Menu
Cleanly remove learning-loop and its footprint. Usage: /learning-loop:uninstall. Walks the three steps — marketplace removal, episodic-memory MCP removal, and purging captured indexes — with confirmation before each destructive action. Does not auto-delete.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Deep research with the local librarian doing the token-heavy middle. Scope on Claude, Search+Fetch+Extract on the local Ollama model, adversarial Verify + Synthesize back on Claude. Usage: /learning-loop:research "<question>". Falls back to Claude-native WebSearch when the librarian is unavailable or sub-tier.
End-of-session consolidation. Usage: /learning-loop:reflect (no args). Reviews conversation, extracts learnings, routes to auto-memory or vault, cross-links projects, promotes inbox notes. Run after substantial work sessions.
measure whether a /dream pass helps, hurts, or ties against no consolidation. usage: /learning-loop:dream-eval --mode={single|control|repeated} [--passes=N] [--mine]. single scores pre/post on the live corpus; control forks two clones and dreams one; repeated dreams a clone N times and plots the drift + content-survival curve.
Consolidate auto-memory between sessions. Usage: /learning-loop:dream (no args). Four-phase cycle: Orient, Gather Signal, Consolidate, Prune Index. Seven operators: MERGE, RESOLVE, ABSTRACT, COMPRESS, PRUNE, LINK, DATE NORMALIZE. Rebuilds MEMORY.md.
Cross-store correction for a retracted or updated belief. Usage: /learning-loop:rewrite "old pattern" "new pattern" [reason]. Searches vault, auto-memory, and episodic history; presents an impact map for triage; executes user-approved changes; records a supersession so future episodic searches get annotated.
Diagnose your learning-loop installation. Runs health checks, presents issues, offers per-fix remediation, re-runs each check after the fix to confirm. Safe to run anytime; only makes changes you approve. Pass --redact to scan plugin data files for leaked credentials instead.
| name | uninstall |
| description | Cleanly remove learning-loop and its footprint. Usage: /learning-loop:uninstall. Walks the three steps — marketplace removal, episodic-memory MCP removal, and purging captured indexes — with confirmation before each destructive action. Does not auto-delete. |
Removing the plugin via /plugin alone leaves two artefacts behind: the
episodic-memory MCP entry in ~/.claude.json and the captured-index data
dir. This skill walks the full removal with operator confirmation.
Confirm intent. Ask the operator to confirm they want to fully remove
learning-loop, including all captured indexes (backlinks, justification
index, session labels). If they only want hooks off, point them at the disableAllHooks: true guidance in
the README's "Disabling parts without uninstalling" section instead and
stop.
Remove the plugin. Tell the operator to run /plugin and remove
learning-loop via the marketplace UI. (Claude cannot drive the marketplace
UI; the operator does this step.)
Remove the dependent MCP (confirm first):
claude mcp remove episodic-memory
Note: only if no OTHER installed plugin depends on episodic-memory. Check
with claude mcp list and ask before removing.
Purge captured indexes (confirm first — irreversible):
rm -rf ~/.claude/plugins/data/learning-loop-learning-loop-marketplace/
Show the operator the dir's du -sh size before deleting so they see what
is being purged.
Report what was removed and what (if anything) the operator chose to keep.
