How this skill is triggered — by the user, by Claude, or both
Slash command
/cortex:cleanThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Activate the `workspace-hygiene` skill. Run the cleanup process.
Activate the workspace-hygiene skill. Run the cleanup process.
If $ARGUMENTS specifies a category, clean only that:
CRITICAL: Always show the assessment FIRST. Never delete without user confirmation.
Also run Cortex data file trimming:
tool-usage.jsonl → keep last 2000 entriesprompt-log.jsonl → keep last 500 entriessession-log.jsonl → keep last 1000 entrieslearnings.jsonl → keep last 200 entriesanti-patterns.jsonl → keep last 100 entriesdecision-journal.jsonl → keep last 500 entriesRequest: $ARGUMENTS
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
npx claudepluginhub pretinnov-inc/claude-plugin-marketplace --plugin cortex