memory-recall

分类: 开发与编程 | 上传者: zilliztech | 下载: 0 | 版本: v1.0（最新）

通过 memsearch 搜索并回忆过去会话中的相关记忆。当用户的问题可以从历史背景、过去的决策、调试笔记、以前的对话或项目知识中受益时使用——尤其是像“我对 X 做了什么决定”、“我们为什么做 Y”或“我以前见过这个”这样的问题。当您看到通过 SessionStart 或 UserPromptSubmit 注入的“[memsearch] Memory available”提示时也可使用。典型流程：搜索 3-5 个块，扩展最相关的内容，可选地通过锚格式深入钻取原始转录本。当问题纯粹是关于当前代码状态（使用 Read/Grep）、短暂（仅限今天的任务）或用户明确要求忽略内存时，请跳过。

更新日志: Source: GitHub https://github.com/zilliztech/memsearch

目录结构

当前层级: tree/main/plugins/claude-code/skills/memory-recall/

📄 SKILL.md 3.3 KB

SKILL.md

---
name: memory-recall
description: "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] Memory available` 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."
context: fork
allowed-tools: Bash
---

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

Collection: !`bash -c 'root=$(git rev-parse --show-toplevel 2>/dev/null || true); if [ -n "$root" ]; then bash "${CLAUDE_PLUGIN_ROOT}/scripts/derive-collection.sh" "$root"; else bash "${CLAUDE_PLUGIN_ROOT}/scripts/derive-collection.sh"; fi'`

## Your Task

Search for memories relevant to: $ARGUMENTS

## Steps

1. **Search**: Run `memsearch search "<query>" --top-k 5 --json-output --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> --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 `python3 ${CLAUDE_PLUGIN_ROOT}/transcript.py <jsonl_path> --turn <uuid> --context 3` to retrieve the original conversation turns.
   - If the anchor format is unfamiliar (e.g. `rollout:`, `db:` instead of `transcript:` + `turn:`), try reading the referenced file directly to explore its structure and 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:

- `ls -t $(git rev-parse --show-toplevel)/.memsearch/memory/ | head -10` — recent daily logs
- `grep -h "^## " $(git rev-parse --show-toplevel)/.memsearch/memory/*.md | sort -u | tail -40` — session headings across all days
- `cat $(git rev-parse --show-toplevel)/.memsearch/memory/<YYYY-MM-DD>.md` — read a specific day

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."

登录后下载/点赞/收藏 ❤ 1.5K | ★ 0

memory-recall

目录结构

SKILL.md

举报内容

提示