How this skill is triggered — by the user, by Claude, or both
Slash command
/automate:automate-deleteThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Arguments: $ARGUMENTS
Arguments: $ARGUMENTS
Read ${CLAUDE_SKILL_DIR}/../../docs/shared-context.md for registry format, merge algorithm, and deletion procedures.
Parse $ARGUMENTS for the automation name.
If no name given, read the registry and show the list, then ask which one to delete.
Read ~/.claude/automations-registry.json and find the automation by name.
If not found, show error and list available automations.
Show the automation details (name, type, scope, path, description).
Use AskUserQuestion with options:
If not confirmed, cancel and stop.
Based on the automation type, follow the deletion procedure from shared-context.md:
Validate any modified JSON files with jq after writing.
Remove the entry from ~/.claude/automations-registry.json.
If the automation had relatedHook or relatedSkill links, warn about orphaned related components.
Show: "Deleted <name> (<type>, <scope>)."
npx claudepluginhub elmisi/claude-code-automation --plugin automateSafely removes plugin assets (skills, agents, rules, scripts, hooks) by detecting dependencies and cleaning up references. Invoke via /safe-remove for decluttering.
Uninstalls community skills installed via the hub, with safety checks, confirmation, and audit logging. Refuses to remove first-party plugin skills.
Scans Claude Code config (skills, memory, hooks, permissions, MCP servers, caches) for stale or redundant items and walks the user through confirm-each-deletion cleanup.