prompt-history

Extract AI prompt history from tool logs into structured JSON payloads.

Updated Feb 2, 2026
One-click install
npx skills add https://github.com/gutierrezje/promptex --skill prompt-history
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-history
Source: https://github.com/gutierrezje/promptex/tree/main/skills/prompt-history
Command: npx skills add https://github.com/gutierrezje/promptex --skill prompt-history

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extracts and curates AI prompt history into PR-ready markdown using PromptEx (pmtx). Use when the user asks about prompt history, wants to document their AI-assisted reasoning for a PR, or asks to extract or summarize their session.

Core Features & Use Cases

  • Extracts AI tool session prompts and metadata from logs.
  • Correlates prompts to PR-ready markdown and structured JSON payloads.
  • Use Case: document reasoning for a PR and provide a traceable prompt history.

Quick Start

Run pmtx extract to generate PR-ready prompt history from your AI tool logs.

Frequently Asked Questions about prompt-history

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

FAQPage Schema
How do I document AI prompt history for a pull request review?

Documenting AI prompt history for a pull request involves extracting prompts from tool logs and converting them into a structured JSON payload, which is then formatted into PR-ready markdown files for traceable review.

What is the best way to extract AI session history from tool logs into markdown?

The best way to extract AI session history from tool logs is to parse the logs for prompts and metadata, convert them into a canonical JSON payload, and render that payload into structured markdown documentation.

Do I need the pmtx binary to curate PR-ready prompts?

Yes, curating PR-ready prompts requires the pmtx binary to execute the extraction process that pulls AI session data from your logs and generates the structured JSON output.

Can I redact sensitive prompts when generating AI session summaries?

Yes, you can redact sensitive prompts when generating AI session summaries, as the extraction process applies redaction to sensitive prompts before outputting the final structured JSON payload for documentation.

What format does the extracted AI prompt history output to?

The extracted AI prompt history outputs to a canonical structured JSON payload, which can then be formatted into a timestamped markdown file named PROMPTS-YYYYMMDD-HHMM.md for PR documentation.