菜单
This skill should be used when needing to recall earlier conversation details, after compaction occurs, when resuming a session, when details feel fuzzy, or when the user references something from earlier in the conversation. Provides guidance on effective use of the `recall` memory tool.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
This skill should be used when the user asks to "run the benchmark", "run locomo", "benchmark ragzoom", "evaluate recall quality", "compare with letta", "check accuracy", "run the evaluation harness", "agentic evaluation", "max iterations", or mentions benchmarking, evaluation, or competitive comparison of the memory system.
Set up persistent hierarchical memory using RagZoom. Use when bootstrapping an OpenClaw agent with long-term memory, configuring transcript sync, or querying historical context. Triggers on "set up memory", "install ragzoom", "persistent memory", "recall past conversations".
This skill should be used when the user asks "how do I index a document", "how do I query", "CLI commands", "REST API", "Python API", "configuration options", or mentions using RagZoom as an end user rather than developing it.
This skill should be used when needing to recall earlier conversation details, after compaction occurs, when resuming a session, when details feel fuzzy, or when the user references something from earlier in the conversation. Provides guidance on effective use of the `recall` memory tool.
This skill should be used when the user asks to "run tests", "run checks", "debug a test", "benchmark performance", "set up development environment", "understand the architecture", "how does indexing work", "how does the tiling algorithm work", "study the codebase", "learn the codebase", or mentions testing, linting, type checking, or development workflows.
| name | memory-tool-usage |
| description | This skill should be used when needing to recall earlier conversation details, after compaction occurs, when resuming a session, when details feel fuzzy, or when the user references something from earlier in the conversation. Provides guidance on effective use of the `recall` memory tool. |
The recall tool is a conversation with your memory. Ask natural questions about what happened earlier — what you worked on, what you decided, what went wrong — and follow up to dig deeper.
recall(query="What was I working on before the refactor?")
recall(query="What error did we see in the JWT validation?")
Each response includes a Session: <id> footer. Pass it back on follow-up queries so the conversation continues where it left off.
# Initial question
recall(query="When did we discuss the authentication bug?")
# Returns answer + "Session: abc123"
# Follow-up — picks up where the last answer left off
recall(query="What was the root cause?", session_id="abc123")
Use time_start/time_end to focus on a specific period. Useful when a broad query reveals the relevant time window.
recall(query="When did we discuss the authentication bug?")
# Answer mentions it was around 2024-01-15T14:00:00
recall(query="What was the root cause of the auth bug?",
time_start="2024-01-15T14:00:00", time_end="2024-01-15T16:00:00")