Skill Analytics: Conversation Usage Mining & Context-Tax ROI Engine

The skill-analytics skill mines local agent conversation transcripts (with 0% sampling and automatic transcript.jsonl + transcript_full.jsonl truncation merging) alongside your installed skill inventory across all tiers (builtin, plugin, global, workspace, and catalog) into a local SQLite warehouse (skill_analytics.db). Use these metrics to prune zero-use "shelfware" skills and rewrite under-performing frontmatter descriptions.

Available scripts

• scripts/analyze.py: Zero-dependency Python 3 CLI for incremental transcript ingestion, full historical rebuilds, pre-packaged ROI/trigger/velocity/gap reports, and ad-hoc SQL queries.
• scripts/test_analyze.py: Automated unit and regression test suite validating schema DDL, views, parser accuracy, and markdown SQL code blocks.

⚡ Quick Start & Primary Actions

All operations are driven via scripts/analyze.py (runnable via uv run scripts/analyze.py):

# 1. Incremental Sync (Only parses new or modified conversation transcripts)
uv run scripts/analyze.py sync --db skill_analytics.db