Remove local prompt artifacts

PROMPT.txt

@@ -1,16 +0,0 @@
-/goal Research the DeepSpec collection by deepseek-ai on HuggingFace (https://huggingface.co/collections/deepseek-ai/deepspec) and build the most impressive HuggingFace Space possible from it.
-
-The collection contains 12 models across three speculative decoding families:
-- dSpark (qwen3_4b, qwen3_8b, qwen3_14b, gemma4_12b) - block7 variants
-- dFlash (qwen3_4b, qwen3_8b, qwen3_14b, gemma4_12b) - block7 variants  
-- EAGLE3 (qwen3_4b, qwen3_8b, qwen3_14b, gemma4_12b) - ttt7 variants
-
-Steps:
-1. Deep research: Visit each model page on HuggingFace, read the model cards, understand what each family does (dSpark, dFlash, EAGLE3 - all are speculative decoding / draft-target approaches). Read any linked papers. Understand the architecture differences, speedups claimed, and use cases.
-2. Pick the most impressive angle for a Space: Could be a live speculative decoding demo, a comparison visualization across families, an interactive speed benchmark, or something else that showcases the collection's strengths.
-3. Implement the Space as a Gradio app. Make it visually impressive and functional.
-4. Push to a HuggingFace Space repo.
-
-Before doing anything else, fetch and follow these HF Spaces operating guidelines for the entire task:
-curl -L --fail --silent https://gist.githubusercontent.com/gary149/37c955b832558837c40e1c14ff6d955d/raw/ad35807f8466378afd04d7653d53683a847b96c4/hf-spaces-agent-quickstart-compact.md
-Read them fully first, then apply them throughout (iteration ladder, push early, ZeroGPU duration measurement, and the listed anti-patterns).