From claude-reflect
Discards queued learning items without processing. Shows a summary with count and item previews, then prompts for confirmation before clearing the queue.
How this command is triggered — by the user, by Claude, or both
Slash command
/claude-reflect:skip-reflectThis command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
## Context - Queue count: !`python3 scripts/read_queue.py 2>/dev/null | python3 -c "import sys,json;print(len(json.load(sys.stdin)))" 2>/dev/null || echo 0` ## Your Task 1. If queue is empty: - Output: "Queue is already empty. Nothing to skip." - Exit 2. If queue has items: - Show: "You are about to discard [count] learning(s). These will be lost:" - List each queued item briefly (type + first 50 chars of message) - Ask: "Are you sure? [y/n]" 3. If user confirms (y/yes): - Clear the project queue: - Output: "Discarded [count] learnings. Queue cleared." 4. If us...
python3 scripts/read_queue.py 2>/dev/null | python3 -c "import sys,json;print(len(json.load(sys.stdin)))" 2>/dev/null || echo 0If queue is empty:
If queue has items:
If user confirms (y/yes):
python3 -c "
import sys, os
sys.path.insert(0, os.path.join(os.environ.get('CLAUDE_PLUGIN_ROOT', '.'), 'scripts'))
from lib.reflect_utils import save_queue
save_queue([])
"
If user declines (n/no):
This is an escape hatch for when auto-detection captures false positives or learnings aren't worth saving. Use sparingly.
npx claudepluginhub georger/claude-reflect --plugin claude-reflect4plugins reuse this command
First indexed Mar 16, 2026
/skip-reflectDiscards queued learning items without processing. Shows a summary with count and item previews, then prompts for confirmation before clearing the queue.
/processTriggers inline queue processing on secretary.db, runs worker script with optional --limit and --verbose, shows before/after depths, breakdowns, and recent decisions/ideas/commitments.
/mkg-reviewWalks the Meta Knowledge Graph human-review queue one item at a time, letting you approve, edit, or reject ambiguous contradictions and user-scoped candidate facts.
/learn-resetClears all accumulated knowledge entries, resets classification cache, and restores learning state to initial values. Warning: irreversible.
/prune-learningsRuns pruning to clean up old learnings: removes stale session dirs, rotates logs, deletes expired archived files, and force-cleans stale lock files. Follows retention.yaml policy.
/queueLoads and executes a Hypo-Workflow skill for maintaining a queue, with a consultation-first boundary that treats discussion inputs as non-editing signals.