feat(skill-catalog-subscription): synced catalog + HTTP sync + MCP tools

Consumes the external Subscription Platform as source of truth for skill
content; reuses skills_learning domain models (extended with KnowledgeSkill)
and workflow.skill_exec resolver. HTTP/MCP deps land in api/ per
CONSTITUTION.md; synced skills use a physically separate SQLite file
(tasks/skills.sqlite3) to preserve the skill-authoring capability boundary.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

skills_learning/__init__.py

@@ -1,12 +1,19 @@
 """Local skill learning from completed task timelines."""
 
 from skills_learning.config import SkillAuthoringConfig, load_config
-from skills_learning.models import FlowStep, FlowTemplateSkill, Skill, SkillMetadata
+from skills_learning.models import (
+    FlowStep,
+    FlowTemplateSkill,
+    KnowledgeSkill,
+    Skill,
+    SkillMetadata,
+)
 from skills_learning.store import SkillStore, get_default_store
 
 __all__ = [
     "FlowStep",
     "FlowTemplateSkill",
+    "KnowledgeSkill",
     "Skill",
     "SkillAuthoringConfig",
     "SkillMetadata",

skills_learning/models.py

@@ -166,6 +166,27 @@ class FlowTemplateSkill(Skill):
         )
 
 
+@dataclass(frozen=True)
+class KnowledgeSkill(Skill):
+    content: str = ""
+
+    def to_dict(self) -> dict[str, Any]:
+        return {
+            **self.metadata.to_dict(),
+            "content": self.content,
+        }
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "KnowledgeSkill":
+        return cls(
+            metadata=SkillMetadata.from_dict(data),
+            content=str(data.get("content") or ""),
+        )
+
+    def with_metadata(self, **changes: Any) -> "KnowledgeSkill":
+        return replace(self, metadata=replace(self.metadata, **changes))
+
+
 def skill_embedding_text(skill: FlowTemplateSkill) -> str:
     goal = skill.originating_goal or ""
     return f"{skill.name}: {skill.description}\nOriginal goal: {goal}"