SuperAPI AI Directory
Partner中文AI newsFavorites
Skillseditor-captions

editor-captions

Design & creation

View repository

Updated 10-18 04:44

About this skill

Editor Captions

Requires

A running Scrollmark editor whose commands you can call: the SocialGPT editor chat, or scrollmark mcp from @scrollmark/cli for a coding agent. Without it the steps below can't run; the kit-by-vibe list is still a fair guide to choosing a caption look in any editor.

Pick the rhythm

  • One word at a time (default): captions.applyRhythm with mode: "word".
  • Three-word chunks, when the user wants chunks rather than single words: captions.applyRhythm with mode: "sequential" and wordsPerCaption: 3.

Never phrase (8-word lines), never phrase-plus-word (an extra word track), and never captions_generate: it makes sequential chunks without the rhythm you chose.

Steps

After the recut, or on a timeline that already has the keep list:

  1. The rhythm op above, then captions.applyPreset with kitId, size and placement: as two ops in one timeline_applyPlan, or as captions_applyRhythm and captions_applyPreset outside a plan.
  2. Pick one kitId from this set. Choose from the footage (transcript, setting, what they are selling). Do not call captions_listPresets just to browse.
  • handwritten — casual talking-head, lifestyle, personal story, home or messy setting
  • soft-promo — product, beauty, UGC, "check this out" energy
  • podcast-plate — interview, seated conversation, darker or serious talk
  • clean-minimal — default if unsure; explainer, professional, clean talking-head

Do not use tiktok, creator-classic, sticker-box, cinematic, yellow-punch, meme-loud, or active-word unless the user names that look. 3. Size: s for word captions, since at m long words clip on a vertical video; m or l only when the user asks for bigger captions. 4. Placing for a platform (the user named one, or the editor's safe zone shows one): pass the same platform to captions.applyRhythm and to captions.applyPreset. The preset recomputes where captions sit, so leaving it out of either call puts them back under the platform's caption block. Then check that platform with qc_run (checks: ["document"]) and fix what it finds with qc_applyFix. 5. If captions already exist with role word, captions_resync. It keeps their kit, colour and size, so do not apply a preset afterwards unless the user asks for a different look.