consistent-character-video
Skill0 starsChanged 5 months agoNo licenceView on GitHub
Step 3. Writes copy-paste-ready image-to-video prompts that ANIMATE a consistent, realistic AI character across multiple clips, using the character's reference images (front + angles, or a character sheet) as input. Covers two models with completely different grammars: Kling 3.0 (the right tool for consistent HUMAN characters — image-to-video, start + end frame chaining) and Seedance 2.0 (6-part cinematic formula, single-shot and timeline). Crucially encodes a hard real-world limit: Seedance 2.0 BLOCKS realistic human face references, so for a recurring human character you lean on Kling. Use this skill whenever the user wants to "animate my character", "turn my reference into a video", "image to video", "Kling prompt", "Seedance prompt", "make my AI character talk/walk/move", "consistent video of my character", or "multiple clips same character". Outputs prompts plus the reference-image setup, or generates the clips directly if a Higgsfield/video MCP is connected.
In this repository13 other files it gives its agents.
- character-angle-sheetSkill
- character-concept-builderSkill
- check-limitsSkill
- graphifySkill
- handoffSkill
- higgsfield-studioSkill
- llm-councilSkill
- podcast-content-producerSkill
- short-form-content-writerSkill
- stop-slopSkill
- ui-ux-pro-maxSkill
- video-prompt-builderSkill
- visual-promptSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.