From agentskill-kaizen
Extracts specific data points like tool timings, query counts, or error summaries from large agent transcripts, kaizen reports, or JSONL files using Grep and DuckDB SQL without loading raw data into context.
npx claudepluginhub jamie-bitflight/claude_skills --plugin agentskill-kaizenThis skill is limited to using the following tools:
A data extraction skill for pulling specific facts from files. Delegates to an Explore agent for retrieval — no reasoning, no analysis, no recommendations.
Analyzes Claude Code JSONL transcripts to detect anti-patterns, tool misuse, user frustration signals, and workflow patterns using DuckDB SQL, 10 dimensions, and PM4Py mining.
Analyzes JSONL and other log files using rg and jq: structured extraction, cross-log correlation, timeline reconstruction, pattern search.
Locates, lists, filters, and extracts structured data from Claude Code native session logs. Supports both single and multiple session analysis.
Share bugs, ideas, or general feedback.
A data extraction skill for pulling specific facts from files. Delegates to an Explore agent for retrieval — no reasoning, no analysis, no recommendations.
Constraint: This skill is orchestrator-invoked only. It is not user-invocable directly. Spawn via the analyze or explore commands.
read_ndjson_auto with absolute paths). Use SQL for counting, aggregation, and filtering. Use Grep only for markdown reports.QUERY: <what was asked>
---
<data-point-name>: <value>
<data-point-name>: <value>
<data-point-name>: <value>
---
SOURCE: <file path or SQL query used>
See extraction-patterns.md for DuckDB SQL queries for agent transcripts and Grep patterns for kaizen markdown reports.
If asked to analyze, respond: "I extract data points only. Ask the orchestrator to analyze the results."