agentleFS
Sign inStart free
JiamingShi-JsPhysJiamingShi-JsPhys/chelate-shell/skills/fulltext-extractor/SKILL.md

fulltext-extractor

Skill10 starsChanged 6 days agoMITView on GitHub

Extracts the text of a local PDF into `process/` so later stages can read plain text instead of a binary. Uses `pdfminer.six` with a `pypdf` fallback, and can be limited to selected pages.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run this exact form — do not read the source tree:

    line 25
  2. Distinctive:

    Only a page range is needed from a long document.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

fulltext-extractor

Converts a PDF into text files under process/fulltext/. It does not summarise, translate or interpret the text.

  • Stage: ingest · Sandbox: no · Dependencies: pdfminer.six or pypdf

Quick Execution

Run this exact form — do not read the source tree:

python run.py --root <WS> --action extract --input paper.pdf
  • --pages '1-5,8' selects 1-based pages; omit it to extract everything.
  • The text lands in <WS>/process/fulltext/, the gate in <WS>/process/gates/.

When to use

  • A PDF must become text before an ingest or gate stage can read it.
  • Only a page range is needed from a long document.

When NOT to use

  • The file is already text or Markdown.
  • You need OCR of a scanned image-only PDF — this is not an OCR tool.

Actions

--actionDoesExtra arguments
extractPDF → text files--input <pdf> [--pages 1-5,8] [--outdir <dir>]

Hard constraints

  • Read-only on the source. The PDF is never modified.
  • No interpretation. Extracted text is passed through unchanged.

Outputs

  • <WS>/process/fulltext/<stem>.txt — one file per input (plus a JSON index).
  • <WS>/process/gates/fulltext-extractor_<ts>.json — the gate result.

Failure handling

  • An unreadable PDF fails the gate with the backend's message.
  • Neither backend installed → UNVERIFIED with an install hint.

Limitations

  • Image-only PDFs yield no text (no OCR).
  • Layout and tables are flattened to reading order.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free