explainer-editor

What it does when it runs

Edit a raw vertical (9:16) take of someone talking to the camera into a finished short in the Pipecorn EXPLAINER LANGUAGE, with the motion of an After Effects edit: the speaker in a frame with round top corners at the BOTTOM of a dark stage lit like a set (charcoal lit from the middle, a vignette, a light on each scene carried by the camera, a red glow in a corner, dust floating, a grid of dots), their head (and hands) rising out of the frame (person matte); ABOVE them, the stage EXPLAINS what they say as they say it, in SCENES joined by CAMERA MOVES (whip pans with a light streak, rises, push-throughs), everything with real MOTION BLUR, springs and expo curves, never still (a slow drift and push, parallax on the dots and the dust), every figure casting a soft SHADOW on the ground and GLOWING in its colour (glossy rims, a sheen across the cards, a flash of light behind what pops in): a two-line title per section (Inter ExtraBold with one Instrument Serif italic accent, a red box or a red underline), then a new figure every second or so on the word that names it: numbered bars with a red edge whose labels are blurred until said, pills, trees wired on with a spark, a phone, image cards and the speaker's own frames, logos, pictograms, an arrow, an equation, a VS with a camera shake, a prompt typed letter by letter, document pages, counters, marks drawn round things; between the stage and the speaker, the speaker's words ONE AT A TIME; a few times a minute a hard cut to FULL SCREEN with a camera flash; the SOUND of the motion: the two base skills' pack on the big moves (the whoosh on every scene change, the glitch on a hit, the riser into a payoff, the flash on the cut) and a light sound of the Motionix pack on everything that appears (a pop, a swish, a tick, a select, a check's confirm, a shutter on a frame of the take, the typing of a prompt, the data of a scan), set on the take's voice and measured as heard; a music bed that goes silent on the breather that lands the point; audio finished at -14 LUFS and verified numerically before delivery. Any take: a close one gets a narrower frame (the head at the reference's size), a take of several shots is framed shot by shot; the whole stage exists in a DARK version (the reference) and a LIGHT one (`--theme light`), the same elements. Use when the user hands over a talking-head take and asks for a split-screen explainer, a breakdown, motion graphics explaining what is said, the speaker at the bottom with animations above, a guide or a tutorial short, or says explainer, split screen, moi en bas et les animations en haut, montage explicatif, style breakdown, motion design.

Automated analysis of the skill and the 20 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply

• ELEVENLABS_API_KEY

Hosts it reaches

• cdn.jsdelivr.net

Tool permissions it declares

No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.

Actions present in the files

shellwrites filesnetwork