install-pdf-full

SkillDocs & knowledge

Install the full PDF parser (pdftext + marker-pdf + CPU-only torch, ~1.5 GB) into an isolated venv. Needed for complex layouts, tables, figures, scanned documents. Skip this if /rtfm:install-pdf (~50 MB, text only) is enough.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the install-pdf-full skill

What this skill tells your AI

The instructions your AI receives, as published by roomi-fields/rtfm in skills/install-pdf-full/SKILL.md and read by ahel’s review.

Warn the user first: this downloads ~1.5 GB (torch CPU-only build is ~500 MB, marker-pdf and its deps add the rest). Confirm they want to proceed before running.

If confirmed, run this command via the Bash tool:

"${CLAUDE_PLUGIN_ROOT}/bin/rtfm-install-extras" pdf-full

After it completes, tell the user to restart Claude Code, then run rtfm_sync to re-index PDFs with the richer parser.

The install uses the PyTorch CPU index (https://download.pytorch.org/whl/cpu) to avoid pulling the default 5 GB CUDA build. No GPU required.

Signals

GitHub stars: 25
Forks: 6
Last commit: Sep 2026

Advanced

Item type: skill
Key: install-pdf-full
Source: github.com/roomi-fields/rtfm

github.com/roomi-fields/rtfm

install-pdf-full

What this skill tells your AI

Signals

Related picks