fix(skills): drop raw_content to avoid doubling skill payload

skill_view response went to the model verbatim; duplicating the SKILL.md
body as raw_content on every tool call added token cost with no agent-facing
benefit. Remove the field and update tests to assert on content only.

The slash/preload caller (agent/skill_commands.py) already falls back to
content when raw_content is absent, and it calls skill_view(preprocess=False)
anyway, so content is already unrendered on that path.

tools/skills_tool.py

@@ -835,7 +835,6 @@ def _serve_plugin_skill(
             "success": True,
             "name": f"{namespace}:{bare}",
             "content": f"{banner}{rendered_content}" if banner else rendered_content,
-            "raw_content": content,
             "description": description,
             "linked_files": None,
             "readiness_status": SkillReadinessStatus.AVAILABLE.value,
@@ -1335,7 +1334,6 @@ def skill_view(
             "tags": tags,
             "related_skills": related_skills,
             "content": rendered_content,
-            "raw_content": content,
             "path": rel_path,
             "skill_dir": str(skill_dir) if skill_dir else None,
             "linked_files": linked_files if linked_files else None,