dinaf2026-web
UserGenre-agnostic editorial team for novelists — 8 Claude Code skills (publisher critique, continuity, fair-play, prose immersion, KDP listing, canon ledger) driven by an auto-detected per-book profile.
Categories
Indexed Skills (19)
manuscript-canon-ledger
Living, versioned canon ledger for any book or series — the persistent source of truth the continuity pass reads before it audits. Holds canon as STATE (per character/place/timeline fact, marked STABLE, DISPUTED, or EVOLVING) plus a DELTAS changelog of intentional changes tagged to book + chapter + reason, and OPEN QUESTIONS for unresolved canon disputes. Stored per project under .manuscript/canon-ledger.json. Use when the author says "canon ledger", "update the ledger", "record a canon change", "is this canon", "what's the canon for X", "add a delta", "resolve open question", or "seed the ledger from book N". It maintains the ledger and renders a human .xlsx view; it does NOT audit a manuscript (continuity-audit does that, consuming this ledger), rewrite prose, or judge mystery logic.
manuscript-continuity-audit
Continuity and canon-integrity auditor for any novel, series, or manuscript. Cross-checks a chapter, scene, outline, or full draft against the book's own bible (set in the project profile) plus its internal logic, and produces a defect list — every contradiction of established canon, every drifted detail, every broken series rule, every internal inconsistency. Use when the author says "continuity check", "canon audit", "does this break canon", "check this against the bible", "did I get the details right", "find inconsistencies", or "continuity pass". It only diagnoses continuity — it does not rewrite prose or grade craft/marketability (those are the other passes).
manuscript-editorial-router
Routes a broad or ambiguous editorial request to the right pass(es) in the Manuscript Editorial Suite. Use when the ask spans more than one kind of feedback or it's unclear which is wanted — "review my book", "give me editorial feedback", "is this ready", "go over this chapter", "full editorial pass", "what should I check". Picks among manuscript-publisher-critique, manuscript- continuity-audit, manuscript-fair-play-audit, manuscript-prose-immersion-audit, and manuscript-listing-critique, runs them in the right order for the book's genre, and hands off. Does not itself critique, score, or rewrite — it only dispatches.
manuscript-fair-play-audit
Mystery-mechanics auditor for any mystery, crime, or thriller manuscript. Maps the clues, tests whether the solution is fair and re-readable, tracks plant-and- payoff, judges red herrings, and flags any place a coincidence — not deduction — solves the plot. Use when the author says "is the mystery fair", "clue audit", "does the solution hold up", "check the plot logic", "fair-play check", "did I plant the clues", "is the ending earned", "track plant and payoff", or "would a reader feel cheated". It judges mystery construction only — not prose, canon, or marketability. For non-mystery genres, this pass does not apply.
manuscript-listing-critique
Sales-listing critic for any book on Amazon KDP (and similar storefronts). Critiques (and, on request, rewrites) back-cover / jacket copy, the Amazon book description, categories, and keywords — the commercial surface that decides whether a browser clicks "buy". Use when the author says "critique the blurb", "review the back cover", "is this description good", "fix my Amazon listing", "rewrite my blurb", "check my categories and keywords", "would this sell", or "KDP listing review". For whole-story craft or an acquisitions verdict use manuscript-publisher-critique instead; this pass works only on selling copy and metadata, and never rewrites manuscript prose.
manuscript-profile-setup
Sets up (or edits) a book project's editorial profile for the Manuscript Editorial Suite. Every other pass auto-detects this profile from the working folder; this skill is what creates it. Use when there is no profile yet, when a pass reports "no profile found", or when the author says "set up my book", "create a profile", "edit my profile", "change my genre/shelf/comps", "onboard this manuscript", or "configure the editorial suite". It writes `<project>/.manuscript/profile.md` and seeds an empty canon ledger. It does not critique, score, or audit — it only configures.
