agentleFS
raphaelbgrraphaelbgr/ai-video-prompting/skills/cinematography/SKILL.md

cinematography

Skill0 starsChanged 2 months agoMITView on GitHub

Use when choosing the shot, lens, aperture, camera move, lighting or colour grade for a generated clip - or when a clip technically rendered but feels flat, the wrong character is in focus, or a listener's face appears where it should not. The director-of-photography layer: what each choice does emotionally, and the exact phrasing that survives a video model.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Close-ups (85mm, f/1.8): only the speaking character is visible.

    line 111
  2. Distinctive:

    If the interface already sets the ratio, do not also write it in the prompt text.

    line 192
  3. Distinctive:

    Every table above runs technique -> effect.

    line 236

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Cinematography for generated video

The camera and lighting decisions, with what each one does to the viewer — because a video model will happily render a technically correct shot that lands emotionally wrong.

Full menus (shot sizes, angles, all camera moves, optics, composition, lighting setups, palettes, film stocks, styles): prompt-expander/references/visual-language.md. This skill is the decision layer on top of them.


1. Shot, lens and aperture by purpose

Pick the row that matches the job of the shot, not the one that sounds most cinematic.

PurposeShotLensAperture
Hook / emotionClose-up85mmf/1.8
Peak intensityExtreme close-up85-135mmf/2.0
DialogueMedium50mmf/2.8
Reveal / contextMedium wide35mmf/4.0–5.6
Two peopleTwo-shot50mmf/3.5
POV / environmentPOV35mmf/5.6
Over-the-shoulderOTS50mmf/2.5

A wide shot has two jobs, and the frame decides which. Subject large in frame with the space around them reads as context. Subject small and swallowed by the space reads as isolation. Both are wides; only the second one is lonely. Say which you want.

Lens to feel: ultra-wide (≤24mm) expands space and exaggerates depth · wide (28–35mm) holds subject and environment · normal (50mm) is human-eye natural · telephoto (85mm+) compresses depth and flatters portraits.

Depth of field:

ApertureEffectUse
f/1.8Very shallow, creamy bokehClose-ups, emotion
f/2.0–2.8Shallow, subject isolatedDialogue, reactions
f/3.5–4.0Moderate, background readsTwo-shots, walking
f/5.6Deep, background visibleReveals, environment

2. Camera movement — pick for the effect, name exactly one

MovementEffectUse case
Slow push-inBuilding intensityHook, punchline
Tracking (parallel)Energy, momentumWalking scenes
Static handheldDocumentary honestyInterviews, reactions
HandheldUrgencySomeone moving with purpose
Shaky cameraChaosThe moment control is lost
Dolly zoomShockThe ground going out from under someone
POV push-inCuriosity, leaning forwardObserving chaos
Dolly-inHero momentTriumphant reveal
Pull-outIsolation, scaleEndings, reveals of scope
Orbit / arcEmphasises importanceDynamic reveal
Whip pan / crash zoomShock, comedy, transitionPattern break

Rules that are not optional:

  • Exactly one move per clip. Two named moves, or a vague one, makes the model default to a near-static drift.
  • Some single moves have two-word names, and they are still one move. dolly zoom, slow push-in, slow pull-out, whip pan, crash zoom. The rule above is about two independent moves ("pan while craning down"), never about word count.
  • Focus and duration are not moves. rack focus (reveal), long take (suspense) and slow motion describe something other than where the camera goes. A clip carrying only one of them still has no camera move and still needs one, or static shot.
  • A locked frame must be stated: static shot, optionally static shot, no camera movement. Omitting the camera line does not give you a still frame.
  • Never write "locked" at all — not "locked tripod", not "locked shot", not "locked off". "Locked tripod" is misread: the model adds motion anyway and has been observed rendering a literal tripod in frame. static shot says the same thing and is safe.
  • Never combine contradictory terms ("drone shot zooming into close-up"). Pick one perspective.

2b. Angle — the cheapest way to change how someone reads

Where the camera sits relative to the eyeline changes who has power in the frame, before a word is spoken. An unstated angle renders eye-level: fine as a decision, a defect as an accident.

AngleReads asUse
Eye levelNeutral, equalDefault; dialogue
Low angleAuthority, threatSomeone taking power
High angleVulnerable, smallSomeone losing it
Dutch angleUnease, instabilitySomething is wrong and nobody has said so yet
Overhead / top-downPowerless, fatedA person as one dot among many

The trap is using the angle that contradicts the beat — a low angle on someone being humiliated makes them look like they are winning. Pick the angle for who should have power in that second, not for what looks impressive.

3. The over-the-shoulder rule (stops the wrong face appearing)

In a dialogue scene between two characters, the listener is where generated clips go wrong — the model renders their face, badly, in the corner of frame.

