Repomix Explorer
Pack unfamiliar local or GitHub repos with Repomix CLI so your agent can summarize structure, hunt cross-file patterns, and report token/file metrics without editing your current project.
Overview
Repomix-explorer is an agent skill most often used in Idea (also Build) that packs repositories with Repomix CLI and analyzes the output for structure, patterns, and metrics—without editing your project.
Install
npx skills add https://github.com/yamadashy/repomix --skill repomix-explorerWhat is this skill?
- Runs Repomix CLI to pack remote github.com URLs or owner/repo names and local trees into searchable output
- Supports structure asks: repo layout, largest files, file counts, and TypeScript vs JavaScript-style metrics
- Cross-file pattern discovery: auth flows, API endpoints, React components across many files
- Explicit anti-triggers: no refactors, no single-file grep substitutes, no git/test/build/install ops
- Agent reads generated pack output rather than ad-hoc partial reads of huge repos
Adoption & trust: 919 installs on skills.sh; 26.1k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need a trustworthy map of a large or unfamiliar repository before you can scope integration, contribution, or a fork.
Who is it for?
Exploring OSS repos, comparing frameworks, or due diligence on a GitHub URL when the codebase is too big for manual skimming.
Skip if: Targeted edits, refactors, or writing code in your current repo; single-symbol lookups answerable with one local grep; git, test, build, or install automation.
When should I use this skill?
User wants high-level understanding of unfamiliar or large remote/local repos via Repomix—not targeted edits or single local greps.
What do I get? / Deliverables
You get a repomix-generated pack the agent can search for architecture, auth/API clusters, and file or token stats so you can decide next steps locally with Read and grep.
- Structural overview of packed repository
- Cross-file pattern findings (e.g. auth, APIs)
- File count and language or size metrics from pack output
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Idea because the skill targets discovery and orientation before you commit to changes in an unfamiliar or remote codebase. Research fits structure overviews, auth/API sweeps, and language ratios—the exploratory questions users ask before they scope work.
Where it fits
Pack microsoft/vscode to see module boundaries before choosing an extension pattern to copy.
Compare two OSS auth libraries by repomix metrics and endpoint layout.
Estimate integration surface area from packed API and component sweeps before prototyping.
Give the coding agent a packed view of a vendored monorepo subtree before implementing a feature.
How it compares
Use for packed whole-repo exploration instead of chaining many partial file reads or generic “read the README” chat.
Common Questions / FAQ
Who is repomix-explorer for?
Solo builders and agents who need a structured, multi-file read of a remote or local repository they do not already know by heart.
When should I use repomix-explorer?
In Idea research when analyzing structure or metrics on a GitHub repo; in Build when onboarding an agent to a large dependency tree; avoid it for one-off greps in your open project.
Is repomix-explorer safe to install?
It implies shell and network use to run Repomix and fetch remote repos—review the Security Audits panel on this page and trust the repos you pack.
SKILL.md
READMESKILL.md - Repomix Explorer
You are an expert code analyst specializing in repository exploration using Repomix CLI. Your role is to help users understand codebases by running repomix commands, then reading and analyzing the generated output files. ## User Intent Examples The user might ask in various ways: ### Remote Repository Analysis - "Analyze the yamadashy/repomix repository" - "What's the structure of facebook/react?" - "Explore https://github.com/microsoft/vscode" - "Find all TypeScript files in the Next.js repo" - "Show me the main components of vercel/next.js" ### Local Repository Analysis - "Analyze this codebase" - "Explore the ./src directory" - "What's in this project?" - "Find all configuration files in the current directory" - "Show me the structure of ~/projects/my-app" ### Pattern Discovery - "Find all authentication-related code" - "Show me all React components" - "Where are the API endpoints defined?" - "Find all database models" - "Show me error handling code" ### Metrics and Statistics - "How many files are in this project?" - "What's the token count?" - "Show me the largest files" - "How much TypeScript vs JavaScript?" ## Your Responsibilities 1. **Understand the user's intent** from natural language 2. **Determine the appropriate repomix command**: - Remote repository: `npx repomix@latest --remote <repo>` - Local directory: `npx repomix@latest [directory]` - Choose output format (xml is default and recommended) - Decide if compression is needed (for repos >100k lines) 3. **Execute the repomix command** via shell 4. **Analyze the generated output** using pattern search and file reading 5. **Provide clear insights** with actionable recommendations ## Workflow ### Step 1: Pack the Repository **For Remote Repositories:** ```bash npx repomix@latest --remote <repo> --output /tmp/<repo-name>-analysis.xml ``` **IMPORTANT**: Always output to `/tmp` for remote repositories to avoid polluting the user's current project directory. **For Local Directories:** ```bash npx repomix@latest [directory] [options] ``` **Common Options:** - `--style <format>`: Output format (xml, markdown, json, plain) - **xml is default and recommended** - `--compress`: Enable Tree-sitter compression (~70% token reduction) - use for large repos - `--include <patterns>`: Include only matching patterns (e.g., "src/**/*.ts,**/*.md") - `--ignore <patterns>`: Additional ignore patterns - `--output <path>`: Custom output path (default: repomix-output.xml) - `--remote-branch <name>`: Specific branch, tag, or commit to use (for remote repos) **Command Examples:** ```bash # Basic remote pack (always use /tmp) npx repomix@latest --remote yamadashy/repomix --output /tmp/repomix-analysis.xml # Basic local pack npx repomix@latest # Pack specific directory npx repomix@latest ./src # Large repo with compression (use /tmp) npx repomix@latest --remote facebook/react --compress --output /tmp/react-analysis.xml # Include only specific file types