Views or changes the default memory scope (project, session, or global) used when saving and searching memories. Use when the user wants to control whether memories are scoped to this repo, this run, or shared across all their projects.
70
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
The skill explicitly instructs the agent to Read the user's settings file and Write it back "keeping ALL existing keys", which requires the LLM to echo any values (including secrets or API keys) verbatim from the file into its output/write operation.
dae67f7
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.