Where are the generated reports saved?

Reports are automatically saved as Markdown files in a local 'field-reports/' directory, named using the subject and session ID for easy organization.

What metrics are included in a performance report?

Reports include task completion status, instruction adherence (if a definition file is found), tool usage patterns, conversation efficiency, and error handling logs.

Can I analyze a skill without its SKILL.md file?

Yes. While having the definition file allows for instruction adherence checks, Field Report can still evaluate general performance, tool usage, and task completion based solely on the session transcript.

How does Field Report locate specific sessions?

It supports both explicit session IDs (starting with ses_) and natural language queries like 'last session' or 'today's session' to automatically resolve and analyze relevant transcripts.

Is sensitive data redacted during the analysis?

Yes, Field Report includes a mandatory sanitization step that automatically redacts API keys, email addresses, IP addresses, and other credentials before the final report is written.

Field Report

Name: Field Report
Author: nicholls-inc

bynicholls-inc

•

Analíticas y Monitorización

Generates evidence-based performance reports on AI agents and skills by analyzing Claude Code session transcripts.

Field Report is a sophisticated diagnostic tool designed for developers to audit and improve the performance of their Claude Code plugins, skills, and agents. By analyzing conversation logs and tool traces, it produces structured, narrative evaluations that highlight task completion rates, instruction adherence, and tool efficiency. It prioritizes data privacy through automatic sanitization while providing actionable recommendations to help maintainers refine AI behavior based on real-world evidence from specific session IDs or natural language history.

Características Principales

01Automated session discovery via natural language or explicit session IDs

02Privacy-safe data sanitization to redact sensitive tokens and PII

033 GitHub stars

04Structured Markdown report generation with actionable developer recommendations

05Evaluation of conversation efficiency and error recovery latency

06Evidence-based analysis of instruction adherence and tool usage patterns

Casos de Uso

01Optimizing tool usage sequences to improve session speed and reliability

02Auditing instruction adherence for custom AI agents before deployment

03Debugging why a specific skill or tool failed during a complex workflow

Características Principales

01Automated session discovery via natural language or explicit session IDs

02Privacy-safe data sanitization to redact sensitive tokens and PII

033 GitHub stars

04Structured Markdown report generation with actionable developer recommendations

05Evaluation of conversation efficiency and error recovery latency

06Evidence-based analysis of instruction adherence and tool usage patterns

Casos de Uso

01Optimizing tool usage sequences to improve session speed and reliability

02Auditing instruction adherence for custom AI agents before deployment

03Debugging why a specific skill or tool failed during a complex workflow