scribe

Identify and close one documentation gap per session.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/ericklemos/ai-tools --skill scribe-ericklemos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scribe
Source: https://github.com/ericklemos/ai-tools/tree/main/.agents/skills/scribe
Command: npx skills add https://github.com/ericklemos/ai-tools --skill scribe-ericklemos

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Closes one meaningful documentation gap per session, making the codebase easier to understand, maintain, and onboard onto.

Core Features & Use Cases

  • Identifies and fills missing comments, outdated READMEs, and undocumented decisions to improve developer understanding.
  • Creates durable knowledge artifacts (journals, memory indexes, and ADRs) to preserve critical decisions for future work.
  • Supports cross-agent memory linking and structured documentation workflows aligned with project standards.

Quick Start

Identify and close one documentation gap in the current session.

Frequently Asked Questions about scribe

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

FAQPage Schema
How do I identify and fill documentation gaps in my codebase?

Documenting codebase architecture involves creating durable knowledge artifacts like journals, memory indexes, and ADRs. These structured outputs preserve critical decisions and architectural explanations for future development and onboarding.

What is the best way to maintain architectural decision records during regular codebase reviews?

Maintaining architectural decision records during reviews means enforcing a documented process that produces consistent, structured ADRs. This approach captures undocumented decisions to improve long-term codebase understanding and developer onboarding.

Can I use this documentation workflow for cross-agent memory linking and onboarding?

Yes, this documentation workflow supports cross-agent memory linking and structured workflows aligned with project standards. It generates consistent, reviewable outputs that make the codebase easier to onboard onto and maintain.

Does this knowledge-management approach work for diverse codebases with outdated READMEs?

Yes, this knowledge-management approach is applied across diverse codebases to target outdated READMEs and missing comments. It closes one meaningful documentation gap per session to ensure consistent project clarity.