semantic-memory-storelisted

# Semantic Memory Store Store knowledge as vector-embedded entries in an optional semantic memory service. When the service is available, entries are automatically embedded and retrievable via cosine similarity search by any agent in future sessions. This skill is **optional**. If no semantic memory service is configured, agents should degrade gracefully and rely on the file-based memory described in the `agent-memory` skill. ## When to Use - Agent discovers a non-obvious insight worth preserving beyond file-based memory - A debugging session reveals a root cause that would help future agents - An architectural decision is made that affects multiple components - A pattern or anti-pattern is confirmed through implementation experience - Cross-project knowledge that does not belong in a single file ## When NOT to Use - Temporary task context (use conversation memory in `.scaffolding/conversations/`) - Information already in CLAUDE.md, docs/, or KNOWLEDGE.md - Large code snippets (use file-based memory instead) - Speculative or unverified conclusions ## Availability Check Before attempting to store or search, verify a semantic memory backend is reachable: - If `mcp__semantic-memory__*` MCP tools are available, use those (see the `semantic-memory-mcp` skill). - If an optional backend service is configured for the project, use its documented interface. - If neither is available, **skip this skill entirely** and use file-based memory from the `agent-memory` skill. Do not b