Agent skill

Deep Voice Analysis

by Ckokoski in Ckokoski/AuthorAgent

Advanced 47-marker voice analysis engine — analyzes your writing to build a comprehensive Voice Profile for AuthorClaw

MITAuto-check passedWriting & Content

Install Deep Voice Analysis

skills CLI
$ npx skills add Ckokoski/AuthorAgent --skill deep-voice-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Ckokoski/AuthorAgent deep-voice-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Ckokoski/AuthorAgent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/_archived/premium/writing-secrets-integration/deep-voice-analysis .claude/skills/deep-voice-analysis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deep-voice-analysis
GitHub stars
123
Token cost
~1.4k tokens
SKILL.md length
498 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Advanced 47-marker voice analysis engine — analyzes your writing to build a comprehensive Voice Profile for AuthorClaw

  • Works in 12 steps: Average sentence length (words) → Sentence length variance (burstiness) → Short sentence frequency (1-5 words) → …
  • Tasks that involve Brand voice and tone
  • SKILL.md covers What Makes This Different From…, The 47 Markers, Analysis Process and Output: Enhanced Voice Profile, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Deep Voice Analysis is an agent skill from Ckokoski/AuthorAgent. Advanced 47-marker voice analysis engine — analyzes your writing to build a comprehensive Voice Profile for AuthorClaw

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Brand voice and tone. The repository describes itself as: The Autonomous AI Writing Agent — a secure, author-focused AI for fiction and nonfiction authors (Planning, Revision, Promotion, and more). The licence is MIT.

When your agent uses it

  • Tasks that involve Brand voice and tone

Example prompts

  • “/deep-voice-analysis”

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. Average sentence length (words)
  2. Sentence length variance (burstiness)
  3. Short sentence frequency (1-5 words)
  4. Medium sentence frequency (6-15 words)
  5. Long sentence frequency (16-25 words)
  6. Very long sentence frequency (26+)
  7. Paragraph average length (sentences)
  8. Paragraph length variance
  9. Scene-opening sentence length pattern
  10. Chapter-opening sentence length pattern
  11. Dialogue line average length
  12. Action beat average length

What it can do on your machine

Read from SKILL.md and the folder at commit 47e9570. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deep Voice Analysis loads about 1.4k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 498 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ckokoski/AuthorAgent at commit 47e9570, republished under its MIT licence (© Ckokoski). 498 words, ~1,391 tokens.

Download SKILL.mdSave it as .claude/skills/deep-voice-analysis/SKILL.md (or your agent's skills folder).
name
deep-voice-analysis
description
Advanced 47-marker voice analysis engine — analyzes your writing to build a comprehensive Voice Profile for AuthorClaw
author
Writing Secrets
version
1.0.0
triggers
analyze my voice, learn my style, deep voice analysis, voice analysis, writing dna, clone my style, study my writing
permissions
file:read, file:write

Deep Voice Analysis — Premium Skill

Advanced writing voice analysis that goes far beyond the free style-clone skill. Analyzes your writing across 47 markers to create a forensic-level Voice Profile.

What Makes This Different From the Free Style-Clone Skill

The free style-clone skill does a basic voice analysis (~10 markers). This premium skill runs a 47-marker deep analysis that captures the invisible patterns that make YOUR writing yours — the kind of patterns that fool AI detectors because they encode genuine human writing habits.

The 47 Markers

Rhythm Markers (12)
  1. Average sentence length (words)
  2. Sentence length variance (burstiness)
  3. Short sentence frequency (1-5 words)
  4. Medium sentence frequency (6-15 words)
  5. Long sentence frequency (16-25 words)
  6. Very long sentence frequency (26+)
  7. Paragraph average length (sentences)
  8. Paragraph length variance
  9. Scene-opening sentence length pattern
  10. Chapter-opening sentence length pattern
  11. Dialogue line average length
  12. Action beat average length
Vocabulary Markers (10)
  1. Vocabulary richness (unique/total word ratio)
  2. Perplexity score (word unpredictability)
  3. Top 20 signature words (words you overuse — in a good way)
  4. Top 10 avoided words (words you never use)
  5. Formality level (casual ↔ academic)
  6. Jargon/domain-specific vocabulary
  7. Curse word frequency and type
  8. Sensory word distribution (sight/sound/touch/smell/taste)
  9. Emotional vocabulary range
  10. Abstract vs. concrete word ratio
Structural Markers (8)
  1. Narrative distance (close/medium/distant POV)
  2. Scene-to-sequel ratio
  3. Dialogue-to-narrative ratio
  4. Description density per scene
  5. Flashback/memory frequency
  6. Transition style (hard cuts vs. smooth)
  7. Chapter hook style (question, action, dialogue, mystery)
  8. White space usage (single-line paragraphs as emphasis)
Dialogue Markers (7)
  1. Tag preference (said/asked vs. creative tags)
  2. Action beat vs. tag ratio
  3. Average dialogue line length
  4. Subtext level (direct ↔ heavily implied)
  5. Interruption frequency
  6. Character voice differentiation score
  7. Monologue vs. rapid exchange ratio
Show full SKILL.md (197 more words)Show less
Punctuation & Mechanics (5)
  1. Em dash frequency
  2. Semicolon frequency
  3. Ellipsis frequency
  4. Exclamation mark frequency
  5. Parenthetical frequency
Voice & Tone (5)
  1. Humor type (dry, sarcastic, physical, dark, witty, none)
  2. Humor frequency
  3. Emotional register style (body-first, thought-first, action-first)
  4. Metaphor/simile density
  5. Overall humanness score (AI-detection bypass potential)

