diff --git a/easy-media-track-gate/references/workflow_wiring.md b/easy-media-track-gate/references/workflow_wiring.md index fceea4c..0cf7bc8 100644 --- a/easy-media-track-gate/references/workflow_wiring.md +++ b/easy-media-track-gate/references/workflow_wiring.md @@ -98,3 +98,29 @@ It contains no LLM node; prompts come from the timeline JSON. This is the pack's agent-driven setup: an external LLM (agent) writes the whole `track_data`, then one run renders it. The pack even ships `skills/easy-media-multitrack-workflow` + `patch_workflow.py` for exactly that flow (our SKILL.md step 5B). + +## The built-in LLM system prompts (published, not locked) + +The rewrite-LLM contract ships in the open in the pack: +`utils/prompt_builder.py` — `MINIMAX_BASE_PROMPT` (~15.7 KB, "Video Prompt Writing +Guide (T2VA / I2VA / FL2VA / L2VA)") and `MINIMAX_REF_PROMPT` (~23.5 KB, "Full- +Reference Mode Rewrite Output Format Guide" — six-section rewrite with +`` / `` / `