follow the skill spec: references/ not refs/, and namespaced subskill names

- refs/ -> references/, the folder name the Agent Skills spec uses and the one
  Hermes skips when it walks for nested skills.
- rl and pinn declared name: rl and name: pinn, which are global names in a flat
  skill namespace. Now ml-debug-rl and ml-debug-pinn. They also called themselves
  sub-skills of 'ml-debugging', which is not this skill's name.
- Drop the dead link to SKILL_old.md. It moved into gitignored slop/, so the link
  was broken for anyone who cloned.
- Route references/llm_judge_litreview.md, the one reference SKILL.md never named.
- Description leads with the trigger situations. Hermes truncates it to 57 chars.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

rl/SKILL.md

@@ -1,6 +1,6 @@
 ---
-name: rl
-description: "RL-specific debugging: probe environments, reward engineering, diagnostics, hyperparameter defaults, and reference implementations. Sub-skill of ml-debugging. Use when debugging reinforcement learning systems."
+name: ml-debug-rl
+description: "RL-specific debugging: probe environments, reward engineering, diagnostics, hyperparameter defaults, and reference implementations. Sub-skill of the ml-debug skill. Use when debugging reinforcement learning systems."
 ---
 
 # RL-Specific Debugging