Simplify the transformation skill

[carlevison]

Simplified cloudinary-transformations into a compact agent playbook that treats Cloudinary docs as the source of truth for exact syntax, current limitations, and costs.

Key changes:

• Reduced the skill from large duplicated reference content to a concise SKILL.md.
• Replaced eight bulky reference files with three focused playbooks:
  - agent-playbook.md
  - debugging-playbook.md
  - cost-and-caching.md
• Preserved core agent guidance: requirement gathering, defaults, validation, debugging order, common footguns, and cost/caching heuristics.
• Added guidance to present transformation parameters in SDK-style alphabetical order within components.
• Validated the skill with quick_validate.py.

[njb90]

One comment but otherwise it is definitely an improvement.

[strausr]

I ran 15 prompts against the new skill (resize, face crop, bg removal, gen fill / 16:9, w_auto, named transforms, baseline strategy, video trim + mute, debugging, g_auto)
First, using only SKILL.md + references, then checking whether the docs-first path (llms.txt) fills the gaps.

Result: path works well (resize, fill crop, overlays, bg removal, f_auto:video, debugging). Without a doc fetch, several common cases were partial or failed: face-focused crops (no g_face), gen fill, w_auto + Client Hints setup, named/baseline URL shape, video trim, and invalid g_auto + c_scale.

Left some comments on where I found some issues.