Kaio

What an agent can do with the llm-video-engine corpus

gmdkaio/llm-video-engine: Turns an HTML presentation deck into a short animated video summary using C++ in ~1min

• Look up how llm-video-engine implements agent-skills, ai, claude, with answers cited to file and line.
• Reuse a worked example: the commit “Measured motion, faster multi-threaded rendering, native Linux build” (15 files · C, C++).
• Answer from llm-video-engine's real C source instead of memory (AI, prompts and agents).

• Where does llm-video-engine handle “Measured motion, faster multi-threaded rendering, native Linux build”?
• How does llm-video-engine implement agent-skills?
• What does engine do in llm-video-engine?

Search the GitHub repository gmdkaio/llm-video-engine with XERJ (https://hub.xerj.org/corpus/gmdkaio--llm-video-engine).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/gmdkaio/llm-video-engine llm-video-engine && git -C llm-video-engine checkout 69029862458cbe977a32f99b74385a2d4c90b822
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./llm-video-engine --url http://127.0.0.1:9200 --prefix llm-video-engine --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus gmdkaio--llm-video-engine · AI, prompts and agents
Related corpora: xobotyi--cc-foundry-cli, xobotyi--cc-foundry-rust, YahyaLendani/motionbrief-claude-skills, zajalist/hayba
AI search and retrieval with XERJ · Case study: reference coding for agents