns
174
+ - **Vocabulary** - Word choice, British/American markers, domain specificity
175
+ - **Sentence structure** - Length distribution, openers, complexity patterns
176
+ - **Voice markers** - First-person usage, hedging language, conversational markers
177
+ - **Punctuation** - Dash types, comma density, parenthetical frequency
163
178
 
164
- ### Anti-Patterns
179
+ ### Argument & Flow Patterns
180
+ - **Argument flow** - How you open, build, and close arguments
181
+ - **Paragraph transitions** - How ideas connect across paragraphs
182
+ - **Conversational devices** - "look", "frankly", "actually" and when they appear
165
183
 
166
- Detects AI clichés in YOUR corpus:
167
- - "delve", "leverage", "unlock"
168
- - Marketing speak patterns
169
- - Generic references
184
+ ### Micro-Rhythm Detection
185
+ The guide annotates examples with invisible patterns that make writing feel human:
186
+ - Mid-thought pivots (comma before "and", "but", "so")
187
+ - Present-tense immediacy ("Right now, it's...")
188
+ - Embedded uncertainty ("I think", "probably")
189
+ - Casual sentence starters ("So,", "And,", "But,")
190
+ - Parenthetical asides
191
+ - Punchy fragments contrasting with longer sentences
170
192
 
171
193
  ## Output Structure
172
194
 
173
195
  ```
174
- corpus/
175
- └── your-name/
176
- ├── articles/ # Collected markdown
177
- ├── corpus.json # Metadata
178
- └── analysis/ # JSON analysis files
179
-
180
- templates/
181
- └── writing_style_your-name.md # LLM-optimized guide
196
+ your-output-directory/
197
+ └── corpus-name/
198
+ ├── articles/ # Collected markdown files
199
+ ├── corpus.json # Metadata
200
+ ├── analysis/ # JSON analysis files
201
+ │ ├── vocabulary.json
202
+ │ ├── sentence.json
203
+ │ ├── voice.json
204
+ │ ├── paragraph.json
205
+ │ ├── punctuation.json
206
+ │ ├── function-words.json
207
+ │ ├── argument-flow.json
208
+ │ └── paragraph-transitions.json
209
+ └── writing_style_[name]_narrative.md # The voice guide
182
210
  ```
183
211
 
212
+ ## Minimum Corpus Size
213
+
214
+ - **Minimum:** 15,000 words (~20 articles)
215
+ - **Recommended:** 30,000 words
216
+ - **Ideal:** 50,000+ words
217
+
218
+ Below 15k words, statistical patterns become unreliable.
219
+
184
220
  ## Tools Reference
185
221
 
186
222
  ### collect_corpus
187
223
 
188
224
  | Parameter | Required | Description |
189
225
  |-----------|----------|-------------|
190
- | `sitemap_url` | Yes | XML sitemap, RSS feed, or URL |
191
- | `output_name` | Yes | Corpus identifier |
226
+ | `sitemap_url` | Yes | XML sitemap URL |
227
+ | `output_name` | Yes | Corpus identifier (e.g., "my-voice") |
228
+ | `output_dir` | Yes | Directory to store corpus |
192
229
  | `max_articles` | No | Limit (default: 100) |
193
230
  | `article_pattern` | No | Regex filter for URLs |
194
231
 
@@ -197,53 +234,32 @@ templates/
197
234
  | Parameter | Required | Description |
198
235
  |-----------|----------|-------------|
199
236
  | `corpus_name` | Yes | Name from collect_corpus |
237
+ | `corpus_dir` | Yes | Directory containing corpus |
200
238
  | `analysis_type` | No | full, quick, vocabulary, syntax |
201
239
 
202
- ### generate_enhanced_guide
240
+ ### generate_narrative_guide
203
241
 
204
242
  | Parameter | Required | Description |
205
243
  |-----------|----------|-------------|
206
244
  | `corpus_name` | Yes | Name from analyze_corpus |
207
- | `output_format` | No | llm, human, both |
208
-
209
- ### generate_tov_guide
210
-
211
- Legacy basic guide generation. Use `generate_enhanced_guide` for production.
212
-
213
- ## Minimum Corpus Size
214
-
215
- - **Minimum:** 15,000 words (20 articles)
216
- - **Recommended:** 30,000 words
217
- - **Ideal:** 50,000+ words
218
-
219
- Below 15k words, you're measuring noise, not signal.
220
-
221
- ## Troubleshooting
222
-
223
- **"No corpus found"**
224
- Run collect_corpus first. Check name matches exactly (case-sensitive).
225
-
226
- **"Not enough data"**
227
- Collect more articles. Minimum 20 articles, 15,000 words.
228
-
229
- **"Z-scores all near zero"**
230
- Indicates typical English usage. May mean mixed authorship or AI-edited content.
245
+ | `corpus_dir` | Yes | Directory containing corpus |
231
246
 
232
247
  ## Development
233
248
 
234
249
  ```bash
235
- git clone https://github.com/houtini-ai/voice-analyser-mcp.git
236
- cd voice-analyser-mcp
250
+ git clone https://github.com/houtini-ai/mcp-server-voice-analysis.git
251
+ cd mcp-server-voice-analysis
237
252
  npm install
238
253
  npm run build
239
254
  ```
240
255
 
