How do I install the Ingest skill?

Run npx skillmds@latest add damionrashford/ingest in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Ingest skill do?

Ingest and vectorize PDFs or text files for RAG retrieval. Use when the user provides a PDF, document, or text file they want to analyze, study, or generate content from. It is listed under AI & ML on SkillMD.

Is Ingest safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ingest?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ingest free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ingest?

damionrashford (@damionrashford) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ingest by damionrashford — Agent Skill

Name: Ingest
Author: damionrashford

File contents

Ingest Documents

Ingest a PDF or text file into the local vector store for retrieval-augmented generation.

Workflow

Run the ingest script:

bun "${CLAUDE_SKILL_DIR}/scripts/ingest.mjs" $ARGUMENTS

Verify ingestion:

bun "${CLAUDE_SKILL_DIR}/scripts/list.mjs"

Confirm to the user: number of chunks and pages. Suggest next actions: report, flashcards, quiz, slides, audio, mind map, infographic, or data table.

Querying ingested sources

To retrieve relevant chunks for any generation task:

bun "${CLAUDE_SKILL_DIR}/scripts/query.mjs" "<question>" --top-k 15

Gotchas

First run downloads the all-MiniLM-L6-v2 model (~23MB). Subsequent runs use cache.
Large PDFs (100+ pages) take 2-5 minutes on CPU — embedding is the bottleneck.
Scanned/image-only PDFs are automatically OCR'd via Tesseract.js (first OCR run downloads ~15MB language data). Use --no-ocr to skip.
The store persists at ~/.notebook-plugin/ across sessions. Use clear to reset.
Multiple files can be ingested into the same store — they're all searchable together.

Additional resources

For supported formats and embedding details, see references/formats.md

Frequently asked questions

Ingest