Merge: skill reorganization + sub-category support

- Sub-category support in prompt_builder.py (backwards-compatible)
- Split mlops (40 skills) into 7 logical sub-categories
- Merged 8 singleton categories into logical parents
- Fixed 2 misplaced skills (code-review, ml-paper-writing)

skills/creative/DESCRIPTION.md

@@ -0,0 +1,3 @@
+---
+description: Creative content generation — ASCII art, hand-drawn style diagrams, and visual design tools.
+---

skills/media/DESCRIPTION.md

@@ -1 +1,3 @@
-Media content extraction and transformation tools — YouTube transcripts, audio, video processing.
+---
+description: Skills for working with media content — YouTube transcripts, GIF search, music generation, and audio visualization.
+---

skills/mlops/cloud/DESCRIPTION.md

@@ -0,0 +1,3 @@
+---
+description: GPU cloud providers and serverless compute platforms for ML workloads.
+---

skills/mlops/evaluation/DESCRIPTION.md

@@ -0,0 +1,3 @@
+---
+description: Model evaluation benchmarks, experiment tracking, data curation, tokenizers, and interpretability tools.
+---

skills/mlops/inference/DESCRIPTION.md

@@ -0,0 +1,3 @@
+---
+description: Model serving, quantization (GGUF/GPTQ), structured output, inference optimization, and model surgery tools for deploying and running LLMs.
+---

skills/mlops/models/DESCRIPTION.md

@@ -0,0 +1,3 @@
+---
+description: Specific model architectures and tools — computer vision (CLIP, SAM, Stable Diffusion), speech (Whisper), audio generation (AudioCraft), and multimodal models (LLaVA).
+---

skills/mlops/research/DESCRIPTION.md

@@ -0,0 +1,3 @@
+---
+description: ML research frameworks for building and optimizing AI systems with declarative programming.
+---

skills/mlops/training/DESCRIPTION.md

@@ -0,0 +1,3 @@
+---
+description: Fine-tuning, RLHF/DPO/GRPO training, distributed training frameworks, and optimization tools for training LLMs and other models.
+---