Screenplay Audit skills for AI agents

Deep structural analysis for screenplays in any format. Maps the script's actual act breaks, inciting incident, midpoint, dark moment, climax, and resolution against ideal structural targets. Produces a visual page-map comparing actual vs expected beat placement.

Detects AI-generated dialogue patterns specific to screenplays: on-the-nose dialogue where characters say exactly what they feel, exposition dumps disguised as conversation, every character being equally articulate, missing subtext, dialogue that reads as written rather than spoken, therapy-speak, characters narrating the plot to each other, and the AI tendency to resolve conflict through a single perfect speech. Produces a per-scene dialogue quality score with specific rewrite direction. Use when screenplay dialogue feels flat, over-written, or like characters are reading essays to each other.

Format-specific checker for animated screenplays across kids, adult, film, stop-motion, and CG formats. Verifies visual stageability, voice performance dialogue, gag specificity, age-appropriate content, and correct act structure for episode length.

Detects AI character flattening in screenplays — where characters lose complexity because AI can only convey interiority through dialogue (not narration like novels). Scans for: characters who speechify their feelings, arc-by-monologue, identical speech patterns across the cast, behavioral predictability, missing character-specific action/business, characters who exist only for exposition or to be wrong so the protagonist can be right, and antagonists who are either cartoons or have their "good point" neutralized by a single speech. Produces character depth scores and rewrite guidance specific to the visual medium. Use when screenplay characters feel thin, functional, or indistinguishable.

Specialized for multi-episode works including limited series, ongoing series, and web series. Tracks character knowledge, relationship status, prop and location continuity, and serialized arc beats across all episodes. Builds a continuity matrix and flags contradictions.

Analyzes screenplay dialogue for subtext depth. Scores each exchange on a 1-5 subtext scale, identifies exposition dumps and on-the-nose dialogue, and provides rewrite suggestions that add layers of meaning beneath what characters actually say.

Format-specific auditor for documentary screenplays. Checks narration for factual accuracy and attribution, interview setups, B-roll directions, archival footage cues, and adherence to observational, expository, or participatory conventions.

Screenplay originality scanner — detects stock premises, predictable beats, clichéd set pieces, genre-default plot structures, and derivative concepts at the story level. Catalogs 40+ screenplay-specific clichés (the ticking bomb, the training montage, the liar revealed, the slow clap, the mentor's death speech), assesses logline originality, identifies which produced films the script most resembles, and provides specific subversion strategies. Use when the screenplay feels derivative, predictable, or like an assembly of familiar parts from other movies.

Screenplay pacing and page-count auditor — detects structural pacing failures specific to film and TV scripts: uniform scene lengths, missing act breaks, no ticking clock, set piece deficiency, page-count bloat or deficit per act, first-act delay (inciting incident too late), second-act sag, rushed third act, scene-count-per-act imbalance, and the AI tendency to write every scene at the same dramatic temperature. Produces a page-count breakdown by act, tension map, and scene length distribution. Use when a screenplay feels flat, too long, too rushed, or structurally unbalanced.

Specialized auditor for TV pilot scripts. A pilot has unique requirements beyond a regular episode: it must establish the world, introduce series regulars, demonstrate the show's engine, set up the central conflict, and work as both a standalone story and a series promise.

Screenplay producibility auditor — assesses whether a screenplay can actually be produced within realistic constraints. Scans for: budget impossibilities, unfilmable action lines, excessive VFX requirements, location sprawl (too many unique locations), cast bloat (too many speaking roles), schedule-killing scenes (children, animals, water, night exteriors), rights issues (real people, songs, brands), and the AI tendency to write without any awareness of production realities. Produces a budget tier assessment, location count, cast breakdown, and specific producibility flags. Use when assessing whether a screenplay is realistically makeable, or when preparing for pitch/production conversations.

Detects repetition patterns specific to AI-generated screenplays: recycled action lines, repeated scene descriptions, reused character business, duplicated transitions, characters having the same conversation twice, identical scene structures, and the AI tendency to describe the same location identically each time it appears. Produces a repetition map with page locations and specific revision guidance. Use when a screenplay feels circular, repetitive, or like scenes are variations of each other.

Evaluates every scene in a screenplay against the essential question: does this scene need to exist? Each scene must advance plot, reveal character, or build the world. Flags inert, redundant, and filler scenes with specific remediation guidance.

Comprehensive AI-generated screenplay auditor. Use this skill whenever the user wants to audit, review, proofread, or quality-check an AI-generated screenplay, script, or teleplay. Triggers include: "audit my screenplay", "check my script", "review my teleplay", "check my pilot", "find script errors", "check scene headings", "verify my story follows the outline", "check character names in my script", "find duplicate scenes", "does my script follow three-act structure", "check my episode", "review my short film script", "web series script QA", "animated script check", "documentary script review". Supports all major formats: Feature Film, TV Limited Series, TV Series (ongoing), Adult Animated Series, Kids Animated Series, Animated Film, Stop-Motion Film, CG Animated Film, Documentary, Short Film, and Web Series. Use even if the user only mentions one specific concern — always run the full audit unless explicitly told otherwise.

Automated detection and correction of screenplay formatting errors. Fixes malformed sluglines, character cue capitalization, parenthetical overuse, transition formatting, scene numbering, and page break issues. Includes the complete formatting reference for all 11 screenplay formats.

Screenplay tone consistency auditor — detects tonal drift, genre confusion, and register inconsistency across a screenplay. Scans for: comedy/drama whiplash, AI defaulting to prestige drama regardless of genre, scenes that belong in a different movie, tonal register shifts between sessions, horror that's not scary, comedy that's not funny, and the AI tendency to flatten everything to "serious with moments of levity." Produces a tonal map and identifies scenes that break the tonal contract. Use when the screenplay feels tonally uneven or like it can't decide what kind of movie it is.

Detects the #1 AI screenplay failure: writing for the page instead of the screen. Scans for talking-head scenes with no visual action, missed opportunities for visual storytelling, scenes that could be silent but aren't, over-reliance on dialogue to convey information/emotion that should be shown, static staging (characters sitting and talking), no use of props/environment/weather/lighting as storytelling tools, and action lines that describe internal states instead of visible behavior. Produces a visual storytelling score and specific cinematic rewrite suggestions. Use when the screenplay reads like a stage play or radio drama rather than a film.

Specialized tool for fixing V.O. (voice-over) and O.S. (off-screen) attribution in screenplays. AI consistently confuses these extensions. Also covers CONT'D usage, PRE-LAP, and other dialogue extensions with clear rules and correction examples.