ihsaneGTM/gtm-skills

8 skill entries

• cold-call-editor

  Edit a vertical (9:16) video whose SOUND is a recorded phone call (a cold call: the caller and the person called) over footage that has nothing to do with it, into a finished short in the Pipecorn CALL LANGUAGE: the most suspenseful line of the call as the hook, up front, glitched on its stressed words (picture and lettering); a paper sheet where the call is placed (the caller's microphone and the other side's handset land in stop-motion, a dotted line, the handset shakes, a synthesised ringback tone); bam (a camera flash, a de-zoom, the music on its first big hit); then the call typed out as a record at the bottom of the frame (Geist Mono, the speaker's name in a column, letter by letter on each measured word onset) with the voice as one thin line of wave above it, in the colour of the voice talking. Who speaks when is MEASURED (a timbre model per voice), the onsets are read on the audio envelope, the music sits about 17 LU under the voice, the audio is finished at -14 LUFS and verified numerically before delivery. Use when the user hands over a cold call, a sales call, a phone call recording, a call with a prospect, and asks to edit it, make a short of it, transcribe it on screen, show the two voices, or says monte cet appel, cold call, appel à froid, transcription de l'appel, style cold call.

  Needs a keyActs undeclared4,068 words
• explainer-editor

  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.

  Needs a keyActs undeclared7,297 words
• video-memo

  Turn a voice memo into shorts you can record: the memo transcribed (any language), the several videos it holds found and cut apart (1 to 3 minutes each), three restructured versions of each in the language of your videos (Straight, Hook first, and a Story, Contrarian or List), each read aloud with ElevenLabs so you hear it instead of reading it, at most three feedbacks per short (an idea to add, a big inconsistency, a link to another of your videos), and the lead magnet checked in every version. The substance stays yours; only the form changes. Writes workspace/memos/<slug>/memo.json for GTM by Pipecorn's Studio, where you pick a version, read it on the teleprompter, then edit it. Trigger on: mémo vocal, vocal, voice memo, j'ai enregistré une idée, transforme mon vocal en vidéos, fais-moi les scripts de ce vocal, plusieurs vidéos dans ce vocal, turn my voice note into shorts.

  Needs a keyActs undeclared1,680 words
• scrapbook-editor

  Edit a raw vertical (9:16) take into a finished short in the SCRAPBOOK STYLE, as validated by the user (2026-10-05), reproduced exactly on any take: every pause cut out (jump cuts, the frame alternating wide and close on each one); captions low, three words at a time, the word being said in yellow; the hook in the reference's TWO FACES (white Archivo words, THE important word in Fraunces in yellow) with a line on PAPER; the paper only for the titles and two or three very important phrases: the reference's collage of small ruled notebook scraps, flat, written in a marker hand (Gochi Hand), landing and unfolding, breathing, folding away, the red marker drawing on it as it is said (a word struck out, an underline); die-cut emoji stickers with white outlines round the head for what the speaker lists; real reaction GIFs from GIPHY as polaroids, big (0.80 of the width) in the middle of the screen, always at the same place, dropped on and flicked away; sections on the same scraps swinging in with the camera punching; app icons joined by a marker arrow; real screens annotated in red; a paper sweep into a change of scene; the ask on paper to the end. Two shadows under everything, motion blur, After Effects style. Hip Hop 02 as the music bed 15 LU under the voice, a real paper sound on every paper and the Motionix pack, -14 LUFS, every sound measured as heard. Use when the user asks for this style, a scrapbook / meme / GIF / paper-label / collage edit, a list or tools video (« 7 skills », « top 5 tools »), jump cuts, or says monte cette vidéo en style scrapbook, mèmes, GIFs, étiquettes papier, style liste, style TikTok éducatif.

