Document post-task learnings into learnings.md and suggest CLAUDE.md improvements.
npx skills add https://github.com/JNZader/javi-ai --skill compound-loop
Please help me install this Agent Skill. Skill: compound-loop Source: https://github.com/JNZader/javi-ai/tree/main/own/skills/compound-loop Command: npx skills add https://github.com/JNZader/javi-ai --skill compound-loop
Post-task learning capture workflow that documents what was learned, appends to learnings.md, and suggests CLAUDE.md improvements.
Describe the task context and trigger the post-task learning capture to append a new entry to learnings.md.
High-intent search queries and answers about installing and using this skill.
You automate post-task learning capture by issuing trigger commands like "compound" after significant work, which documents learnings and appends a structured entry with dates and tags to learnings.md.
The best way to append structured learnings is to prepend entries to a dedicated learnings.md file using a standardized format with dates, tags, and optional Engram integration for cross-project retrieval.
Yes, you can suggest CLAUDE.md improvements based on captured task learnings by analyzing the documented learnings entry and proposing updates to enhance future AI sessions.
Post-task reflection supports optional Engram integration, enabling cross-project knowledge retrieval by storing standardized learning entries with dates and tags in learnings.md.
You should trigger a learning entry capture after completing significant work or when issuing specific commands like "what did we learn" to document and reflect on the task outcomes.
dtinthAnalyze recent work across four dimensions and generate proposed documentation updates.
ashcastelinocs124Capture coding session learnings and append dated entries to learnings.md.
akiyoshiAggregate and search session learnings stored in learnings.jsonl.
AIBiz-AutomatyzacjeArchive completed tasks and extract insights from project context files.