manuscript-prose-immersion-audit
Line-level prose and scene-immersion auditor for any narrative manuscript — the deep craft pass beneath the publisher's read. Diagnoses scenes for the failures that keep prose at draft level: information dialogue, talking-heads, filter words, furniture-inventory description, missing micro-reactions, weak environmental presence, and emotion stated instead of threaded. Use when the author says "line audit", "prose immersion audit", "prose pass", "diagnose this scene", "is this immersive", "does this read like a draft", "craft pass", or "kill the info-dumping". It diagnoses at the line level — it does NOT rewrite prose, grade marketability, check canon, or judge mystery logic. For rewritten prose, route to the author's writing/voice skill.
manuscript-publisher-critique
The publisher's read for any manuscript — an acquisitions verdict plus a developmental craft breakdown, delivered as a scored report card graded against the markers of a great book in its genre (set by the project profile). Use for a single craft/acquisitions read of a scene, chapter, outline, full manuscript, or query: "publisher's read", "acquisitions verdict", "critique this", "score this", "grade this", "editor's letter", "would a publisher take this", "what's weak here", "read this like an editor". For a broad "review my book / full editorial pass" that may need several checks, use manuscript-editorial-router. NOT for canon checking (continuity-audit), mystery-fairness logic (fair-play-audit), line-level immersion (prose-immersion-audit), or blurb/listing copy (listing-critique). Diagnoses and scores; does not rewrite prose.
manuscript-editorial-router
Routes a broad or ambiguous editorial request to the right pass(es) in the Manuscript Editorial Suite. Use when the ask spans more than one kind of feedback or it's unclear which is wanted — "review my book", "give me editorial feedback", "is this ready", "go over this chapter", "full editorial pass", "what should I check". Picks among manuscript-publisher-critique, manuscript-continuity-audit, manuscript-fair-play-audit, manuscript-cinematic-scene-audit, manuscript-prose- immersion-audit, and manuscript-listing-critique, runs them in the right order for the book's genre, and hands off. Does not itself critique, score, or rewrite — it only dispatches.
manuscript-cinematic-scene-audit
Cinematic blocking and scene-population auditor for any narrative manuscript. Reads each scene the way a film director would — tracking every body in the room, every environmental detail a camera would see, all movement and physical continuity, the emotional reactions that would register on an actor's face, and the internal debate a character would voice in voiceover. Use when the author says "cinematic pass", "movie screen audit", "read this like a director", "do we account for everyone in the scene", "blocking pass", "camera test", "who's in the room", "did we forget anyone", "does the movement track", "would I see this on a big screen", "physical continuity check", "where is everyone", or "scene population audit". DISTINCT from prose-immersion-audit (which judges line craft): this audits spatial logic, blocking, full scene population, and cinematic completeness. It diagnoses and flags; it does NOT rewrite prose.
manuscript-canon-ledger
Living, versioned canon ledger for any book or series — the persistent source of truth the continuity pass reads before it audits. Holds canon as STATE (per character/place/timeline fact, marked STABLE, DISPUTED, or EVOLVING) plus a DELTAS changelog of intentional changes tagged to book + chapter + reason, and OPEN QUESTIONS for unresolved canon disputes. Stored per project under .manuscript/canon-ledger.json. Use when the author says "canon ledger", "update the ledger", "record a canon change", "is this canon", "what's the canon for X", "add a delta", "resolve open question", or "seed the ledger from book N". It maintains the ledger and renders a human .xlsx view; it does NOT audit a manuscript (continuity-audit does that, consuming this ledger), rewrite prose, or judge mystery logic.
manuscript-cinematic-scene-audit
Cinematic blocking and scene-population auditor for any narrative manuscript. Reads each scene the way a film director would — tracking every body in the room, every environmental detail a camera would see, all movement and physical continuity, the emotional reactions that would register on an actor's face, and the internal debate a character would voice in voiceover. Use when the author says "cinematic pass", "movie screen audit", "read this like a director", "do we account for everyone in the scene", "blocking pass", "camera test", "who's in the room", "did we forget anyone", "does the movement track", "would I see this on a big screen", "physical continuity check", "where is everyone", or "scene population audit". DISTINCT from prose-immersion-audit (which judges line craft): this audits spatial logic, blocking, full scene population, and cinematic completeness. It diagnoses and flags; it does NOT rewrite prose.
