scribe

Log exploratory work, archive files, and capture Git state.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyYAML, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps researchers and developers keep a structured, auditable narrative of exploratory work by logging entries, archiving relevant files, and capturing the Git state for reproducibility.

Core Features & Use Cases

  • Narrative logging: Propose-confirm workflow to capture decisions, experiments, and outcomes.
  • Archiving & retrieval: Archive important files and restore them later for review.
  • Git state capture: Record the repository state and optionally commit the entry to document changes.

Quick Start

Start a new entry by running the prepare subcommand, fill in the title/body, optionally archive files, then finalize to append to the daily log.

Frequently Asked Questions about scribe

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

FAQPage Schema
How do I maintain a living log of experiments and research notes?

To maintain a living log of experiments, use a propose-confirm workflow to capture decisions and outcomes, structure entries with frontmatter, and append finalized records to a daily log for retrieval by time or topic.

How do I capture Git state to anchor my research experiments?

You capture Git state to anchor research experiments by recording the repository state and optionally committing the log entry, ensuring your exploratory work remains reproducible and auditable alongside code changes.

What is the best way to archive files during iterative research workflows?

The best way to archive files in iterative research workflows is to stage important files during your session and retrieve them later for review, preserving the context of your exploratory work.

Do I need PyYAML to use structured frontmatter for research logging?

Yes, you need PyYAML installed to enforce structured frontmatter for research logging, as the dependency enables proper parsing and validation of the metadata anchoring your experiment entries.

Can I retrieve archived experiment files by topic or related entries?

Yes, you can retrieve archived experiment files by time, topic, or related entries, because the logging workflow enforces structured frontmatter that organizes records for targeted retrieval during iterative research.

What are the limitations of using a daily log for exploratory research?

A limitation of using a daily log for exploratory research is that entries are appended sequentially, meaning retrieval depends on structured frontmatter and manual staging rather than automatic relational database querying.