Stats
Actions
Tags
How this skill is triggered — by the user, by Claude, or both
Slash command
/semantic-memory:rememberThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
User invoked with: **$ARGUMENTS**
User invoked with: $ARGUMENTS
Store a piece of text in LogosDB for retrieval in future sessions.
Parse the arguments:
--namespace=<name> or -n <name> sets the collection (default: global).Call the logosdb_index MCP tool with the text and namespace.
The global namespace is shared across all projects and sessions — use it for cross-cutting facts, preferences, decisions, or anything worth remembering in future work.
Use a project-specific namespace (e.g. code, decisions) when the memory is only relevant to this project.
Respond with one line only:
Remembered → '<namespace>'
On tool error, surface the server's Error: message on a single line, unchanged.
/remember always prefer functional components over class components
/remember --namespace=decisions use Postgres not SQLite for this project
/remember -n global my preferred tab size is 2 spaces
skills/semantic-memory/SKILL.md — global memory, thinking traces, session auto-store.
Searches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.
npx claudepluginhub jose-compu/claude-code-semantic-memory --plugin semantic-memory