From awareness-memory
Searches Awareness memory for past code implementations, architectural decisions, and relevant context using semantic/keyword queries via MCP tools or HTTP API.
How this skill is triggered — by the user, by Claude, or both
Slash command
/awareness-memory:recallThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Search Awareness Memory for relevant context.
Search Awareness Memory for relevant context.
Query: $ARGUMENTS
Try MCP tools first (awareness_recall).
If MCP tools are NOT available, use Bash to call the local daemon HTTP API directly:
# awareness_recall (summary)
curl -s -X POST http://localhost:37800/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"awareness_recall","arguments":{"semantic_query":"...","keyword_query":"...","detail":"summary","limit":10}}}'
# awareness_recall (full, with specific IDs)
curl -s -X POST http://localhost:37800/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"awareness_recall","arguments":{"semantic_query":"...","detail":"full","ids":["id1","id2"]}}}'
The response is JSON-RPC: result.content[0].text contains the tool output as JSON string.
REWRITE the user query:
Phase 1 — Lightweight index:
Call awareness_recall with:
Phase 2 — Expand selected items (only when needed):
Call awareness_recall again with detail: "full" and ids: [relevant IDs from Phase 1].
Skip if summaries already answer the question.
Present results clearly:
Rules:
npx claudepluginhub edwin-hao-ai/awareness-sdk --plugin awareness-memoryChecks memory before code exploration when answering questions about code, architecture, or patterns. Saves time by recalling past knowledge.
Searches stored memories and decisions using MCP tools to answer questions about past learnings, architectural choices, patterns, and project context like 'what testing framework did we decide on?' or 'ESM import issues?'
Implements 3-layer memory search workflow to recall past work, decisions, errors, and project history token-efficiently via layered functions.