  Needs a keyActs undeclared6,777 words
• short-editor

  Edit a raw vertical (9:16) take into a finished short in the Pipecorn VERTICAL LANGUAGE: the speaker's own words as big headlines at the TOP of the frame (Impact capitals with one Sacramento script accent) passing BEHIND them where their head rises into them (person matte), the real logos and product coming out from behind them, full-frame paper plates whose elements move in stop-motion under discreet subtitles, a music bed from the shelf, a sound design from the SFX pack (a camera flash on a change of shot, a click on what appears, a whoosh into the paper, a glitch on one text pop, a riser into the payoff), and audio finished at the -14 LUFS platform standard, verified numerically before delivery. An OLD-RADIO HOOK (the voice through an old radio set, the picture in an old CRT TV, on the first seconds only: around 7 s, never past 10 s) is a BONUS offered in the first question every time, never applied by default. Also assembles a RUSH (a long take where the speaker restarts each sentence) into one clean take first, and cuts the intro of a 16:9 video in landscape mode. Use when the user hands over a video file and asks to edit it, add headlines, subtitles, animations or sound effects, a radio voice or an old-TV look on the hook, cut the dead air, keep the good takes, fix the volume, or says montage, monte cette vidéo, edit this short.

  Needs a keyActs undeclared6,596 words
• shorts

  Long video to shorts (/video-long-to-shorts, formerly /video-shorts): your long video, filmed talking to the camera (often derushed already, horizontal or vertical; the same file the YouTube video editor edits, at the same time if you like), in; several vertical shorts out. Its key moments found and REORGANISED (the strongest line moved first as the hook, the rest in the order that makes a short), each subject in about 30 s, 1 min and 1 min 30, the retakes and dead air cut, your real voice wherever you said it, and where a short needs a line you never said (a hook, a bridge), your cloned voice says it, in your words, if you add an ElevenLabs key (the take itself is heard on your Mac, no key). Your face from the first frame, the words in Dynamic text (the short editor's vertical language), the long video's pictures with its effects, white pages that draw the idea, three ways: Behind you (default), Prints, Cutaways; an end card to the long video on YouTube, with your brand's channel, if you want one; one music; -14 LUFS; checked. Trigger on: long video to shorts, make shorts from my video, cut my long video into shorts, clips from my YouTube video, find the best moments, repurpose my video, fais des shorts de ma vidéo, découpe ma vidéo longue en shorts, les meilleurs moments, des reels à partir de ma vidéo YouTube.

  Needs a keyActs undeclared2,668 words
• voiceover-video

  YouTube video editor (/video-youtube-editor; this folder keeps its first name, voiceover-video): a complete edit of a horizontal YouTube video (16:9, often long), three ways, the same skill. FACECAM: the user filmed the whole video talking to the camera; their real voice runs all along, cut tight (retakes, fillers and dead air cut out), illustrated in motion design with their dressed face shots in between. AI VOICE: no filming; the whole video in motion design, said by their voice clone, an ElevenLabs voice or Ihsane's once shared, from a script, an idea or an article. HYBRID: they film only the intro (and a few cutbacks), their cloned voice says the rest. The style « Document » settled over twelve reviews on 2026-10-12/13 (real homepages at the full viewport and real logos, LinkedIn-style cards of fictional people, editorial lines with a yellow marker, numbers that count, charts one per metric under their app icon, the yellow V chapter pages, the method list), real stock shots in a frame on the paper and GIFs as pinned prints; face shots dressed (graded, at their speed, cut out, lockups behind the head, punches); junctions on the same frame, no dead air; ONE music; -14 LUFS; a 1080p draft and a 720p preview, the 4K only when the user asks. Trigger on: edit my YouTube video, YouTube video editor, horizontal video, long video, facecam, no facecam, AI voice video, I only filmed the intro, use my voice for the rest, cloned voice video, voiceover video, monte ma vidéo YouTube, vidéo horizontale, sans facecam, j'ai filmé que l'intro, fais la suite avec ma voix clonée.

  Needs a keyActs undeclared5,775 words
• whiteboard-editor

  Whiteboard, the first style of the Short video editor (/video-whiteboard-editor): one raw vertical take of you talking to the camera in, one finished short out, edited in exactly the look of Long video to shorts: your face from the first frame, a visual hook (the problem as a title, a few pictures of the subject), your words in Dynamic text, the pictures sliding out from behind you (or pinned over the frame, or as cutaways), white pages that draw the idea as a moving schema, one music 19 LU under the voice, -14 LUFS, the feed's safe zones, checked. The take keeps its own order (its retakes and dead air cut); no long-video analysis, no end card unless you ask. Heard on your Mac (Whisper), no key needed. Trigger on: whiteboard, whiteboard style, edit this short like my long-video shorts, the shorts' look on one take, white pages, monte cette vidéo en Whiteboard, le style des shorts sur ma prise.

  Needs a keyActs undeclared1,833 words