'Stitch this' opinion: 5 seconds of their claim, 25 seconds of your answer
The stitch format in which a short borrowed clip sets up a claim and you answer with one argument and one demonstration. The prompt picks the 5 seconds to keep and bans the straw man.
Write a stitch script replying to a clip that claims {the claim} about {topic}. The format works because the borrowed clip is the hook (the claim is stated by someone the viewer may already have seen) and the viewer stays for the answer. Rules: quote the clip fairly (the 5 seconds where the claim is clearest, not the weakest moment), answer with ONE argument, and show the argument rather than assert it. Structure (30 s, 9:16): - 0-5 s THE CLIP: the 5 seconds of the source where the claim is said. On-screen over it: nothing; let it play. - 5-8 s THE TURN: me, face to camera, my position in one sentence. On-screen: the position in 4 words. - 8-22 s THE ARGUMENT: one reason, with a demonstration (a screen, an object, two photos, a number I measured). Three spoken lines max, 12 words each. - 22-27 s THE CONCESSION: the case where the original claim is right, one sentence. This is what makes the reply shareable rather than argued with. - 27-30 s CLOSE: 'Stitch this if you disagree.' No download ask; if my demonstration used a product it was on screen. Word budget: 60-70 words at 165 wpm for my part. On-screen: the position at 5-8 s, one label during the demonstration, nothing over the source clip. Return: which 5 seconds of the source to keep (timestamps and the words), then a table (time, what is on screen, spoken line, on-screen text), then the argument in one line for the caption. Source transcript with timestamps: {transcript} My position: {position} What I can show: {the demonstration I have}
In Claude Code, paste the prompt as a message.
Example
Claim: ‘You need a DSLR to sell anything handmade online.’ Position: a phone by a window is enough for a listing. Demonstration: the same mug shot both ways.
Keep: 0:04-0:09 of the source, ‘if you’re shooting on a phone, nobody is taking your shop seriously.’
| Time | On screen | Spoken line | On-screen text |
|---|---|---|---|
| 0-5 s | Source clip | (source audio) | |
| 5-8 s | Me, kitchen, phone in hand | A phone by a window is enough for a listing photo. | PHONE IS ENOUGH |
| 8-13 s | Same mug, two photos side by side | Left is a camera with a lens that costs more than the mug. Right is my phone. | SAME MUG · SAME WINDOW |
| 13-18 s | Zoom into both | At listing size you can’t tell. At phone size, nobody can. | LISTING SIZE |
| 18-22 s | Thumb cuts the background out, white | Background off, white on. That took longer to say than to do. | |
| 22-27 s | Me | If you’re printing a catalogue or shooting glass with reflections, yes, get the camera. | WHEN THE CAMERA WINS |
| 27-30 s | Me | Stitch this if you disagree. |
Caption: At listing size a phone by a window and a camera with a lens show the same mug. The camera wins for print and for glass.
Tips
- Keep the strongest 5 seconds of the source, not the silliest. A reply to a straw man gets replied to.
- The concession at 22-27 s is not politeness; it is what makes the viewer believe the first 22 seconds.
| works with | Claude Code: Runs as a skill or a prompt in the terminal; can read your files and write the result. · Claude: Paste into claude.ai or the Claude app. · ChatGPT: Paste into ChatGPT; works with any GPT model. · Any LLM: Model-agnostic: Gemini, Mistral, a local model. |
| cost | Free. No API, no key. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-01 |
| for agents | stitch-this-opinion-format.md |
Related
Reaction / duet style: respond to a clip in 30 seconds without stealing it
The split-screen or picture-in-picture response format, written so the reaction adds a fact or a demonstration instead of a face. The prompt plans the pause points and what you say at each.
Countdown listicle: 5 items in 45 seconds, best one last, numbers on screen
The ranked list format, with the rule that makes it hold: each item gets shorter as the count drops and number one gets the longest shot. The prompt returns script, text plan and the caption list.
POV: a 15-second first-person scene with the text doing the storytelling
The POV format in which the camera is the viewer's eyes and one line of on-screen text sets the situation; the prompt writes the text, the single action and the beat where it turns.
Before/after: the 20-second reveal with the 'after' shown first
The before/after format with the twist that keeps it from being skipped: open on the finished result, then show how bad it was, then the change. The prompt returns a timed script and text plan.
Day in the life: a 45-second cut from real footage with one through-line
A recipe for the vlog-style day that keeps working because the viewer waits for one promised payoff; the prompt turns your clip list into a timed script with text overlays.
Founder explainer: 'I built this because' in 40 seconds, to camera, one problem
The founder-to-camera format that converts because it names the specific moment the problem became unbearable, then shows the product once. The prompt bans origin-story clichés and budgets the words.