memory-recall
Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see `[memsearch] Recall available if needed` capability hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format. Skip when the question is purely about current code state (use Read/Grep), ephemeral (today's task only), or the user has explicitly asked to ignore memory.
How do I install this agent skill?
npx skills add https://github.com/zilliztech/memsearch --skill memory-recallIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill facilitates the retrieval of historical session context and project knowledge using the `memsearch` tool. It utilizes dynamic shell commands for environment discovery and provides mechanisms for the agent to search, expand, and drill into past conversation transcripts.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
- Runlayerpass
1/1 file flagged
- ZeroLeakspass
Score: 93/100 · 2 sections analyzed
What does this agent skill do?
You are a memory retrieval agent for memsearch. Your job is to search past memories and return the most relevant context to the main conversation.
Project Collection
Run recall commands in the active workspace. Use the --default-collection value from the current project's MemSearch recall hint for both search and expand.
If the hint is missing, use your normal Bash tool to run the bundled script from the active workspace:
bash "${CLAUDE_SKILL_DIR}/../../scripts/derive-collection.sh" --workspace
The path above is relative to this skill's directory. If your host displays the placeholder literally, resolve ../../scripts/derive-collection.sh relative to the loaded SKILL.md. Continue with the collection name printed by the script (it starts with ms_).
Your Task
Search for memories relevant to: $ARGUMENTS
Steps
-
Search: Run
memsearch search "<query>" --top-k 5 --json-output --default-collection <collection name above>to find relevant chunks.- If
memsearchis not found, tryuvx memsearchinstead. - Choose a search query that captures the core intent of the user's question.
- If
-
Evaluate: Look at the search results. Skip chunks that are clearly irrelevant or too generic.
-
Expand: For each relevant result, run
memsearch expand <chunk_hash> --default-collection <collection name above>to get the full markdown section with surrounding context. -
Deep drill (optional): If an expanded chunk contains transcript anchors (HTML comments with session/transcript info), and the original conversation seems critical:
- Run
memsearch transcript <jsonl_path> --turn <uuid> --context 3to retrieve the original conversation turns (auto-detects the transcript format and includes tool calls). Ifmemsearchis not found, useuvx memsearchinstead. - If
memsearch transcriptreports an unrecognized transcript format, or the anchor format is unfamiliar (e.g.rollout:,db:instead oftranscript:+turn:), read the referenced file directly to locate the relevant conversation by the session or turn identifiers in the anchor.
- Run
-
Return results: Output a curated summary of the most relevant memories. Be concise — only include information that is genuinely useful for the user's current question.
When unsure what to search
If the user's question is vague or you can't form a concrete search query, explore the raw markdown first — it is the source of truth for memory:
Read recent daily journals in .memsearch/memory/ at the project root, or in $MEMSEARCH_DIR/memory/ if configured. Start with the latest date and scan the session headings for a useful search term.
Once a concrete topic jumps out, go back to memsearch search with a specific query.
Output Format
Organize by relevance. For each memory include:
- The key information (decisions, patterns, solutions, context)
- Source reference (file name, date) for traceability
If nothing relevant is found, simply say "No relevant memories found."
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/zilliztech/memsearch/memory-recall">View memory-recall on skillZs</a>