Maintain the existing May Shorts teaching compositions using their legacy face-mode, scene-overlay, and karaoke-caption patterns. Use only when working on those examples or explicitly requesting this legacy scaffold. For new reels, Shorts, or short advertisements, use short-form-edit.
SkillScore90Maintained
Automatic
◆Marketing & Content pack
Last verified 10/10/2026
What it changes
Passed 18 of 20 test cases with the skill, and 7 of 20 without it.
Without skill35%
With skill90%
Checks it passed that the model alone missed
Recommends using short-form-edit for brand-new video builds.
Performs draft render before word-exact PNG frame extraction.
Executes ffprobe commands to measure original and edited media durations.
and 10 more in the full report
11 fixed7 passed either way2 still failing0 broke3 errored
Pass-rate lift
+55 pp
Tokens
+179%
Agent turns
0%
Response time
-44%
Model gemini-3.6-flashMeasured 10/10/2026v118 of 23 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
Beyond mode changes between scenes, what continuous camera motion animation must be applied to the talking-head face video over its full duration?
What was checked, without and with the skill
Checked
Without skill
With skill
Applies a subtle Ken Burns zoom from scale 1.00 to 1.025 with ease: "none" over the full duration.
Missed
Passed
case-19 · gemini-3.6-flash · 10/10/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md325 linessingle file
Short-Form Vertical Video (Hyperframes)
Short-form = 1080x1920 vertical, 10–30s, talking-head face + motion-graphic scene overlays + karaoke captions. Everything in this skill is distilled from the May Shorts 19 iteration autopsy (v1 → v4) and is preserved for maintenance of those examples. Use short-form-edit for new recordings.
Always invoke /hyperframes first. This skill sits on top of it — it does not replace the framework rules (data-* attributes, window.__timelines, composition structure). Those are non-negotiable regardless of the format.
When this skill fires
Maintaining the existing May Shorts examples.
Explicitly requesting their legacy four-layer scaffold.
The playbook (high-level)
Audio is source of truth. Edit audio FIRST (cut retakes, pauses). Save as <name>-edit.mp4. Measure exact duration with ffprobe — this is the composition's data-duration.
Transcribe the edited audio with the root scripts/transcribe-elevenlabs.mjs helper (ElevenLabs Scribe), a student-selected alternative normalized per docs/TOOLS-AND-API-KEYS.md, or if retiming an existing build with a shift() function in captions, keep the existing captions and just shift scene starts.
Author scene boundaries in edited-time — NEVER mix original-time and edited-time anchors in the same file. See "Audio-sync protocol" below.
Build the composition scaffold (4 layers: ambient-bg, seam-treatment, captions, face) — see "Composition scaffold" below.
Author scenes with LOCAL offsets relative to each scene's data-start. Each scene is its own sub-composition under compositions/scene<N>-<label>.html.
Lint → draft render → word-exact frame verification → final render. This is the verification gate. Never skip step 3 (frame verification).
Composition scaffold (the 4 always-on layers)
Every short-form vertical has these four sub-compositions under compositions/, loaded on shared tracks: