AugmentClaude
Apache-2.0DocsNotes

XERJ Document Search

Search your local files and documents to find facts with their source locations.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/xerj-knowledge-xerj-org/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Works for every skill.

    What this command does
    1. Makes a new, empty temporary folder.
    2. Downloads the skill's folder, plugins/xerj-knowledge/skills/xerj-knowledge, from github.com/xerj-org/xerj (branch main), the GitHub repository it's listed from. You get the version that is there now, not a copy we keep.
    3. Copies that folder to ~/.claude/skills/xerj-knowledge-xerj-org/.
    4. Deletes the temporary folder.

    Installing runs none of the skill's files; it only downloads and copies them. When you later use the skill, Claude follows its SKILL.md and may run scripts that come with it. Read them first.

    How we check skills, and what we don't · Report this skill

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Search the user's own local documents (folders, notes, PDFs, Word, PowerPoint, Excel, EPUB, mail and mbox exports) with XERJ and answer with the file and page each fact came from. Use when the user asks to find something in their files, notes, mail or spreadsheets.

What this skill does

Search local documents with XERJ

XERJ indexes a folder on this machine and returns ranked passages with their source. Nothing is uploaded: the index and the files stay local.

When to use it

  • "Find the contract that mentions the renewal date", "what did we decide about the budget in the March notes", "which spreadsheet has the Q3 numbers".
  • Any question whose answer is in the user's own documents rather than on the web or in a code base.

How

  1. If the folder is not indexed yet, index it once (it is incremental on re-runs, so running it again only picks up changed files): xerj autoindex "<folder>" --prefix <name> Pick a short <name> per folder (for example notes, mail, finance) and reuse it.
  2. Search with the MCP tool xerj_search (a plain-string query is fine), or on the command line: xerj search --prefix <name> "<plain words>". The ranking matches words, not meaning, so use the words the document would use: names, titles, figures, phrases.
  3. Open the passage's source before relying on it when the answer matters.

Citing

  • Every claim in the answer names its source as it was printed: the file path, plus the page (PDF), slide (PPTX), sheet (XLSX) or message (mail) when the hit carries one.
  • If nothing relevant comes back, say so and say what was searched (folder and prefix). Do not fill the gap from memory.

Limits

  • XERJ needs the xerj binary on PATH and a running local node for these tools. If the tool is missing or the node is down, tell the user how to start it (see the plugin README) instead of guessing an answer.
  • Scanned PDFs without a text layer have no text to search.

Related skills