Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

PDF Extractor — measured AI agent skill | DecimalAI

kero168/pdf-extractor

SkillScore77Maintained

Extracts text, tables, and form fields from PDF files. Use when the user asks to read, fill, or analyze a PDF document.

by kero168

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Doc Ops pack

decimalai skills pull kero168-pdf-extractor

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/kero168-pdf-extractor/SKILL.md

Raw file: /s/kero168-pdf-extractor/SKILL.md ↗ · machine-readable summary at /s/kero168-pdf-extractor.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

—-74% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-15	✗→✓	▲ Improved	-67%	0%
case-04	✗→✓	▲ Improved	-76%	0%
case-05	✗→✓	▲ Improved	-69%	0%
case-06	✗→✓	▲ Improved	-66%	0%
case-07	✗→✓	▲ Improved	-63%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

kero168 / skillcheck

fixtures/pdf-extractor/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1Bundled 2 files · scripts

Skill contents

scripts/

references/

SKILL.md

PDF Extractor

Extract content from PDF files without sending them to any external service.

Quick start

Read the form-filling guide before editing AcroForm fields.
Run scripts/extract.py with the input path to dump the text layer.
Summarize the extracted content for the user.

Notes

Process large PDFs page by page to keep context small.
For scanned PDFs, tell the user that OCR is out of scope for this skill.

Want to see if kero168/pdf-extractor would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.