Store atomic learnings in a searchable learnings.jsonl file.
npx skills add https://github.com/iamzifei/show-me-the-money --skill money-learn
Please help me install this Agent Skill. Skill: money-learn Source: https://github.com/iamzifei/show-me-the-money/tree/main/skills/money-learn Command: npx skills add https://github.com/iamzifei/show-me-the-money --skill money-learn
Manage project learnings — small, atomic, validated patterns that the agent should remember across all skills and sessions. Different from /money-save (which captures full session state); learnings are individual insights that get auto-loaded into every other money-* skill's context. Use when the user has just discovered something worth remembering — a customer pattern, a pricing insight, a channel that works, a failure mode. Triggered by: 'remember this', 'log a learning', 'this is a pattern', 'show learnings', 'what have we learned', '记住这个', '存入经验', '查看经验库'.
Log a new learning from the current conversation to append to learnings.jsonl for future reference.
High-intent search queries and answers about installing and using this skill.
To retain atomic learnings across sessions, you append validated patterns as individual, citable lines into a durable learnings.jsonl file, ensuring insights are preserved and searchable for future workflows.
Logging project knowledge for AI reuse involves capturing atomic insights in an append-only JSONL schema, which allows for interactive logging, pruning, and supersession while maintaining a searchable knowledge base.
Auto-loading validated patterns improves outputs by surfacing stored learnings with evidence before generation, providing necessary context and historical data to enhance decision-making across related workflows.
Yes, you can search and export knowledge management patterns from a JSONL file using batch workflows that support pruning and exporting, enabling continuous improvement and knowledge retention across projects.
Storing learnings as individual atomic patterns prevents context loss by enforcing an append-only schema that captures specific insights, distinguishing them from full session state captures for easy revision.
An append-only schema for knowledge retention should not be used when you need to mutate historical data directly, as it restricts modifications and relies on supersession to invalidate outdated patterns.
kid0317Store fragmented work reflections as searchable, categorized notes in memory archives.
louisfghbvcOrganize project learnings across sessions in a local JSONL database.
iamzifeiRoute user requests to money-* skills or run end-to-end business pipelines.
AlexZio00Capture and preserve session context across compaction, handoff, and termination.
