Analyze conversation corrections to detect skill gaps and prepare targeted skill-library maintenance tasks. Use after any session with user corrections, rework, or retrospective requests. After finding correction loops, also load +common/common-learning-log to persist mistake entries to AGENTS_LEARNING.md.
74
—
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
common/session-retrospective/
├── SKILL.md # Protocol (this file)
└── references/
└── methodology.md # Signal tables, taxonomy, report templatereferences/. Update AGENTS.mdcommon/common-learning-log protocol (Signal: Session retrospective)Emit trigger miss block (schema in references/methodology.md) for each miss detected.
AGENTS.md before creating — extend existing guidance first.skillsrc agents fieldcommon/skill-creator standardsreferences/ per skill-creator standardSignal tables, root cause taxonomy, report template, real-world example: references/methodology.md
611f52a
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.