Back to Details

remember

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Remember - Store Learning in Memory

记忆功能 - 将学习内容存储到记忆中

Store a learning, pattern, or decision in the memory system for future recall.
将学到的知识、模式或决策存储到记忆系统中，以便日后调取。

Usage

使用方法

/remember <what you learned>
Or with explicit type:
/remember --type WORKING_SOLUTION <what you learned>
/remember <你学到的内容>
或者指定类型：
/remember --type WORKING_SOLUTION <你学到的内容>

Examples

示例

/remember TypeScript hooks require npm install before they work
/remember --type ARCHITECTURAL_DECISION Session affinity uses terminal PID
/remember --type FAILED_APPROACH Don't use subshell for store_learning command
/remember TypeScript hooks 需要先执行 npm install 才能正常工作
/remember --type ARCHITECTURAL_DECISION 会话亲和性使用终端PID
/remember --type FAILED_APPROACH 不要对 store_learning 命令使用子shell

What It Does

功能说明

  1. Stores the learning in PostgreSQL with BGE embeddings
  2. Auto-detects learning type if not specified
  3. Extracts tags from content
  4. Returns confirmation with ID
  1. 将学习内容存储到带有BGE embeddings的PostgreSQL中
  2. 若未指定类型，自动检测学习内容类型
  3. 从内容中提取标签
  4. 返回带ID的确认信息

Learning Types

学习内容类型

TypeUse For
WORKING_SOLUTION
Fixes, solutions that worked (default)
ARCHITECTURAL_DECISION
Design choices, system structure
CODEBASE_PATTERN
Patterns discovered in code
FAILED_APPROACH
What didn't work
ERROR_FIX
Specific error resolutions
类型适用场景
WORKING_SOLUTION
有效的修复方案、解决办法（默认类型）
ARCHITECTURAL_DECISION
设计选择、系统结构相关决策
CODEBASE_PATTERN
在代码中发现的模式
FAILED_APPROACH
无效的尝试方案
ERROR_FIX
特定错误的解决方法

Execution

执行逻辑

When this skill is invoked, run:
bash
cd $CLAUDE_OPC_DIR && PYTHONPATH=. uv run python scripts/core/store_learning.py \
  --session-id "manual-$(date +%Y%m%d-%H%M)" \
  --type <TYPE or WORKING_SOLUTION> \
  --content "<ARGS>" \
  --context "manual entry via /remember" \
  --confidence medium
调用该技能时，运行以下命令：
bash
cd $CLAUDE_OPC_DIR && PYTHONPATH=. uv run python scripts/core/store_learning.py \
  --session-id "manual-$(date +%Y%m%d-%H%M)" \
  --type <TYPE or WORKING_SOLUTION> \
  --content "<ARGS>" \
  --context "manual entry via /remember" \
  --confidence medium

Auto-Type Detection

自动类型检测

If no 
--type
specified, infer from content:
  • Contains "error", "fix", "bug" → ERROR_FIX
  • Contains "decided", "chose", "architecture" → ARCHITECTURAL_DECISION
  • Contains "pattern", "always", "convention" → CODEBASE_PATTERN
  • Contains "failed", "didn't work", "don't" → FAILED_APPROACH
  • Default → WORKING_SOLUTION
若未指定
--type
，将根据内容推断类型：
  • 包含“error”、“fix”、“bug” → ERROR_FIX
  • 包含“decided”、“chose”、“architecture” → ARCHITECTURAL_DECISION
  • 包含“pattern”、“always”、“convention” → CODEBASE_PATTERN
  • 包含“failed”、“didn't work”、“don't” → FAILED_APPROACH
  • 默认 → WORKING_SOLUTION