claude-remember · diff
git:20260725.e280791 to git:20260925.32ce6c0
76 added, 46 removed. Audit A to A.
---
name: claude-remember
- description: Review auto-memory entries and propose promotions across memory layers (project-level, user-level, shared). Also detects outdated, conflicting, and duplicate entries. Adaptable to any AI agent's memory hierarchy.
+ description: "Review auto-memory entries and produce a report of proposed promotions across the memory hierarchy (project-level, user-level, daily log, shared), plus cleanup of duplicate, outdated, and conflicting entries. Adaptable to any AI agent's memory layout. Use when the user wants to review, organize, or promote their auto-memory entries. Trigger phrases: \"review my memories\", \"organize memories\", \"promote to MEMORY.md\", \"clean up memories\", \"memory review\", \"check for duplicate memories\", \"what should go in MEMORY.md\", 整理记忆, 检查记忆, 记忆回顾, 清理记忆, 提升到 MEMORY.md。用法：/claude-remember [optional focus area or specific memory to review]"
allowed-tools: ["Read", "Write", "Edit", "Glob", "Grep", "AskUserQuestion"]
- when_to_use: |
- Use when the user wants to review, organize, or promote their auto-memory entries.
- Trigger phrases: "review my memories", "organize memories", "promote to MEMORY.md",
- "clean up memories", "memory review", "check for duplicate memories",
- "what should go in MEMORY.md".
argument-hint: "[optional focus area or specific memory to review]"
---
# Memory Review
- ## Goal
- Review the user's memory landscape and produce a clear report of proposed changes, grouped by action type. Do NOT apply changes — present proposals for user approval.
+ ## Purpose
- ## Memory File Locations
+ Review the user's memory landscape and produce a clear report of proposed changes, grouped by
+ action type. The skill never applies changes by itself — it presents proposals for user approval.
+ It also surfaces duplicates, outdated entries, and cross-layer conflicts.
- AI agent 的记忆系统通常分多个层级。执行本技能前，先确认当前运行环境的记忆层级：
+ ## When to Use
- 1. **项目级记忆**: 存储于项目根目录下的记忆文件（如 `MEMORY.md` / `CLAUDE.md` / `.cursorrules` 等），所有协作者共享
- 2. **用户级记忆**: 存储于用户主目录下的全局记忆文件，跨项目共享个人偏好
- 3. **运行日报**: 每日追加的工作日志（如 `YYYY-MM-DD.md`）
- 4. **自动记忆/云记忆**: 系统自动维护的长期记忆（通常不可手动修改）
+ - The user wants to review, organize, or promote their auto-memory entries.
+ - The user asks what should be promoted into `MEMORY.md`, or where an entry belongs.
+ - The user suspects duplicate, stale, or contradictory memory entries.
+ - Trigger phrases: "review my memories", "organize memories", "promote to MEMORY.md",
+ "clean up memories", "memory review", "check for duplicate memories",
+ "what should go in MEMORY.md", 整理记忆, 检查记忆, 记忆回顾, 清理记忆, 提升到 MEMORY.md。
- > **执行前先扫描**: 使用 Glob/Grep 工具确认实际存在的记忆文件路径，不要假设固定的文件命名。
+ ## When NOT to Use
- ## Steps
+ - The user just wants something written to a memory file now -> write it directly with Edit/Write;
+ the review-and-propose flow is unnecessary overhead.
+ - The user wants to change a tool's own settings (editor theme, IDE keybindings) -> that is not
+ assistant memory; direct them to the tool's configuration.
+ - The target file does not exist and the user only wants it created -> create it, then optionally
+ offer the review.
- ### 1. Gather all memory layers
+ ## Workflow
- Read all existing memory files from the locations above. Your auto-memory content is already in your system prompt — review it there. Note which team memory sections exist, if any.
+ Each step has a success criterion; do not advance until it is met.
- **Success criteria**: You have the contents of all memory layers and can compare them.
+ 1. **Gather all memory layers.** Read every existing memory file in the layers above. The
+ auto-memory content is already in your system prompt — review it there. Note which team memory
+ sections exist, if any. *Success: you hold the contents of all layers and can compare them.*
+ 2. **Classify each auto-memory entry.** For every substantive entry, determine the best
+ destination using the table in `## Decision Rules`.
+ *Success: each entry has a proposed destination or is flagged as ambiguous.*
+ 3. **Identify cleanup opportunities.** Scan across all layers for duplicates (already captured in
+ project/user memory), outdated entries (contradicted by newer auto-memory), and conflicts
+ (contradictions between any two layers, noting which is more recent).
+ *Success: all cross-layer issues identified.*
+ 4. **Present the report** grouped by action type, per `## Output`.
