Documentary Script Checker
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.
Documentary screenplays operate under fundamentally different rules than fiction. Narration must be factual. Interview subjects must be real and properly identified. Visual direction must guide an editor working with real footage, not a cinematographer staging fiction. This skill audits documentary scripts against these requirements. ## Key Points - Statistics without sourcing: "Over 40% of Americans..." — source? - Historical claims without attribution: "In 1847, the city was destroyed..." — per whom? - Characterizations presented as fact: "She was the most talented surgeon of her era" - Cause-and-effect claims without evidence: "This decision led directly to the crisis" - Observable facts: "The sun rises over the valley" (visual description) - Statements introduced with attribution: "According to Dr. Smith..." - Clearly labeled opinion: "Critics argued that..." - Fabricated quotes attributed to real living or historical people - Reenactments not clearly labeled as reenactments - Composite characters presented as real individuals - Narration that presents speculation as established fact - Interview questions designed to entrap or mislead subjects
skilldb get screenplay-audit-skills/documentary-script-checkerFull skill: 138 linesDocumentary Script Checker
Documentary screenplays operate under fundamentally different rules than fiction. Narration must be factual. Interview subjects must be real and properly identified. Visual direction must guide an editor working with real footage, not a cinematographer staging fiction. This skill audits documentary scripts against these requirements.
When to Use
Use when the user submits a documentary screenplay or asks to "check my documentary script", "review my doc", "audit my documentary", or when the declared format is DOC. Also use for hybrid formats (docudrama, mockumentary) with adjusted rules.
Documentary Sub-Formats
Six sub-formats exist: Expository (narrator-driven argument; Planet Earth, 13th), Observational (no narration, camera follows subjects; Hoop Dreams), Participatory (filmmaker present; Super Size Me), Poetic (mood/imagery over argument; Koyaanisqatsi), Performative (personal essay; Sans Soleil), Reflexive (about filmmaking itself). Identify the sub-format before auditing — rules differ significantly.
Check 1: Narration Quality
Factual Attribution
Every factual claim in narration must be attributable to a source. Documentary narration is not fiction — it makes claims about the real world.
Flag:
- Statistics without sourcing: "Over 40% of Americans..." — source?
- Historical claims without attribution: "In 1847, the city was destroyed..." — per whom?
- Characterizations presented as fact: "She was the most talented surgeon of her era"
- Cause-and-effect claims without evidence: "This decision led directly to the crisis"
Do not flag:
- Observable facts: "The sun rises over the valley" (visual description)
- Statements introduced with attribution: "According to Dr. Smith..."
- Clearly labeled opinion: "Critics argued that..."
No Editorializing
Flag narration that tells the audience what to think: "Tragically...", "The shocking truth...", "Anyone could see..." — these are editorial. Narration should present facts and let the audience draw conclusions. Exception: participatory and poetic sub-formats allow the filmmaker's perspective.
No Fabricated Quotes
Never put words in a real person's mouth. Flag fabricated inner monologue ("Lincoln thought to himself..."), speculative dialogue ("She probably said..."), and paraphrased quotes presented as direct quotes. All quotes must be sourced.
Check 2: Interview Setups
Every interview segment must include proper setup information for the editor and audience.
Required Elements
Each interview must include: subject's full name, title/credential/relationship to the story, location, and basic visual setup direction. Flag responses that sound scripted rather than conversational, leading questions (unless deliberately confrontational), and interview segments with no visual cutaway direction between quotes.
Check 3: B-Roll Directions
B-roll is the visual footage that plays over narration and between interviews. Flag: narration running 3+ lines with no visual direction, interview responses with no cutaway direction, and transitions with no visual bridge.
Flag vague B-roll: "B-ROLL: The city" (which city? what aspect?). B-roll must be specific enough for a camera crew or stock footage researcher to execute without guessing.
Use correct labels by type: B-ROLL: (original footage), ARCHIVAL FOOTAGE: (historical),
STILL: / PHOTO: (photographs), GRAPHIC: (animations/maps), SCREEN: (screen
recordings), REENACTMENT: (staged recreations).
Check 4: Archival Footage Cues
Archival footage must be precisely identified so the production team can source and license it.
Each archival cue must include: description, source/rights holder, approximate date, and any licensing notes. Flag: footage without source identification, footage that may not exist or be licensable, reenactments presented as archival (ethical violation), and unlabeled archival mixed with original footage.
Check 5: Structural Conventions
Expository: Opening/hook/thesis (5-10%), Evidence/exploration (60-70%), Complication that adds nuance (10-15%), Resolution/synthesis (10-15%).
Observational: Establishment through observed behavior (15-20%), Rising action through events (50-60%), Crisis/turning point (15%), Resolution or open ending (10-15%).
Participatory: Filmmaker's entry (10-15%), Investigation/interaction (60-70%), Revelation/confrontation (15%), Reflection/conclusion (10%).
Flag: Observational doc with heavy narration, expository doc with no thesis, participatory doc where the filmmaker is absent, any doc with a manufactured climax.
Check 6: Ethical Red Flags
Documentary scripts must not cross ethical lines. Flag:
- Fabricated quotes attributed to real living or historical people
- Reenactments not clearly labeled as reenactments
- Composite characters presented as real individuals
- Narration that presents speculation as established fact
- Interview questions designed to entrap or mislead subjects
- Footage used out of context to misrepresent events
Output Format
Present findings in tables per check category (Narration, Interview Setups, B-Roll, Archival Footage, Structure, Ethics) with columns appropriate to each: Page, Issue, Severity, Fix. End with a summary count of issues per category.
Anti-Patterns
- Applying fiction rules to documentary. Documentary narration is not "on-the-nose dialogue." It is informational by design. Do not penalize clear, factual narration.
- Demanding narration in observational docs. Observational documentaries work through footage selection and editing, not narration. No narration is correct for this format.
- Ignoring the ethical dimension. Documentary is non-fiction. Errors of fact or attribution are not style issues — they are ethical issues. Treat them as critical.
- Over-scripting. Documentary scripts are often working documents that evolve during production. They are less polished than fiction scripts by design. Flag structural and factual issues, not prose style.
Install this skill directly: skilldb add screenplay-audit-skills
Related Skills
originality-logline-scanner
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.
pacing-page-count-auditor
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.
Pilot Episode Auditor
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.
producibility-auditor
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.
repetition-auditor-screenplay
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.
Scene Function Auditor
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.