jj

Search Markdown documentation and return relevance-ranked snippets with source citations.

1|Updated Jun 13, 2017
One-click install
npx skills add https://github.com/RoyMcCrain/dotsfile --skill jj-roymccrain
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: jj
Source: https://github.com/RoyMcCrain/dotsfile/tree/main/claude/skills/jj
Command: npx skills add https://github.com/RoyMcCrain/dotsfile --skill jj-roymccrain

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provides fast, source-cited access to Jujutsu (jj) documentation so developers and agents can answer questions using the project's official docs without manual browsing.

Core Features & Use Cases

  • Full-text search across Markdown documentation stored in the skill's references directory, returning context-aware snippets.
  • Preserves and exposes YAML frontmatter metadata (source_url, fetched_at) so responses can always cite the original page and fetch date.
  • Supports JSON-formatted output, a CLI search wrapper, and a documented update workflow that fetches the latest docs via site2skill for Claude-targeted skills.

Quick Start

Search the jj documentation for branching and return the most relevant snippets with source URLs and fetched dates.

Frequently Asked Questions about jj

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

FAQPage Schema
How do I search jujutsu documentation and get source citations?

Search jujutsu documentation by querying Markdown files in the references directory, which returns relevance-ranked snippets with source URLs and fetched dates from YAML frontmatter. The skill extracts metadata to ensure responses cite the original page and fetch date.

Can I get JSON output from a jj docs search?

Yes, the jj docs search supports JSON-formatted output for structured retrieval. The search wrapper invokes scripts to return context-aware snippets and metadata, enabling programmatic integration of documentation results into developer queries.

Do I need uvx to run the jujutsu docs search assistant?

Yes, uvx is a required dependency to run the jujutsu docs search assistant. The skill relies on uvx to execute its search and update scripts, which operate on Markdown files to retrieve and rank documentation snippets.

What is the best way to update jujutsu docs for a Claude chatbot?

Update jujutsu docs by invoking the documented update workflow via scripts/update_docs.py, which fetches the latest documentation using site2skill for Claude-targeted skills. This ensures the Markdown corpus in the references directory stays current.

How does site2skill fetch and convert documentation for Claude?

Site2skill fetches the latest jujutsu documentation and converts it into Markdown files stored in the skill's references directory for Claude-targeted retrieval. This process preserves YAML frontmatter like source_url and fetched_at for accurate citations.