What problem does it solve? AI agents repeat the same mistakes across sessions because failures, user corrections, and discovered best practices are never persisted. This Skill creates a traceable learning loop by logging errors, learnings, and feature requests to structured Markdown files, then promoting proven rules into long-term memory. ## Core Features & Use Cases - Structured Logging: Records errors (ERR), learnings (LRN), and feature requests (FEAT) with unique IDs, priorities, statuses, and metadata into LEARNINGS.md, ERRORS.md, and FEATURE_REQUESTS.md. - Scoped Storage & Promotion: Writes to a skill-level data directory by default, supports project-level .learnings/ scopes, and promotes cross-project entries to a public area with duplicate protection and automatic status back-writing. - Memory Integration: Defines hard criteria for promoting recurring patterns into the Minis memory system, including recurrence counting and pattern-key deduplication. - Use Case: After a curl command fails with HTTP 429 during a task, run the logging script to record the error with context; when the same issue recurs across projects, promote the entry so future sessions avoid the mistake. ## Quick Start Ask the agent to record the last command failure as an error entry using the self-improving-agent logging script.
