CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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

  1. Search: Run memsearch search "<query>" --top-k 5 --json-output --default-collection <collection name above> to find relevant chunks.

    • If memsearch is not found, try uvx memsearch instead.
    • Choose a search query that captures the core intent of the user's question.
  2. Evaluate: Look at the search results. Skip chunks that are clearly irrelevant or too generic.

  3. Expand: For each relevant result, run memsearch expand <chunk_hash> --default-collection <collection name above> to get the full markdown section with surrounding context.

  4. 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 3 to retrieve the original conversation turns (auto-detects the transcript format and includes tool calls). If memsearch is not found, use uvx memsearch instead.
    • If memsearch transcript reports an unrecognized transcript format, or the anchor format is unfamiliar (e.g. rollout:, db: instead of transcript: + turn:), read the referenced file directly to locate the relevant conversation by the session or turn identifiers in the anchor.
  5. 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."

Repository

zilliztech/memsearch

Path

plugins/claude-code/skills/memory-recall/SKILL.md

Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.