The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like rm -rf, sed, and jq to delete directories, remove specific environment variable exports from shell profiles, and modify local JSON configuration files.
[CREDENTIALS_UNSAFE]: The uninstallation process includes steps to identify and delete application-specific tokens stored in the macOS Keychain using the security utility.
[DYNAMIC_EXECUTION]: Inline Python code is utilized to programmatically edit JSON files, such as installed_plugins.json and settings.json, to remove specific keys related to the plugin.
[INDIRECT_PROMPT_INJECTION]: The skill reads local configuration files and shell profiles to identify content for removal. While this represents a data ingestion surface, the risk is mitigated by the fact that it only performs targeted deletions based on hardcoded patterns and requires user confirmation for all actions.
[SAFE]: The skill operates entirely locally without network access and requires explicit user confirmation via the AskUserQuestion tool before performing any destructive actions or modifications to system files.

uninstall