Menü
Use when an agent needs a file-first ReMe workspace as the source of durable setup facts, stable preferences, or reusable daily decision records.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | reme-personal-memory |
| description | Use when an agent needs a file-first ReMe workspace as the source of durable setup facts, stable preferences, or reusable daily decision records. |
This is the legacy-compatible root shim for the repository.
The canonical implementation of this skill lives at skills/reme-personal-memory/. Use that version when your host can load multiple skills from one repository.
Use this root shim when your installer loads only the repository root and you still need the original file-first reme-personal-memory behavior.
Use it to:
Do not use it for vector-backed memory, HTTP or MCP startup, Tool Memory, or Working Memory.
The compatibility contract is unchanged:
SETUP.md stores stable entrypoints, startup methods, integration topology, and boundary conditionsMEMORY.md stores long-lived preferences, standing rules, and durable factsmemory/YYYY-MM-DD.md stores daily actions, validations, incidents, and decisionsRead order:
SETUP.mdMEMORY.mdmemory/YYYY-MM-DD.mdWrite policy:
SETUP.mdMEMORY.mdmemory/YYYY-MM-DD.mdskills/reme-personal-memoryskills/reme-personal-memory as the canonical source for future editsUse when an agent needs a file-first ReMe workspace as the source of durable setup facts, stable preferences, or reusable daily decision records.
Use when you need vector-backed personal memory in ReMe, including preference extraction, personal-memory retrieval, or PersonalMemoryService and ReMeApp integration.
Use when integrating ReMeLight into an agent loop and you need file-based context checks, compaction, tool-result offload, semantic search, or session memory.
Use when starting ReMe over HTTP or MCP, or when embedding ReMeApp directly into an application without changing memory-type semantics.
Use when you need ReMe to learn from prior task trajectories, extract reusable success or failure patterns, or retrieve procedural memory for similar tasks.
Use when many tools look similar and you need ReMe to learn historical tool quality, parameter patterns, or retrieval guidance for future tool selection.