Stats
Actions
Tags
How this skill is triggered — by the user, by Claude, or both
Slash command
/semantic-memory:searchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
User invoked with: **$ARGUMENTS**
User invoked with: $ARGUMENTS
Search LogosDB for semantically similar content and respond concisely (file paths + scores only — never echo or paraphrase the full chunk text in the slash-command reply).
Parse the arguments:
--namespace=<name> or -n <name> sets the collection (default: code).--top-k=<n> or -k <n> sets the number of results (default: 5, hard cap at 8 for slash use — keep output small).ts_from / ts_to:
--from-ts=<iso> or --ts-from=<iso> → pass as ts_from--to-ts=<iso> or --ts-to=<iso> → pass as ts_to--candidate-k=<n> → pass as candidate_k when using a timestamp window (default: 10 × top_k).Call the logosdb_search MCP tool with the query, namespace, top_k, and (when bounds are set) ts_from, ts_to, and candidate_k if provided.
Respond with only the following block. Do not wrap it in fences, do not include the raw tool JSON, and do not paste chunk text.
Searching '{namespace}' (top_k={top_k}{ts_note}): {N} matches
1. {file_path} (score: {score})
2. {file_path} (score: {score})
...
{file_path} is extracted from the [file:...] prefix in the result text.{ts_note} is , ts=[{ts_from}..{ts_to}] when either bound is set, else empty.No matches found in '{namespace}' namespace. — single line, nothing else.When the agent invokes logosdb_search outside of /search (i.e. as part of answering a normal question), it should still:
top_k 3–5.src/foo.ts) in the final prose.npx claudepluginhub jose-compu/claude-code-semantic-memory --plugin semantic-memorySearches 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.