agentskill-kaizen

Run autonomous transcript analysis pipeline across sessions

Interactive transcript exploration — presents findings, user steers investigation

Produce hook scripts from discovered anti-patterns — drafts by default, --install writes to settings

Generate summary report from existing analysis in .planning/kaizen/

Transform analysis findings into actionable improvements — generates hook scripts, skill patches, agent prompt refinements, and CLAUDE.md updates based on discovered anti-patterns and inefficiencies

Deep-dive into Claude Code session transcripts using DuckDB SQL and process mining tools — spawned by analyze and explore commands to query JSONL data, detect anti-patterns, extract frustration signals, and mine workflow patterns across sessions

Agentskill kaizen plugin documentation index. Load when needing to read about cross-platform notes, improvement plans, or DuckDB integration.

Transform transcript analysis findings into actionable improvements. Triggers on "generate hooks from findings", "improve agent", "fix anti-pattern", "kaizen improvement", "generate hook proposals", or "create improvement plan". Provides templates for hook generation, agent prompt refinement, skill patches, CLAUDE.md updates, and script automation from analysis data.

Use when extracting specific data points from large agent output transcripts, kaizen analysis reports, or JSONL session files — tool timings, query counts, error summaries, or any structured facts — without loading raw data into orchestrator context. Activates when the orchestrator needs targeted facts from large files and context pollution must be avoided.

This skill should be used when analyzing Claude Code session transcripts, reviewing agent performance, finding anti-patterns or tool misuse, detecting user frustration signals, mining workflow patterns, running kaizen analysis, debugging agent behavior, or performing session forensics. Provides JSONL schema (kaizen-analysis get_transcript_jsonl_schema or MCP resource kaizen://session-log/schema or references/jsonl-schema.md), arbitrary DuckDB SQL over JSONL via kaizen-duckdb execute_query, cookbook query patterns, 10 analysis dimensions, and PM4Py process mining methodology.