recall
Retrieve context from past sessions before implementing. Use for learned patterns, past solutions, anti-patterns, session history, or when the user mentions "recall", "memory", "history", "cass", "cm", or "what do we know about".
Security Assessment
About recall
The 'recall' skill is designed to retrieve and leverage relevant context from past sessions to aid in the execution of current tasks. This capability solves the problem of repetitive decision-making by providing access to previously used solutions, learned patterns, and identified anti-patterns, ensuring more efficient and informed task execution. It pulls context from historical sessions, which includes both rules and previous failures to avoid, so users don't have to start from scratch each time a new task arises.
FAQ
How do I trigger the recall skill?
You can trigger the recall skill by using the command 'cm context' with a task description, or by directly mentioning 'recall', 'memory', 'history', 'cass', 'cm', or 'what do we know about'.
What happens if I use 'cass' without the '--robot' or '--json' options?
Using 'cass' without the '--robot' or '--json' options will launch a TUI (Text User Interface) that can cause AI agents to hang. Always use these flags to prevent this issue.
Can I customize the recall commands to suit my specific tasks?
Yes, you can modify the task descriptions in the 'cm context' command to retrieve context relevant to any specific task you are working on, such as implementing a feature or fixing an issue.
What are the limitations of the recall skill?
The recall skill is designed to retrieve context from past sessions but does not offer deep analysis or generate new insights beyond the historical data available in the system.
Install recall
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
Mburdo/knowledge_and_vibes