- Home
- Skills
- Writing & Content
- storyledger continuity
storyledger continuity
Give it a manuscript or a few chapters and get contradictions.md, with every contradiction quoted from both sides by file and line. No setup or story bible needed.
$10
Works with the AI Agents you already use
storyledger continuity
Example session with this skill installed
Run a full continuity check on the chapters in /manuscript. I'm worried about character ages and the timeline of the heist in Chapter 4.
- Read your context and instructions
- Compiled the storyledger continuity
I have completed a full continuity check of the 12 chapters found in /manuscript. I ran the timeline and people scanners to build a fact ledger, specifically focusing on the chronological markers during the heist sequence.
Continuity Report: /manuscript/continuity/contradictions.md
| ID | Status | Category | Description | Source Citations |
|---|---|---|---|---|
| C-001 | open | Contradiction | Character age mismatch for Elias. | ch1.md:L42 ("Elias, barely twenty"), ch8.md:L115 ("his thirty years of experience") |
| C-002 | open | Contradiction | The heist timeline regresses. | ch4.md:L202 ("It was 2:00 AM"), ch4.md:L310 ("The clock struck midnight as they entered the vault") |
| P-003 | open | Possible | Physical attribute drift for Sarah. | ch2.md:L15 ("bright blue eyes"), ch9.md:L88 ("her dark brown gaze") |
| D-004 | open | Plan vs Draft | Event order differs from outline.md. | outline.md:L12 (Vault breach), ch4.md:L150 (Vault breach happens before alarm bypass) |
Fact Ledger Summary
- Timeline: The heist covers a 4-hour window, but internal timestamps conflict in Chapter 4.
- People: 4 major characters tracked. Elias has an impossible age jump.
- Objects: The "Silver Key" is correctly tracked from Chapter 2 to Chapter 5.
Next steps
- Review
contradictions.mdto decide which Elias age is canonical. - Fix the timestamp sequence in the Chapter 4 vault scene.
- Update
outline.mdif the new heist order was an intentional creative choice.
Connects securely to your tools. The creator never sees your data.
About this skill
Fiction writing is a mess of shifting details. You start with a character having blue eyes in Chapter 1 and they are suddenly green by Chapter 20. Dates slip, ages don't add up, and "first time" events happen twice. StoryLedger Continuity automates the tedious process of hunting these discrepancies across thousands of words, providing a structured audit of every factual slip-in your draft.
What it does
- Conflict detection finds physical contradictions like eye colors, heights, or scars that change without explanation.
- Timeline auditing flags date regressions, impossible travel times, and arithmetic errors in character ages.
- Knowledge tracking monitors who knows what and when, catching instances where characters act on information they haven't learned yet.
- Fact ledgering builds a temporary database of people, objects, and world rules to ensure consistency across chapters.
- Plan vs. Draft comparison checks your prose against outlines or story bibles to highlight where you deviated from your intended plot.
How it works
- Manuscript Scan: The agent identifies your chapter files and establishes the scope of the check.
- Lead Collection: Node.js scripts scan the text for name variants, age markers, and absolute claims like "never" or "first."
- Ledger Building: The agent reads chapters in order to track character locations, inventory, and established world laws.
- Verification: Every potential contradiction is cross-referenced with the text to ensure it isn't just a character lying or a planned change.
- Report Generation: A
contradictions.mdfile is produced with direct quotes, line numbers, and severity ratings.
Frameworks & tools
This skill utilizes Node.js (v18+) for high-speed pattern matching and text analysis. It operates on standard .md and .txt manuscript files and integrates with StoryLedger workspace formats.
Why this beats prompting it yourself
Generic prompts often hallucinate contradictions or miss subtle timeline drifts across long texts. This skill uses specific scripts to gather hard data first, ensuring every flagged error is backed by a direct, line-cited quote from your manuscript.
Use cases
- Auditing a finished 80,000-word draft for physical consistency before querying agents.
- Checking a new chapter against the previous ten to ensure character ages and dates remain aligned.
- Identifying "dropped threads" or setups that were never resolved in a long-form series.
- Verifying that a revised draft still aligns with the rules established in your world-building notes.
Known limitations
Large manuscripts over 30,000 words may require batch processing or "Quick" mode to manage token limits. It cannot natively read .docx or .pdf files without conversion to plain text or Markdown.
Requires Node 18+ for script execution. Best with .md or .txt files. Manuscripts over 30k words require batching or Quick mode. Cannot interpret visual-only cues or subtextual contradictions.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
File Scopes