SS

    storyledger structure

    1

    Your book's shape on one page. Chapter lengths, POV balance, tension, where each theme and thread lives and goes quiet, how chapters open and close, and what the draft does differently from your outline.

    $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
    SS

    storyledger structure

    Example session with this skill installed

    Perform a full structural edit on the manuscript in the /drafts folder. Check against the outline in outline.md and track the "Inheritance" plot thread.

    • Read your context and instructions
    • Compiled the storyledger structure

    I have completed a full structural edit of the manuscript in /drafts. I ran scan-structure.js across 24 chapters and scan-presence.js to track the "Inheritance" thread using the keywords: will, lawyer, estate, uncle.

    StoryLedger Structure Report

    Mode: Full Structural Edit
    Word Count: 82,400
    POV Share: Elias (62%), Sarah (38%)

    ChapterWord CountPOVTensionHookClosing
    13,200Elias4ActionQuestion
    24,100Sarah3AtmosphereSleep
    32,800Elias6DialogueRevelation
    43,500Elias5CharacterTrailing

    Key Findings

    S-001: Sagging Middle. Tension ratings for Chapters 10 through 14 show a flatline at 2/10. These chapters focus heavily on travel with no progress on the "Inheritance" thread.

    S-002: POV Gap. Sarah is absent from Chapter 8 through Chapter 15 (approx. 22,000 words). Consider inserting a Sarah POV scene in the Chapter 12 slot to maintain her arc.

    S-003: Thread Resolution. The "Inheritance" thread (tracked keywords: will, estate) goes quiet after Chapter 18 and has no presence in the finale.

    S-004: Cliche Hook. Chapter 2 opens with a weather description (cliche_weather). Recommend starting with Sarah's reaction to the letter instead.

    Next steps

    1. Review the proposed purpose and tension tags for Chapters 10-14 and approve writing them to frontmatter.
    2. Review the Inheritance keyword list; I suggest adding "attorney" and "safe-box" for better tracking.
    3. Open structure/report.md to see the full sparklines and plan-vs-draft comparison.

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

    About this skill

    Novelists and editors often struggle to see the "forest for the trees" when finishing a long manuscript. You can easily miss a sagging middle, a dropped plot thread, or a POV character that disappears for eighty pages. StoryLedger Structure provides a developmental edit that maps your book's shape on a single page, identifying structural flaws before you start your next draft.

    What it does

    • Pacing Analysis generates sparklines for chapter lengths and tension levels to visualize the book's flow.
    • POV Monitoring calculates POV share and detects gaps where specific characters go quiet for too long.
    • Thread Tracking maps themes and plot threads across chapters to identify unresolved arcs or missing motifs.
    • Hook Auditing flags repetitive chapter openings or weak closings, including cliches like waking up or weather descriptions.
    • Outline Comparison identifies discrepancies between the draft and the original plan, flagging moved or missing scenes.

    How it works

    1. Manuscript Scan identifies chapter files or splits a single-file manuscript based on headings.
    2. Structural Measurement runs scripts to quantify word counts, dialogue percentages, and narrative perspective.
    3. Presence Mapping tracks specific keywords and character aliases to visualize where plot threads live and die.
    4. Report Generation produces a comprehensive structure/report.md with stable issue IDs, sparklines, and cited developmental entries.

    Frameworks & tools

    This skill uses Node 18+ to run scanning scripts (scan-structure.js and scan-presence.js) and outputs standard Markdown reports compatible with GitHub-flavored Markdown.

    Why this beats prompting it yourself

    Generic prompts often lose track of long-range dependencies in 80k-word manuscripts. This tool uses specialized scripts to extract hard data on length, presence, and dialogue, ensuring your developmental feedback is grounded in math rather than just a shallow read of the final chapters.

    Use cases

    • Auditing a first draft to find where the narrative tension flats out.
    • Ensuring a secondary plot thread is consistently developed throughout the middle chapters.
    • Balancing screen time between multiple protagonists in a complex ensemble cast.
    • Identifying "throat-clearing" chapters that fail to advance the story or establish a hook.

    Known limitations

    Dialogue detection may struggle with straight single quotes lacking punctuation. Designed for English-language manuscripts. Scene detection requires specific markers or visible breaks like *** to be accurate.

    English only. Dialogue detection may misread straight single quotes without punctuation. Split-file manuscripts preferred over one-file books for chapter-level accuracy.

    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
    plots/**
    themes/**
    characters/**
    structure/**
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    The skill requires a Node 18+ environment to run its specialized scanning scripts. It is designed to work within AI agents that have filesystem access, allowing it to process your manuscript files locally and generate Markdown reports.

    Unlike a simple prompt that might forget the beginning of a book by the time it reaches the end, this skill uses dedicated scripts to extract hard data across the entire manuscript. This ensures pacing and POV balance metrics are based on the full 80k+ word count rather than an LLM's limited context window.

    StoryLedger is most effective when chapters are clearly defined by headings or when scenes are separated by standard markers like '***'. While it can split single-file manuscripts, using consistent formatting ensures the most accurate thread tracking and pacing sparklines.

    You will receive the core scanning scripts (scan-structure.js and scan-presence.js), the integration logic for your AI agent, and a template for the comprehensive structure/report.md output.

    The skill currently identifies dialogue based on standard punctuation; if your manuscript uses non-standard markers or lacks punctuation in dialogue, detection accuracy may decrease. Additionally, the tool is optimized specifically for English-language narrative structures.