Stats
Actions
Tags
From buidl
Displays learning system health report with pattern counts, agent scores, project-type profiles, and prune log. Runs audit script and suggests pruning if patterns are stale.
How this command is triggered — by the user, by Claude, or both
Slash command
/buidl:buidl-learningThis command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
# The Loop — Learning System Health Print a health report of the learning system, including pattern counts, agent scores, project-type profiles, and prune log. ## Steps 1. Run the audit script: 2. Display the full output to the user. 3. If patterns are stale (last_seen_version 2+ major versions behind), suggest running pruning:
Print a health report of the learning system, including pattern counts, agent scores, project-type profiles, and prune log.
bash ${CLAUDE_PLUGIN_ROOT}/scripts/audit-learning.sh
bash ${CLAUDE_PLUGIN_ROOT}/scripts/update-scores.sh <state-file> pass --prune
npx claudepluginhub bc1plainview/buidl-opnet-plugin/patternsValidates pattern learning system across commands and agents, checks storage integrity and format, analyzes effectiveness trends, generates health reports and analytics. Supports --analytics, --quick, --filter flags.
/statusQueries Supabase for real-time learning system status including connection health, feedback counts, agent success rates, workflow metrics, and recent activity.
/learning-statusDisplays learning metrics dashboard showing reviews analyzed, issue trends by category/severity, recurring issues, improvement effectiveness, and recommendations.
/superpowers-statusDisplays health dashboard for project's AI Literacy habitat, checking core files, harness, agent team, compound learning, model routing, and CI status.
/patternsManage learned patterns: save high-value ones as skills/agents, analyze quality, review usefulness with SM-2, and view statistics.
/statusDisplays a quality metrics dashboard with code review trends, technical debt hotspots, learning loop suggestions, observability per-stage metrics, and active feedback loops.