storyledger prose

    1

    A line edit of your whole manuscript in numbers. Filter words, adverbs, passive voice, rhythm, repetition, tense and POV slips, quote and spelling consistency, graded against your own style guide and cited by line.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    storyledger prose

    Example session with this skill installed

    Run a prose audit on the chapters in the /manuscript folder. I'm going for a noir voice with short, punchy sentences. Check for filter words and tense slips.

    • Read your context and instructions
    • Compiled the storyledger prose

    I have scanned the 12 chapters found in /manuscript against your noir style preferences. The scripts identified a high density of filter words in the middle chapters, though your sentence length remains appropriately low for the genre.

    Prose Analysis Report

    CategoryMeasureStatusLead Chapter
    Filter Words18.2 / 1k wordsWarningChapter 04
    Sentence Length9.4 words avgOn TargetChapter 02
    Tense Slips14 instancesSuggestionChapter 07
    Passive Voice4.1%NoteChapter 01

    Key Findings

    L-001 (Chapter 04:112): "He could see the rain hitting the glass." (Filter word: could see).

    Suggestion: "Rain lashed the glass."

    L-002 (Chapter 07:45): "He walks to the door and turned the handle." (Tense shift: walks to turned).

    Warning: Mixed past/present narration.

    L-003 (Chapter 02:201): "Dead. Again. Like the last time." (Fragments).

    Treated as Voice: Matches noir target.

    Where to start
    Chapter 04 and Chapter 07 contain the highest density of actionable issues. Specifically, the tense slips in Chapter 07 should be addressed first to maintain narrative consistency.

    Next steps

    1. Review the full report at prose/report.md.
    2. Ask me to "fix L-002" to see a proposed rewrite for the tense shift.
    3. Would you like to add the filter word 'noticed' to your style/allow.txt if it is part of your narrator's specific tic?

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Polishing a novel manuscript often involves subjective guesswork or expensive editing fees. StoryLedger Prose replaces vague intuition with a data-driven line edit, measuring your prose against specific stylistic benchmarks to identify habits that weaken your narrative.

    What it does

    • Quantifiable Analysis calculates densities of filter words, adverbs, and passive voice per 1,000 words.
    • Rhythm Mapping identifies sentence length monotony, long runs, and repetitive structures that disrupt flow.
    • Consistency Audits detects slips in tense, POV, quote marks, and spelling styles across the entire manuscript.
    • Context-Aware Grading distinguishes between intentional character voice in dialogue and accidental habits in narration.
    • Citations maps every identified issue to a specific file and line number for immediate verification.

    How it works

    1. Manuscript Ingestion scans your project directory to identify chapters while skipping notes or beat sheets.
    2. Style Alignment loads your custom targets from YAML/Markdown files or asks clarifying questions to define your voice.
    3. Automated Scanning runs Node.js scripts to extract linguistic leads and rhythm patterns from your text.
    4. Report Generation produces prose/report.md featuring a "Where to start" roadmap and categorized issues with unique IDs.

    Frameworks & tools

    This skill uses Node.js 18+ for high-speed text analysis via scan-words.js, scan-rhythm.js, and scan-copyedit.js. It parses Markdown, text, and YAML frontmatter.

    Why this beats prompting it yourself

    Generic prompts often hallucinate "errors" or apply a bland house style that erases your unique voice. This skill uses deterministic scripts to ensure every count is accurate and every suggestion respects your pre-defined compositional guides.

    Use cases

    • Auditing a finished draft for "purple prose" and filter words before submission.
    • Standardizing British vs. American spelling and punctuation across multiple files.
    • Finding accidental tense shifts in long-form narration without manual re-reading.
    • Validating chapter rhythm to ensure high-action scenes use appropriate sentence lengths.

    Known limitations

    Word lists for hedges and adverbs are English-only. The system requires specific frontmatter or headings to reliably split one-file manuscripts into chapters.

    English language only. Requires Node.js 18+ for automated scanning. Only detects standard dialogue punctuation styles. Manual review needed for hard-wrapped text or hand-written style guides.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Write Files

    File Scopes

    chapters/**
    manuscript/**
    draft/**
    *.md
    *.txt
    style/**
    STRUCTURAL_STYLE_GUIDE.md
    style-targets.yml
    COMPOSITIONAL_STYLE_GUIDE.md
    prose/**
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    StoryLedger Prose uses deterministic Node.js scripts to provide precise, verifiable counts for things like filter words and sentence variety, whereas generic AI prompts often guess at densities or 'hallucinate' stylistic errors that aren't there.

    The skill is optimized for Node.js 18+ environments and works best with agents that have file-system access to read your manuscript folders and generate the Markdown reports.

    Yes, the 'Style Alignment' feature allows you to define your own stylistic benchmarks via YAML or Markdown files, ensuring the audit respects your unique voice rather than enforcing a generic style.

    The skill includes the core analytical scripts (scan-words, scan-rhythm, and scan-copyedit), documentation for setting up your project directory, and a guide for configuring your custom style targets.

    StoryLedger Prose currently supports English-language manuscripts and requires files to be in Markdown, plain text, or formatted with YAML frontmatter for proper chapter splitting.

    The 'Citations' feature assigns a unique ID to every identified issue and maps it to a specific file and line number, allowing you to instantly verify every suggestion before making a change.

    New in Writing & Content