Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Book Production QC Bible — The Complete Gate Set

    1

    Twenty-five gates that catch what 'looks fine' misses — off-page answer keys, uncountable promises, unsolvable puzzles.

    $89

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Book Production QC Bible — The Complete Gate Set

    Book Production QC Bible — The Complete Gate Set

    Example session with this skill installed

    Run a full QC gate on the interior PDF and cover for 'Logic Puzzles Vol 1'. The listing sheet says 120 pages, 6x9, 50 puzzles. Verify the key join and check the cover for splice cliffs.

    • Read your context and instructions
    • Compiled the book production qc

    The QC scan for 'Logic Puzzles Vol 1' is complete. I have measured the interior PDF and cover image against the provided listing sheet. Findings include a census match and a successful coordinate scan, though a minor row-mean luminance step was detected on the cover join.

    Self-QC Report: Logic Puzzles Vol 1

    Book: LP-V1-001 · Byline/Imprint: BrainByte Press
    Files: interior (12,450,112 bytes, hash: 8f2a...) · cover (1875x2775 px, 2,104,332 bytes, hash: 3d11...)

    1. Mechanical: pages 120/120 · trim 6x9 uniform Y · fonts embedded YES · structure check clean
    2. Coordinate scan: words outside box 0 · widest display span 320pt · clipped cells 0 · fill lines N/A
    3. Visual proof: pages viewed 1, 2, 15, 60, 110, 120 · min page chars 142 · blank/near-blank 0 · duplicate pages 0

    Census: promised 50 puzzles vs counted 50 per section · in-book count claims verified YES · Contents pp verified Y
    5. Density: items/content page 1 · half-empty pages 0 · full-page tables N/A
    6. Relevance: sections read ALL · items replaced 0 · off-subject remaining 0
    7.

    Keys: join 50/50 · key pages viewed 110, 115, 120 · key coordinate scan 0 off-page · solution identity Verified · key pattern shuffled Y
    8. Solvability: method logic-solver · checked 50 · failures 0
    9. Accuracy: sample 10 puzzles · errors 0 · recomputation coverage 100%
    10. Production-language sweep: hit counts per term 0 · contamination scan 0
    11. Branding: owner/company/internal names 0 across all files
    12. Front matter: p2 complete per splice standard Y · ISBN handling Omitted · three-way title agreement Y
    13. Cover: step Δ @ join row 1.2 · band max (58-74%) 2.1 · full view PASS · hash differs from failed covers Y
    14. Price: list 9.99 · net arithmetic 2.45 · sheet = seo = draft price Y
    15. Sheet truthfulness: all numbers verified Y · hashes from correct files Y · flags None

    Defects found & fixed before delivery: none found — checks above.

    Next steps

    • Proceed to upload the interior and cover files to the distributor.
    • Archive the self-QC report in the delivery folder for audit trail.
    • Update the production log with the final file hashes.

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

    About this skill

    The complete quality-control system for anyone who produces books with AI agents, freelancers, or a small team — and needs every delivery verified before it ships. This is not a checklist of good intentions; it is the measured gate set behind production QC for hundreds of titles: a full-book coordinate scan with a zero-tolerance rule for off-page, clipped or struck-through text; a census rule requiring every counted promise (puzzles, designs, log pages, contents page numbers) to reconcile exactly; programmatic solvability — logic puzzles solved from the printed page by an independent solver, word searches reconstructed letter by letter, sudoku proven unique, chess mates engine-verified; a cover-acceptance metric (the row-mean step scan) that detects composited-cover seams that stripe scans pass; listing-sheet truthfulness rules (hashes quoted from the correct file, qualified-review flags carried honestly instead of cleared); an EPUB structural-validation standard; a per-title self-QC report template; an evidence standard that treats unrun gates as NOT MEASURED and ranks producers by whether their evidence re-measures clean; and the writing-quality gates — the five failure modes (restatement, continuity breaks, summary instead of scene, undifferentiated voices, middle sag) plus a voice-and-heart standard with a precise no-whining rule. Includes a fix-forward policy so mechanical defects get repaired at QC instead of bouncing deliveries for weeks.

    Cannot clear legal or clinical gates. Requires access to final PDF/EPUB files and listing metadata. Mechanical fixes are limited to non-creative production adjustments.

    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 8 days ago

    Permissions

    Read Files
    Listed8 days ago

    What's inside

    Frequently Asked Questions

    This skill focuses on 'invisible' technical errors that standard AI prompts miss, such as font embedding issues, margin breaches, and mechanical metadata mismatches that could lead to printer rejection.

    Yes, the skill includes independent solver logic specifically designed to verify that Sudokus, word searches, and logic puzzles are unique and solvable as printed.

    The skill is designed to work with standard book production files, including PDF text layers, image-rendered page proofs, and structural EPUB data.

    You will receive the complete QC Bible skill configuration, the §20 standardized reporting template, and a guide for integrating the skill into your existing publishing workflow.

    The skill generates a structured §20 QC report that explicitly flags any 'not measured' areas, preventing the AI from hallucinating a clean pass and ensuring you have an audit trail for KDP or IngramSpark.

    While it audits writing quality for voice and locale-specific spelling, it does not provide legal or clinical reviews for specialized medical or technical content.

    New in Workflow Automation