awow-usage-coachAnalyse how a team or an individual works through agent sessions in the awow repo (or a sibling repo as stand-in) and produce one of two markdown reports: (a) team-nudge — proposed additions to .agents/AGENTS.md / copilot-instructions based on recurring sequence + editing patterns, or (b) self-coach
mlflow-exportExport all traces and grouped chat sessions from a Databricks MLflow experiment to local JSON files. This skill should be used when the user asks to export, dump, download, or back up MLflow traces, sessions, or chat-sessions from a Databricks experiment (often given as an MLflow experiment URL or n
project-timelineBuild an interactive visual timeline + whole-project read of how a repo was built across many agent sessions — the fan-out/contract rhythm, handoffs, idle time, context load, per-user split, token cost, and optional per-session coaching. Reads raw Claude Code logs (zero setup, richest detail) or an
prompt-skill-analysisAssess prompt-engineering quality from a Claude Code session and write a markdown report. Use when the user asks for a prompt-skill review, prompting feedback, prompt-quality assessment, or wants to evaluate how well they (or someone else) prompt Claude Code. Accepts either a raw Claude Code session
session-exportExport a project's Claude Code sessions into a readable transcript dump (the input the project-timeline skill needs). Walks the user through choosing the project, scoping which sessions to include (date window, excluding meta/plugin runs), and warns about secrets before writing. Use when the user wa