manuscript-continuity-audit
Continuity and canon-integrity auditor for any novel, series, or manuscript. Cross-checks a chapter, scene, outline, or full draft against the book's own bible (set in the project profile) plus its internal logic, and produces a defect list — every contradiction of established canon, every drifted detail, every broken series rule, every internal inconsistency. Use when the author says "continuity check", "canon audit", "does this break canon", "check this against the bible", "did I get the details right", "find inconsistencies", or "continuity pass". It only diagnoses continuity — it does not rewrite prose or grade craft/marketability (those are the other passes).
manuscript-editorial-router
Routes a broad or ambiguous editorial request to the right pass(es) in the Manuscript Editorial Suite. Use when the ask spans more than one kind of feedback or it's unclear which is wanted — "review my book", "give me editorial feedback", "is this ready", "go over this chapter", "full editorial pass", "what should I check". Picks among manuscript-publisher-critique, manuscript-continuity-audit, manuscript-fair-play-audit, manuscript-cinematic-scene-audit, manuscript-prose- immersion-audit, and manuscript-listing-critique, runs them in the right order for the book's genre, and hands off. Does not itself critique, score, or rewrite — it only dispatches.
manuscript-fair-play-audit
Mystery-mechanics auditor for any mystery, crime, or thriller manuscript. Maps the clues, tests whether the solution is fair and re-readable, tracks plant-and- payoff, judges red herrings, and flags any place a coincidence — not deduction — solves the plot. Use when the author says "is the mystery fair", "clue audit", "does the solution hold up", "check the plot logic", "fair-play check", "did I plant the clues", "is the ending earned", "track plant and payoff", or "would a reader feel cheated". It judges mystery construction only — not prose, canon, or marketability. For non-mystery genres, this pass does not apply.
manuscript-listing-critique
Sales-listing critic for any book on Amazon KDP (and similar storefronts). Critiques (and, on request, rewrites) back-cover / jacket copy, the Amazon book description, categories, and keywords — the commercial surface that decides whether a browser clicks "buy". Use when the author says "critique the blurb", "review the back cover", "is this description good", "fix my Amazon listing", "rewrite my blurb", "check my categories and keywords", "would this sell", or "KDP listing review". For whole-story craft or an acquisitions verdict use manuscript-publisher-critique instead; this pass works only on selling copy and metadata, and never rewrites manuscript prose.
manuscript-profile-setup
Sets up (or edits) a book project's editorial profile for the Manuscript Editorial Suite. Every other pass auto-detects this profile from the working folder; this skill is what creates it. Use when there is no profile yet, when a pass reports "no profile found", or when the author says "set up my book", "create a profile", "edit my profile", "change my genre/shelf/comps", "onboard this manuscript", or "configure the editorial suite". It writes `<project>/.manuscript/profile.md` and seeds an empty canon ledger. It does not critique, score, or audit — it only configures.
manuscript-prose-immersion-audit
Line-level prose and scene-immersion auditor for any narrative manuscript — the deep craft pass beneath the publisher's read. Diagnoses scenes for the failures that keep prose at draft level: information dialogue, talking-heads, filter words, furniture-inventory description, missing micro-reactions, weak environmental presence, and emotion stated instead of threaded. Use when the author says "line audit", "prose immersion audit", "prose pass", "diagnose this scene", "is this immersive", "does this read like a draft", "craft pass", or "kill the info-dumping". It diagnoses at the line level — it does NOT rewrite prose, grade marketability, check canon, or judge mystery logic. For rewritten prose, route to the author's writing/voice skill.
manuscript-publisher-critique
The publisher's read for any manuscript — an acquisitions verdict plus a developmental craft breakdown, delivered as a scored report card graded against the markers of a great book in its genre (set by the project profile). Use for a single craft/acquisitions read of a scene, chapter, outline, full manuscript, or query: "publisher's read", "acquisitions verdict", "critique this", "score this", "grade this", "editor's letter", "would a publisher take this", "what's weak here", "read this like an editor". For a broad "review my book / full editorial pass" that may need several checks, use manuscript-editorial-router. NOT for canon checking (continuity-audit), mystery-fairness logic (fair-play-audit), line-level immersion (prose-immersion-audit), or blurb/listing copy (listing-critique). Diagnoses and scores; does not rewrite prose.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.