Analysis Process

  1. Intake: Author provides 5,000+ words (ideal: 20,000+). Multiple samples across scenes/chapters is best.
  2. Tokenize: Break text into sentences, paragraphs, scenes, dialogue blocks.
  3. Measure: Calculate all 47 markers with statistical confidence.
  4. Compare: Benchmark against genre averages to identify what's distinctive.
  5. Generate: Create the Voice Profile markdown file.
  6. Validate: Show the author their profile and ask "does this sound like you?"

Output: Enhanced Voice Profile

Saved to workspace/soul/VOICE-PROFILE.md with all 47 markers organized into sections that AuthorClaw's Soul system reads on every interaction.

markdown
# Voice Profile — Deep Analysis (47 Markers)
## Generated: [date] | Sample size: [N] words

## Humanness Score: [0-100]

## Rhythm
- Avg sentence: [N] words | Variance: [N] (burstiness)
- Distribution: [%] short / [%] medium / [%] long / [%] very long
- Paragraphs: [N] sentences avg
- Openers: [pattern description]

## Vocabulary
- Richness: [score] | Perplexity: [score] | Formality: [level]
- SIGNATURE WORDS (use naturally): [list]
- NEVER USE: [anti-AI words list]
- Sensory bias: [primary sense]

## Structure
- Narrative distance: [level]
- Dialogue ratio: [%] of text
- Description density: [level]
- Chapter hooks: [dominant style]

## Dialogue
- Tags: [preference] | Beats: [frequency]
- Avg line: [N] words | Subtext: [level]
- Voice differentiation: [score]

## Mechanics
- Em dashes: [freq] | Semicolons: [freq]
- Ellipsis: [freq] | Exclamation: [freq]

## Voice
- Humor: [type] at [frequency]
- Emotional style: [body/thought/action]-first
- Metaphor density: [level]

## RULES FOR AI
When writing as this author:
1. Follow the sentence distribution above (this is critical for humanness)
2. Use signature words naturally — don't force them but let them appear
3. NEVER use the avoided words list
4. Match the punctuation profile
5. Keep the narrative distance at [level]
6. Apply the [type] humor at appropriate moments
7. Lead with [body/thought/action] for emotional moments
8. Maintain [level] metaphor density — no more, no less

Commands

  • deep voice analysis or analyze my voice deeply — Start the full 47-marker analysis
  • show voice profile — Display the current enhanced profile
  • voice check [text] — Score new text against all 47 markers
  • voice report — Generate a detailed report comparing recent writing to the profile
  • update voice profile from [text] — Refine the profile with new sample data

© Ckokoski, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/_archived/premium/writing-secrets-integration/deep-voice-analysis of Ckokoski/AuthorAgent.

Open the folder on GitHubat commit 47e9570

Compare with similar skills

Deep Voice Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deep Voice Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deep Voice Analysis this skillCkokoski/AuthorAgent123—~1.4kAutomated safety check: PassMIT
Avoid AI Writingconorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMIT
BrandOhh-889/skyroc79513 repos~733Automated safety check: PassMIT
Khazix WeChat Article WriterKKKKhazix/khazix-skills21k1 repos~2.9kAutomated safety check: PassMIT
Writing Guidelinesvercel-labs/agent-skills32k7 repos~309Automated safety check: PassNone
Unslop AI Writing Cleanuptheclaymethod/unslop516—~1.7kAutomated safety check: PassMIT

Similar skills

  • Avoid AI Writing

    conorbronsdon/avoid-ai-writing

    Audit and rewrite content to remove AI writing patterns ("AI-isms").

    4.9k GitHub starsUsed in 3 repos~8.1k tokens
    Writing & ContentAuto-check passed
  • Brand

    Ohh-889/skyroc

    Brand voice, visual identity, messaging frameworks, asset management, brand consistency.

