Microsoft's AI-Engineering-Coach reads your local agent session logs and grades your prompting.

microsoft/AI-Engineering-Coach parses local AI coding session logs on-machine and returns agentic readiness checks, instruction-file audits, workspace context maps and five practice scorecards with severity ratings and example prompts, backed by 45 editable markdown detection rules and a coverage heatmap. MIT, 3,968 stars, pushed today, with no marketplace listing and no release, so you build the .vsix yourself; the dashboard also runs as a canvas inside the GitHub Copilot app. First first-party tool I've seen that treats your own transcripts as the diagnostic artifact instead of your code.