research-transcript

Audit agent session transcripts for compliance and reasoning gaps.

Updated Feb 10, 2026

Search Tags:#session analysis #reasoning analysis #agent auditing #non-compliance #compliance ledger

Ready to run

npx skills add https://github.com/tz5514/zet-claude-code-settings --skill research-transcript

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: research-transcript
Source: https://github.com/tz5514/zet-claude-code-settings/tree/main/skills/research-transcript
Command: npx skills add https://github.com/tz5514/zet-claude-code-settings --skill research-transcript

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, json, pandas, numpy, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill audits and analyzes agent session transcripts to identify non-compliance, reasoning gaps, and adherence to governing instructions, providing insights into the agent's behavior and decision-making process.

Core Features & Use Cases

Non-compliance Audit: Identify instances where the agent did not follow documented steps or violated governing instructions.
Reasoning Analysis: Examine the agent's thought process and identify self-rationalized shortcuts or degradation over time.
Compliance Ledger: Generate a detailed report outlining adherence rates, violations, and recommendations for improvement.
Use Case: After an agent session, use this Skill to review the transcript and understand where and why the agent deviated from expected behavior.

Quick Start

Use the research-transcript skill to analyze the session transcript located at '/path/to/transcript.jsonl'.

Frequently Asked Questions about research-transcript

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I audit agent session transcripts for non-compliance?▼

To audit agent session transcripts, you compare documented steps and governing instructions against actual behavior. This process identifies non-compliance and reasoning gaps, generating a detailed compliance ledger outlining adherence rates and violations.

Can I analyze JSONL transcripts from Claude Code, Cursor, and Codex?▼

Yes, you can analyze JSONL transcripts from Claude Code, Cursor, and Codex. The analysis requires Python, JSONL parsing, and machine learning models to examine the agent's thought process and identify self-rationalized shortcuts.

What is agent reasoning analysis and how does it work?▼

Agent reasoning analysis examines an agent's thought process to identify self-rationalized shortcuts or degradation over time. It works by comparing documented steps and governing instructions against actual behavior in session transcripts.

Do I need Python and pandas to analyze agent session transcripts?▼

Yes, you need Python, pandas, numpy, and JSON parsing to analyze agent session transcripts. These dependencies support the machine learning models required to audit compliance and examine reasoning behavior in JSONL files.

How do I generate a compliance ledger for agent behavior?▼

You generate a compliance ledger by auditing agent session transcripts to compare documented steps against actual behavior. The resulting report outlines adherence rates, violations, and recommendations for improvement based on the analysis.

What are the limitations of using machine learning for session analysis?▼

The limitations of using machine learning for session analysis include the requirement for structured JSONL transcripts and dependencies on Python, pandas, and numpy. The analysis is constrained by the quality of the documented steps and governing instructions provided.