remember
npx machina-cli add skill parcadei/Continuous-Claude-v3/remember --openclawFiles (1)
SKILL.md
1.8 KB
Remember - Store Learning in Memory
Store a learning, pattern, or decision in the memory system for future recall.
Usage
/remember <what you learned>
Or with explicit type:
/remember --type WORKING_SOLUTION <what you learned>
Examples
/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
What It Does
- Stores the learning in PostgreSQL with BGE embeddings
- Auto-detects learning type if not specified
- Extracts tags from content
- Returns confirmation with ID
Learning Types
| Type | Use 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 |
Execution
When this skill is invoked, run:
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
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
Source
git clone https://github.com/parcadei/Continuous-Claude-v3/blob/main/.claude/skills/remember/SKILL.mdView on GitHub Overview
Remember stores a learning, pattern, or decision in the memory system for future recall. It uses PostgreSQL with BGE embeddings, auto-detects learning type if not provided, extracts tags, and returns a confirmation with an ID to enable easy reuse.
How This Skill Works
When invoked, content is stored in PostgreSQL with BGE embeddings. If a type isn't provided, the system auto-detects it, extracts tags from the content, and returns a unique ID confirming the memory entry for later recall.
When to Use It
- You’ve learned a fix or solution and want to recall it later as a WORKING_SOLUTION.
- You’ve made a design choice and want to capture it as an ARCHITECTURAL_DECISION.
- You’ve discovered a coding pattern worth reusing as a CODEBASE_PATTERN.
- You attempted something that didn’t work and want to record the FAILED_APPROACH for future avoidance.
- You resolved a specific error or bug and want to remember the ERROR_FIX for reference.
Quick Start
- Step 1: Run /remember <your learning content>
- Step 2: Optionally add --type <TYPE>
- Step 3: Review the confirmation with the new memory ID
Best Practices
- Be explicit and concise about what you learned or decided.
- Include enough context (why, where, when) to make the memory useful later.
- Prefer specifying --type when possible; rely on auto-detection if unsure.
- Let the system extract tags to improve future searchability.
- Store memories with a clear session-id and note the returned ID for easy retrieval.
Example Use Cases
- /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 --type CODEBASE_PATTERN Extracted patterns discovered in codebase
- /remember --type ERROR_FIX Fixed a recurring install error by updating the npm script
Frequently Asked Questions
Add this skill to your agents
