agent-transcript

Parse and sanitize agent JSONL logs into Markdown transcripts for GitHub PRs.

Updated Jun 24, 2026
One-click install
npx skills add https://github.com/starrank-soft/PixelArraySkill --skill agent-transcript-starrank-soft
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-transcript
Source: https://github.com/starrank-soft/PixelArraySkill/tree/main/skills/agent-transcript
Command: npx skills add https://github.com/starrank-soft/PixelArraySkill --skill agent-transcript-starrank-soft

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill solves the lack of transparency in agent-driven development by providing a secure, redacted, and human-readable record of an agent's reasoning and actions within GitHub PRs and issues.

Core Features & Use Cases

  • Automated Redaction: Automatically strips sensitive information like tokens, cookies, and private paths from raw session logs.
  • Contextual Transparency: Generates a structured Markdown summary of agent decisions, tool usage, and outcomes to help reviewers understand the context of a PR.
  • Use Case: When an agent creates a complex refactoring PR, use this skill to append a sanitized transcript to the PR body, allowing human reviewers to quickly verify the agent's logic and testing steps without digging through raw logs.

Quick Start

Use the agent-transcript skill to find the most relevant session for the current branch and append a redacted summary to the pull request body.

Frequently Asked Questions about agent-transcript

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

FAQPage Schema
How do I attach agent session logs to a GitHub PR?

To attach agent session logs to a GitHub PR, you can parse local agent JSONL logs and generate a sanitized Markdown transcript. This skill appends the redacted summary directly to the pull request body for human reviewers.

How do I sanitize sensitive data from agent JSONL logs before sharing?

Sanitizing sensitive data from agent JSONL logs requires automated redaction to strip tokens, cookies, and private paths. The process extracts relevant session turns while filtering out unrelated tasks to ensure secure provenance.

What is the best way to provide transparency for agent-created pull requests?

Providing transparency for agent-created pull requests involves generating a structured Markdown summary of agent decisions and tool usage. This gives reviewers contextual insight into the agent logic without exposing raw logs.

Do I need local access to agent logs to generate PR transcripts?

Yes, you need local access to agent JSONL logs to generate PR transcripts. This skill operates entirely within the local development environment to parse sessions and filter out sensitive system data before formatting outputs.

Can I use PR automation to document agent reasoning for human reviewers?

Yes, you can use PR automation to document agent reasoning by appending a redacted transcript to the PR body. This allows human reviewers to quickly verify the agent testing steps and logic during code reviews.

Why are my raw agent logs unsuitable for direct GitHub issue attachment?

Raw agent logs are unsuitable for direct GitHub issue attachment because they contain sensitive system data, tokens, and unrelated tasks. Sanitizing and extracting relevant turns ensures only redacted, human-readable context is shared.