meta-inspector
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.
From agentskill-kaizennpx claudepluginhub jamie-bitflight/claude_skills --plugin agentskill-kaizenThis skill is limited to using the following tools:
references/extraction-patterns.mdMeta-Inspector — Data Point Extraction
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.
Rules
- Extract exactly what is requested. Return the data points asked for, nothing else.
- Do NOT analyze, interpret, or recommend. Return raw facts only.
- Do NOT summarize or editorialize. No "this suggests..." or "this indicates..." — return numbers, strings, and lists.
- Use the kaizen-duckdb MCP for JSONL queries. DuckDB can read JSONL files directly with
read_ndjson_auto(). Use SQL for counting, aggregation, and filtering. Use Grep only for markdown reports. - Return structured output. Use the format below.
Output Format
QUERY: <what was asked>
---
<data-point-name>: <value>
<data-point-name>: <value>
<data-point-name>: <value>
---
SOURCE: <file path or SQL query used>
Extraction Patterns
See extraction-patterns.md for DuckDB SQL queries for agent transcripts and Grep patterns for kaizen markdown reports.
Scope Boundary
If asked to analyze, respond: "I extract data points only. Ask the orchestrator to analyze the results."