Three caption variants plus hashtags, with per-platform length limits
An agent prompt that writes three captions (short, story, question) and a hashtag set per platform, counting characters and hashtags against limits you paste in from today's upload form.
Write captions for the video described below, for these platforms: {TikTok, Reels, Shorts, LinkedIn}. Limits to respect (parameters; I checked them against the upload forms today): {TikTok: caption max 4000 characters, 3-5 hashtags; Reels: caption max 2200 characters, 30 hashtags max, use 3-5; Shorts: title max 100 characters, description max 5000, 2-3 hashtags; LinkedIn: post max 3000 characters, 3-5 hashtags, first 2 lines visible before 'see more'}. For each platform, three variants: A. SHORT: one line, max 80 characters, the hook of the video in text form. B. STORY: 2-4 short lines, what happened and the one takeaway; for LinkedIn, the first line must stand alone before the fold. C. QUESTION: one line that asks the viewer something they can answer in a comment, max 100 characters. Then hashtags per platform: the stated count, mixed as 1 broad, 2 topic, 1-2 niche; no hashtag that is a brand I do not own; lowercase; no spaces. Output per platform: the three variants with their character counts, the hashtag line with its count, and a one-line note if any limit was close. Rules: no emoji unless the platform list says so; no 'link in bio' unless I give a link; numbers and names exactly as in the video; nothing claimed that the video does not show. Video: {one-paragraph description, the hook line, the CTA}
In Claude Code, paste the prompt as a message.
Steps
- Open each platform's upload form and check the current caption and hashtag limits; paste them into the limits line. They change, and the agent's memory of them is stale.
- Pick one variant per platform; a different variant per platform costs nothing and tells you which kind of caption your audience answers.
- Keep the chosen caption and hashtags in a text file beside the video with the posting date.
Tips
- The question variant is the one that gets replies; the short variant is the one that gets saves. Which you want depends on the video.
- On LinkedIn the first line is the whole caption for most readers. Put the number there.
| 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 | caption-variants-hashtags-per-platform-prompt.md |
Related
Hook text on screen: a plan for the first three seconds, word by word
A prompt that plans what text appears in the first 3 seconds of a vertical video: the words, the moment each appears, the hold, what the picture does under it. Written so the hook works muted.
Turn a blog post into three short scripts: one claim per video
A prompt that reads a post and returns three 30-45 second scripts, each built on a different claim from the text, with the hook, the proof, the ask and the source sentence for each.
Accessible on-screen text: contrast, the bottom 20 percent, no flashing
A checklist for text that everyone can read, including people watching muted, on a small screen, in sunlight, or with photosensitivity. Eight checks, each with the parameter to test against.
Reading speed for on-screen text and speech: the parameters to check against
How long a text overlay must stay up and how many words a voice can carry per second, given as parameters you measure on yourself, with the formula and the two failure modes: unreadable, and slow.
Turn an article or PRD into a social media pack (/content-gen)
Use when "create content", "write LinkedIn post", "social media pack", "marketing copy", "promotion content", "posts from this article", "repurpose this post", "посты из статьи", or need soc
SRT cleanup: fix names from a glossary, merge short cues, cap line length
An agent prompt that takes a raw speech-to-text SRT and returns one you can publish: names fixed from your glossary, sub-second cues merged, lines wrapped at a character cap, timings untouched.