241
- ## Research Foundation
242
-
243
- The function word stylometry approach draws from computational authorship analysis research. Z-score comparisons against reference English corpora create statistical fingerprints that are difficult to replicate by chance.
256
+ ## Limitations
244
257
 
245
- Key insight: function words (the, of, and, to) are used unconsciously and form stable individual patterns. Content words vary by topic; function words reveal the author.
258
+ - Requires XML sitemap (RSS feeds not currently supported)
259
+ - Works best with consistent single-author content
260
+ - Mixed authorship or heavily edited content produces weaker signals
261
+ - The approach is experimental - results vary by writing style
246
262
 
247
263
  ---
248
264
 
249
- MIT License - [Houtini.ai](https://houtini.ai)
265
+ Apache License 2.0 - [Houtini.ai](https://houtini.ai)
@@ -0,0 +1,50 @@
1
+ /**
2
+ * Argument Flow Analyzer v2.0
3
+ * Detects how this writer builds arguments with confidence scoring
4
+ */
5
+ export interface ArgumentPattern {
6
+ pattern: string;
7
+ description: string;
8
+ frequency: number;
9
+ confidence: 'high' | 'medium' | 'low';
10
+ confidenceScore: number;
11
+ examples: ArgumentExample[];
12
+ }
13
+ export interface ArgumentExample {
14
+ fullText: string;
15
+ components: {
16
+ opening?: string;
17
+ claim?: string;
18
+ evidence?: string;
19
+ counterpoint?: string;
20
+ dismissal?: string;
21
+ conclusion?: string;
22
+ linkingPhrase?: string;
23
+ };
24
+ }
25
+ export interface ConversationalDevice {
26
+ type: 'thought_restart' | 'tangent_marker' | 'reader_alignment' | 'admission' | 'emphasis';
27
+ trigger: string;
28
+ context: string;
29
+ purpose: string;
30
+ frequency: number;
31
+ examples: string[];
32
+ }
33
+ export interface ArgumentFlowAnalysis {
34
+ patterns: ArgumentPattern[];
35
+ conversationalDevices: ConversationalDevice[];
36
+ openingMoves: {
37
+ type: string;
38
+ description: string;
39
+ frequency: number;
40
+ examples: string[];
41
+ }[];
42
+ closingMoves: {
43
+ type: string;
44
+ description: string;
45
+ frequency: number;
46
+ examples: string[];
47
+ }[];
48
+ }
49
+ export declare function analyzeArgumentFlow(text: string): ArgumentFlowAnalysis;
50
+ //# sourceMappingURL=argument-flow.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"argument-flow.d.ts","sourceRoot":"","sources":["../../src/analyzers/argument-flow.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAIH,MAAM,WAAW,eAAe;IAC9B,OAAO,EAAE,MAAM,CAAC;IAChB,WAAW,EAAE,MAAM,CAAC;IACpB,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,EAAE,MAAM,GAAG,QAAQ,GAAG,KAAK,CAAC;IACtC,eAAe,EAAE,MAAM,CAAC;IACxB,QAAQ,EAAE,eAAe,EAAE,CAAC;CAC7B;AAED,MAAM,WAAW,eAAe;IAC9B,QAAQ,EAAE,MAAM,CAAC;IACjB,UAAU,EAAE;QACV,OAAO,CAAC,EAAE,MAAM,CAAC;QACjB,KAAK,CAAC,EAAE,MAAM,CAAC;QACf,QAAQ,CAAC,EAAE,MAAM,CAAC;QAClB,YAAY,CAAC,EAAE,MAAM,CAAC;QACtB,SAAS,CAAC,EAAE,MAAM,CAAC;QACnB,UAAU,CAAC,EAAE,MAAM,CAAC;QACpB,aAAa,CAAC,EAAE,MAAM,CAAC;KACxB,CAAC;CACH;AAED,MAAM,WAAW,oBAAoB;IACnC,IAAI,EAAE,iBAAiB,GAAG,gBAAgB,GAAG,kBAAkB,GAAG,WAAW,GAAG,UAAU,CAAC;IAC3F,OAAO,EAAE,MAAM,CAAC;IAChB,OAAO,EAAE,MAAM,CAAC;IAChB,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,EAAE,MAAM,CAAC;IAClB,QAAQ,EAAE,MAAM,EAAE,CAAC;CACpB;AAED,MAAM,WAAW,oBAAoB;IACnC,QAAQ,EAAE,eAAe,EAAE,CAAC;IAC5B,qBAAqB,EAAE,oBAAoB,EAAE,CAAC;IAC9C,YAAY,EAAE;QACZ,IAAI,EAAE,MAAM,CAAC;QACb,WAAW,EAAE,MAAM,CAAC;QACpB,SAAS,EAAE,MAAM,CAAC;QAClB,QAAQ,EAAE,MAAM,EAAE,CAAC;KACpB,EAAE,CAAC;IACJ,YAAY,EAAE;QACZ,IAAI,EAAE,MAAM,CAAC;QACb,WAAW,EAAE,MAAM,CAAC;QACpB,SAAS,EAAE,MAAM,CAAC;QAClB,QAAQ,EAAE,MAAM,EAAE,CAAC;KACpB,EAAE,CAAC;CACL;AAED,wBAAgB,mBAAmB,CAAC,IAAI,EAAE,MAAM,GAAG,oBAAoB,CActE"}