  • Close-ups (85mm, f/1.8): only the speaking character is visible. Do not mention the other one at all.
  • Medium (50mm/35mm) and wider: show the back of the other character's head at the edge of frame. Describe them only from behind — "back of head", "back of shoulders", "shirt collar seen from behind". Never describe their face, expression, eyes or glasses.

Wrong — this renders a face:

Man frozen in shock visible at frame edge left in soft focus. Balding with semi-rimless glasses. Completely stunned expression, gaze fixed on her.

Right — this renders an over-the-shoulder:

The back of his head and shoulders visible at frame edge left in soft focus. His balding crown and the back of his light blue-grey shirt collar seen from behind. He is facing away from camera toward her.

Same idea generalises: in a close-up, keep exactly one character in focus. Others are soft-blurred, off-screen, or speaking from off-screen.


4. Lighting

StyleDescriptionUse
Flat documentaryEven, overhead fluorescentHallways, offices
Split warm/coolTwo colour temperatures meetingDoorway scenes, transitions
Soft diffusedGentle, flatteringInterview subjects
Harsh overheadHard shadowsRaw documentary feel
Window naturalWarm, cosyHome interiors
ChiaroscuroStrong side light, extreme contrastDramatic character moments

Colour temperature:

SettingTempMood
Fluorescent office4000–4100KCool, corporate
Afternoon daylight5200–5600KNatural, bright
Golden hour4000–4500KWarm, heroic
Indoor apartment5000KCosy, domestic
Mixed (doorway)split 3500K / 4100KTransition

Standard lighting line:

Lighting: [quality] [source] at [angle]. [detail]. Color temperature [X]K. [grade]. 24fps.

Examples:

Lighting: Bright harsh fluorescent office lighting from multiple ceiling panels.
Color temperature 4100K cool white. Very slight green cast typical of office
fluorescents. 24fps.

Lighting: Warm natural afternoon sunlight from a window at camera-left. Soft golden key
on the face. Color temperature 5000K. Warm cosy domestic grade. 24fps.

One lighting motif per clip. And never write a mid-clip lighting transition into the look line — a light that changes is a cut, not a description.


5. Framing for the aspect ratio

9:16 (vertical): centre the subject · leave headroom at the top for platform UI · keep everything important inside the centre 80% of frame · text overlays read best at top and bottom.

16:9 (landscape): rule of thirds · more room for environmental context · better for wide shots and scenery.

PlatformRatio
TikTok · Instagram Reels · YouTube Shorts9:16
YouTube (standard)16:9
Facebook / LinkedIn16:9 or 1:1

If the interface already sets the ratio, do not also write it in the prompt text.


5b. Composition — where the subject sits inside the frame

CompositionReads asUse
Centre frameControl, stabilitySomeone in command of the room
Negative spaceAnticipationSomething is about to enter the empty half
Frame within a frameTrappedShooting through a doorway, window, mirror, windscreen

In 9:16 you buy centre framing whether you want it or not. Section 5 tells you to centre the subject for platform reasons — under-the-UI safety, not meaning — and the frame still reads as control. To signal instability in vertical you have to work for it: a dutch angle, or the subject pushed hard to one side against deliberate negative space.

Frame-within-a-frame is easy to use by accident. Anything shot through a window, a doorway or a windscreen is one, and it says trapped even when the scene is about freedom. Check that the meaning is the one you want before shooting the whole film through glass.

6. Where the shot fits the story

One clip is one beat. Choose the coverage to match:

BeatCoverage
Revealslow push-in as they see it
Reactionclose-up; face shifts from calm to shock
Tension buildrising stillness, held breath, static frame
Payoffrelease — exhale, sudden motion, pull-out
Establishingwide, deep DoF, then cut in

Standard sequence: establishing wide → medium → detail/close. Reveal, then specify.

Identity holds best in calm close and medium shots and drifts in fast action and wide shots — so put identity-critical beats in calm coverage and let action shots run loose. See identity-and-likeness.


7. Emotion -> technique (reverse index)

Every table above runs technique -> effect. This one runs the way a writer actually arrives: knowing how the beat should feel and needing the camera that delivers it.

The beat should feelReach for
AnticipationNegative space
AuthorityLow angle
ChaosShaky camera
ConflictOver-the-shoulder
ConnectionClose-up, 85mm f/1.8
Controlstatic shot; centre frame
ImmersionPOV
IntensityExtreme close-up
IsolationWide, subject small in frame
LonelinessSlow pull-out
MomentumTracking shot
PowerlessOverhead / top-down
RevealRack focus
ShockDolly zoom
SuspenseLong take
TensionSlow push-in
TrappedFrame within a frame
UneaseDutch angle
UrgencyHandheld
VulnerableHigh angle

[FIELD PRACTICE]. These pairings are live-action editorial convention, not vendor documentation, and nothing in this repo yet proves a video model renders "low angle" as authority rather than merely as a low camera. Use them to choose, then let a shoot confirm. Source and the gap analysis they came from: docs/camera-agent/emotion-technique-map.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.