From scaffolding
Searches vector memory for prior insights mid-task using semantic_search and semantic_recall tools. Activates when debugging, encountering unfamiliar patterns, or making design decisions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/scaffolding:semantic-memory-mcpThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You have access to three MCP tools for semantic memory. Use them PROACTIVELY -- do not wait to be asked.
You have access to three MCP tools for semantic memory. Use them PROACTIVELY -- do not wait to be asked.
| Tool | Purpose | All agents | Write agents only |
|---|---|---|---|
semantic_search | Find memories by similarity query | Yes | -- |
semantic_recall | Get formatted memories for current context | Yes | -- |
semantic_store | Store a new memory with embedding | -- | Yes |
Write agents: developer, architect, debugger, analyst, researcher, reviewer, optimizer. Read-only agents: tech-writer, devops, gitops.
Uwaga: Jesli ten skill jest aktywny w repozytorium bez MCP server
semantic-memory, pomin te instrukcje. Agent bez dostepu domcp__semantic-memory__*toolow powinien po prostu pracowac bez pamieci semantycznej -- file-based fallback w.scaffolding/agent-memory/wciaz dziala.
semantic_search when you want structured results with metadatasemantic_recall when you want a quick formatted summaryproject_id so results are scoped to the current repository.
The memory-project-id SessionStart hook injects the value to use (a
scaffold:<hash> derived from the git remote); pass that exact value to
every semantic_search / semantic_recall / semantic_store call. If no
project_id is provided in session context, the backend uses a shared
default namespace.semantic_recall(context="SQLAlchemy async session event loop issues", project_id="scaffold:ab12cd34ef56")
semantic_search(query="deployment nginx proxy configuration gotchas", project_id="scaffold:ab12cd34ef56")
semantic_search(query="Redis task queue timeout handling", project_id="scaffold:ab12cd34ef56", agent_name="debugger")
tags for filtering (3-5 tags)content_type correctly: learning, error, pattern, or decisionsemantic_store(
content="TextBuffer in step event pipeline buffers assistant_text and thinking events but passes all others through immediately. If you add a new bufferable event type, you must add it to TextBuffer._BUFFERED_TYPES or events will be lost silently.",
agent_name="debugger",
content_type="pattern",
tags=["step-events", "text-buffer", "pipeline"]
)
semantic_store(
content="When creating async SQLAlchemy engine in a worker thread, you must create a NEW engine+session bound to that thread's event loop. Reusing the module-level async_session_maker causes 'attached to a different loop' errors.",
agent_name="developer",
content_type="error",
tags=["sqlalchemy", "async", "threading", "event-loop"]
)
Before storing, self-check:
If all four are YES, store it. Otherwise, skip or use file-based conversation memory.
npx claudepluginhub komluk/scaffolding --plugin scaffoldingStores reusable insights as vector-embedded entries for cosine-similarity recall across sessions. Use when an agent discovers patterns, decisions, or gotchas worth retrieving later.
Guides agents to deliberately search or skip memory using dejavu MCP tools, with query strategies and metadata filters for decisions, user preferences, conventions, and anti-patterns.
Integrates sage-memory for persistent knowledge across sessions via MCP tools or file fallback. Automates recall at session/task starts and storage during work.