tfcbot/agent-video-team · Archived

prompt-writer

>- Write concise Kling 3.0 Motion Control prompts for Vidjutsu clone videos. Use when a staged source and identity-locked starting image define the motion, framing, and character, and the caller needs an optional motion prompt.

First seen Apr 12, 2026

Installation

$ npx skills add tfcbot/agent-video-team --skill prompt-writer

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from tfcbot/agent-video-team · top by installs.

npx skills add tfcbot/agent-video-team

Browse all from tfcbot/agent-video-team

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

License LICENSE
Default branch main
Open issues 0
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,797 B
  • docs SUMMARY.md 245 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 2 installs

SKILL.md

Prompt Writer

Write one concise optional prompt for Kling Motion Control. The source video already defines motion, timing, camera, and sound; the starting image already defines identity and initial composition.

Inputs

Collect the intended tone, any motion behavior that must be preserved, any scene-specific exclusions, and the requested overlay or caption text. Do not place overlay text in the generation prompt; add it in post-production.

Prompt structure

Use 30–60 words:

Preserve the source performance, timing, camera motion, and original sound.
Maintain the starting-image identity and wardrobe throughout. [Optional
scene-specific continuity or expression guidance.] Avoid identity drift,
warping, extra limbs, broken hands, and added on-screen text.

Rules

  • Describe only constraints that improve motion-control fidelity.
  • Do not duplicate the character description; the starting image carries it.
  • Do not request a different aspect ratio, resolution, duration, sound mode,

provider, or model. Those are not prompt parameters.

  • Do not provide alternate-model, upstream-provider, extra request-field, or

upstream-task instructions.

  • Keep the source soundtrack unless the user later performs a clearly labeled

external edit. Vidjutsu does not replace audio tracks.

Output

Return the optional prompt string plus any post-production overlay/caption text as separate fields. If the default motion-control behavior is sufficient, recommend omitting prompt entirely.