refactor(agent): align 'Agent' naming to 'AI/LLM' to match current implementation

- locales/en.json: 'Enrich Metadata (Agent)' -> 'Enrich Metadata (AI)'
- Rename SKILL.md -> prompt.md with backward compat in skill_registry.py
- JS context menu action IDs: enrich-hf-agent -> enrich-hf-llm
- HTML template data-action attributes synced to match
- docstring cleanup: 'agent skill' -> 'skill pipeline' / 'feature'

py/services/agent/skills/enrich_hf_metadata/md_to_html.py

@@ -1,8 +1,8 @@
 """Inline markdown-to-HTML converter and LLM-prompt cleaner for HF README content.
 
 No external dependencies.  Strips YAML frontmatter, ``<Gallery />`` sections,
-badge images, and HTML comments before rendering.  Only used by the
-``enrich_hf_metadata`` skill.
+badge images, and HTML comments before rendering.  Used by the
+``enrich_hf_metadata`` feature.
 
 Also provides :func:`clean_readme_for_llm` which pre-processes the raw README
 before it is injected into the LLM prompt, removing content that has zero value