+ *Success: the user can approve or reject each proposal individually.*
- ### 2. Classify each auto-memory entry
+ If auto-memory is empty, say so and offer to review existing memory files for cleanup instead.
- For each substantive entry in auto-memory, determine the best destination:
+ ## Decision Rules
+ Destination mapping:
+
| Destination | What belongs there | Examples |
|---|---|---|
| **项目 MEMORY.md** | 项目级约定和规范，所有协作者应遵循 | "用 bun 不用 npm"、"API 路由使用 kebab-case"、"测试命令是 bun test" |
| **用户 MEMORY.md** | 跨项目的用户个人偏好和习惯 | "偏好简洁回复"、"总是解释 trade-off"、"运行测试前不要提交" |
| **项目日报** | 每日工作日志，仅追加 | 当天完成的工作、技术选型、项目约定变更 |
| **保持在自动记忆** | 临时上下文、工作笔记、不明确归属的条目 | 会话特定观察、不确定的模式 |
- **Important distinctions:**
- - 记忆文件存储的是 AI 助手的指令，不包括用户对外部工具的偏好（编辑器主题、IDE 快捷键等）
- - Workflow practices (PR conventions, merge strategies, branch naming) are ambiguous — ask the user whether they're personal or team-wide
- - When unsure, ask rather than guess
+ - Entry's destination is clear -> propose it directly.
+ - Entry is a tool preference (editor theme, IDE shortcuts) -> do NOT promote; not assistant memory.
+ - Entry looks like a workflow practice (PR conventions, merge strategy, branch naming) -> treat as
+ ambiguous and ask the user whether it is personal or team-wide.
+ - Entry contradicts another layer -> propose resolving the older layer, stating which is newer.
+ - Still unsure -> ask via `AskUserQuestion`; do not guess.
+ - Need the layer definitions or the reasoning behind these rules -> read
+ `references/memory-layers.md`.
- **Success criteria**: Each entry has a proposed destination or is flagged as ambiguous.
+ ## Constraints
- ### 3. Identify cleanup opportunities
+ - Present **all** proposals before making any changes.
+ - Do NOT modify files without explicit user approval.
+ - Do NOT create new files unless the target does not exist yet.
+ - Ask about ambiguous entries — never guess a destination.
+ - Use `AskUserQuestion` for clarifications when needed.
+ - "No action needed" is a required conclusion category, not an omission.
- Scan across all layers for:
- - **Duplicates**: Auto-memory entries already captured in project or user memory files → propose removing from auto-memory
- - **Outdated**: Memory entries contradicted by newer auto-memory entries → propose updating the older layer
- - **Conflicts**: Contradictions between any two layers → propose resolution, noting which is more recent
+ ## Verification
- **Success criteria**: All cross-layer issues identified.
+ Before reporting done:
- ### 4. Present the report
+ - [ ] All memory layers present in the environment were actually read.
+ - [ ] Every substantive auto-memory entry has a proposed destination or an ambiguity flag.
+ - [ ] Duplicates, outdated entries, and conflicts were scanned across layers, not just within one.
+ - [ ] No file was modified; only proposals were produced.
+ - [ ] Every proposal is individually approve/reject-able by the user.
- Output a structured report grouped by action type:
- 1. **Promotions** — entries to move, with destination and rationale
- 2. **Cleanup** — duplicates, outdated entries, conflicts to resolve
- 3. **Ambiguous** — entries where you need the user's input on destination
- 4. **No action needed** — brief note on entries that should stay put
+ ## Output
- If auto-memory is empty, say so and offer to review existing memory files for cleanup.
+ A structured report grouped by action type:
- **Success criteria**: User can review and approve/reject each proposal individually.
+ 1. **Promotions** — entries to move, with destination and rationale.
+ 2. **Cleanup** — duplicates, outdated entries, conflicts to resolve.
+ 3. **Ambiguous** — entries needing the user's input on destination.
+ 4. **No action needed** — brief note on entries that should stay put.
- ## Rules
+ - **Outcome**: a review report; no file changes.
+ - **Done when**: the user can review and approve/reject each proposal individually.
+ - **Evidence**: each proposal names the source layer, the target, and the reason; if auto-memory is
+ empty, the report says so explicitly and offers cleanup of existing files.
- - Present ALL proposals before making any changes
- - Do NOT modify files without explicit user approval
- - Do NOT create new files unless the target doesn't exist yet
- - Ask about ambiguous entries — don't guess
- - Use AskUserQuestion for clarifications when needed
+ ## References
+
+ Load only when needed:
+
+ - `references/memory-layers.md` — read when a destination is ambiguous, when the user asks why an
+ entry belongs in one layer rather than another, or when two layers conflict and you need the
+ tie-break rule.