From openltm
Retrieves patterns and lessons from past sessions to reuse fixes, avoid mistakes, and recover context after compaction.
How this skill is triggered — by the user, by Claude, or both
Slash command
/openltm:LearnedThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Session learnings distilled into reusable patterns. Use this skill when past work, decisions, or fixes may apply to the current task.
Session learnings distilled into reusable patterns. Use this skill when past work, decisions, or fixes may apply to the current task.
| Trigger | Use |
|---|---|
| "what did we learn", "past patterns", "previous sessions" | Review accumulated knowledge |
| "what worked before", "known gotchas", "lessons learned" | Pull relevant session patterns |
| "review past decisions", "reference earlier fixes" | Check historical context |
| "when should I reuse this", "has this been solved before" | Search the learning summary |
skills/Learned/summary.md — condensed session summaries and recent learning history, auto-updated by the EvaluateSession hook.mcp__plugin_openltm_memory__recall.mcp__plugin_openltm_memory__recall) when you need the exact reasoning, gotcha, or implementation detail behind a past decision.npx claudepluginhub rohirik/openltm --plugin openltmSearches past learnings, mistakes, and correction history to surface relevant patterns before starting a task. Helps avoid repeated errors and apply prior insights.
Searches project memory via progressive filtering with MEMORY.md index and grep for task-relevant patterns before non-trivial work; stores structured problem-solution insights after completion.
Captures high/medium/low confidence patterns from conversations to prevent repeating mistakes and preserve successes. Invoke proactively after corrections, praise, edge cases, or skill-heavy sessions.