oma-recap

Generate themed Markdown work summaries from AI conversation histories.

46|2|Updated Mar 23, 2025
One-click install
npx skills add https://github.com/gracefullight/krds --skill oma-recap-gracefullight
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oma-recap
Source: https://github.com/gracefullight/krds/tree/main/.agents/skills/oma-recap
Command: npx skills add https://github.com/gracefullight/krds --skill oma-recap-gracefullight

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of manually reviewing scattered AI tool conversation logs to understand what you actually accomplished during a day or time period.

Core Features & Use Cases

  • Daily or windowed recap generation: Summarizes conversation history for a specific date, relative date, or time window into a coherent recap.
  • Theme and project grouping by work content: Groups activity by projects/themes rather than by which AI tool was used, while relegating very short tasks to Miscellaneous.
  • Actionable, user-facing Markdown output: Produces a structured Markdown recap that includes TL;DR, overview, themes or projects, and tool usage patterns, and saves it to .agents/results/recap/.

Quick Start

Run oma-recap for today’s activity and generate a Markdown recap from the available AI conversation history.

Frequently Asked Questions about oma-recap

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

FAQPage Schema
How do I generate daily work summaries from AI chat history?

Work summaries from AI chat history are generated by collecting normalized JSON conversation logs across tools like Claude and Codex, then processing a specified date or time window to output structured Markdown reports for standups or retros.

Can I group standup notes by project themes instead of by AI tool?

Standup notes can be grouped by project themes instead of by AI tool. The recap process organizes conversation activity into content themes, relegating very short tasks to a Miscellaneous category to maintain clear project-driven sections.

Does the recap tool support conversation analysis across multiple AI tools like Claude and Codex?

Conversation analysis supports multiple AI tools including Claude and Codex. It collects normalized JSON conversation history from these platforms, applies date-window resolution rules, and generates a unified recap of cross-platform AI activity.

What is included in the Markdown reporting output for AI recaps?

Markdown reporting output for AI recaps includes a TL;DR, overview, grouped accomplishments organized by project themes, and tool-usage patterns. These structured Markdown files are saved directly to a local agents results recap directory.

Do I need normalized JSON conversation history to run a multi-day work recap?

Normalized JSON conversation history is required to run a multi-day work recap. The tool collects this data via a specific JSON recap command or a local fallback, then applies date-window resolution rules to generate accurate time window reporting.