    795 GitHub starsUsed in 13 repos~733 tokens
    Writing & ContentAuto-check passed
  • Khazix WeChat Article Writer

    KKKKhazix/khazix-skills

    Writes long-form WeChat official account articles in the personal style of the Khazix account, from briefs, links, PDFs or rough notes, with a topic quality check.

    21k GitHub starsUsed in 1 repo~2.9k tokens
    Writing & ContentAuto-check passed
  • Writing Guidelines

    vercel-labs/agent-skills

    Official

    Review docs/prose for Writing Guidelines compliance. An agent skill from vercel-labs/agent-skills.

    32k GitHub starsUsed in 7 repos~309 tokens
    Writing & ContentAuto-check passed
  • Unslop AI Writing Cleanup

    theclaymethod/unslop

    Removes AI writing tells from prose through an audit-first flow, routing to a two-pass rewrite, a report-only cleanup, voice teaching or mimicry depending on the sub-command used.

    516 GitHub stars~1.7k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • UX Writing

    content-designer/ux-writing-skill

    Applies UX writing practice to interface copy such as buttons, errors, forms and onboarding, using four quality standards and accessibility guidance.

    224 GitHub starsUsed in 1 repo~3.8k tokens
    Writing & ContentAuto-check passed

More from Ckokoski/AuthorAgent

All 23 skills in this repo
  • After Action Review

    Ckokoski/AuthorAgent

    Structured post-goal reflection that extracts lessons, evaluates quality, and feeds the self-improvement loop

    123 GitHub stars~1.6k tokensUpdated 3 mo ago
    Auto-check passed
  • Comp Title Finder

    Ckokoski/AuthorAgent

    Find and analyze comparable titles for query letters, marketing, and positioning strategy

    123 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Continuity Check

    Ckokoski/AuthorAgent

    Scan manuscript for inconsistencies in characters, timeline, settings, and names

    123 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Dictation Cleanup

    Ckokoski/AuthorAgent

    Transform raw speech-to-text dictation into polished prose while preserving the author's natural voice

    123 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed
  • Error Recovery

    Ckokoski/AuthorAgent

    Intelligent error diagnosis, automatic recovery strategies, and prevention of recurring failures

    123 GitHub stars~1.7k tokensUpdated 3 mo ago
    Auto-check passed
  • First Chapter Hook

    Ckokoski/AuthorAgent

    Analyze and rewrite first chapters for maximum reader retention using genre-specific hook patterns

    123 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

Questions about Deep Voice Analysis

What does Deep Voice Analysis do?

Advanced 47-marker voice analysis engine — analyzes your writing to build a comprehensive Voice Profile for AuthorClaw. Deep Voice Analysis is an agent skill from Ckokoski/AuthorAgent.

When should I use Deep Voice Analysis?

Deep Voice Analysis fits situations like: tasks that involve Brand voice and tone.

How do I install Deep Voice Analysis in Claude Code?

Run `npx skills add Ckokoski/AuthorAgent --skill deep-voice-analysis -a claude-code`. Or copy the skill folder (skills/_archived/premium/writing-secrets-integration/deep-voice-analysis in Ckokoski/AuthorAgent) into .claude/skills/deep-voice-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Deep Voice Analysis in Codex?

Run `npx skills add Ckokoski/AuthorAgent --skill deep-voice-analysis -a codex`. Or copy the skill folder (skills/_archived/premium/writing-secrets-integration/deep-voice-analysis in Ckokoski/AuthorAgent) into .agents/skills/deep-voice-analysis in your project. Codex loads it when a task matches its description.

Can I use Deep Voice Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ckokoski/AuthorAgent --skill deep-voice-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-voice-analysis, .gemini/skills/deep-voice-analysis, .github/skills/deep-voice-analysis and .opencode/skills/deep-voice-analysis in your project.

What does Deep Voice Analysis need to run?

SKILL.md names no scripts, command-line tools or credentials: Deep Voice Analysis is instructions for the agent only.

Does Deep Voice Analysis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deep Voice Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deep Voice Analysis use?

Deep Voice Analysis is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deep Voice Analysis use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deep Voice Analysis?

Skills that share tags, products or a category with Deep Voice Analysis: Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars), Brand (Ohh-889/skyroc, 795 stars), Khazix WeChat Article Writer (KKKKhazix/khazix-skills, 21k stars) and Writing Guidelines (vercel-labs/agent-skills, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deep Voice Analysis?

Ckokoski (a GitHub user) maintains it in Ckokoski/AuthorAgent, which has 123 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on July 11, 2026.

Source: Ckokoski/AuthorAgent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.