Ready to supercharge your AI agents?

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

PDF & Document Extraction · graniet | DecimalAI

documentationby graniet

PDF & Document Extraction

graniet/ocr-and-documents

Source graniet/kheish ↗License Apache-2.0

Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.

SkillScore88Maintained

Automatic

Doc Ops pack

Last verified 8/23/2026

What it changes

Passed 19 of 22 test cases with the skill, and 9 of 22 without it.

Without skill40%

With skill88%

Checks it passed that the model alone missed

Passes pages 0-4 to extract_pymupdf.py.
Uses web_search to perform paper discovery.
Executes extract_marker.py with the check flag.

and 9 more in the full report

12 fixed10 passed either way3 still failing0 broke

Pass-rate lift: +48 pp
Tokens: +46%
Agent turns: 0%
Response time: -53%

Model gemini-3.6-flashMeasured 8/23/2026v122 of 25 cases passed with skill · 22 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/graniet-ocr-and-documents/SKILL.md https://app.decimal.ai/s/graniet-ocr-and-documents/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add graniet-ocr-and-documents, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/graniet-ocr-and-documents/ and pins it in .decimal/skills.lock

decimalai skills add graniet-ocr-and-documents

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/graniet-ocr-and-documents/SKILL.md https://app.decimal.ai/s/graniet-ocr-and-documents/SKILL.md

Raw file: /s/graniet-ocr-and-documents/SKILL.md ↗ · machine-readable summary at /s/graniet-ocr-and-documents.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

I need to read document metadata such as title and author from `whitepaper.pdf` using a helper script. What flag should be passed?

What was checked, without and with the skill
Checked	Without skill	With skill
Passes the metadata flag to extract_pymupdf.py.	Missed	Passed

case-23 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md172 lines3 filesincludes scripts

Kheish Compatibility

This skill is repo-local and stays inactive until explicitly activated.

When the original instructions refer to legacy tool names, use these Kheish mappings:

terminal => bash
web_extract => web_fetch, plus web_search when discovery is needed
search_files => grep_search and glob_search
browser_* tools require a browser-capable surfaced tool or MCP; if none is available, use the closest available surface and say so explicitly

When the instructions mention local helper files, resolve them from ${KHEISH_SKILL_DIR}.

PDF & Document Extraction

For DOCX: use python-docx (parses actual document structure, far better than OCR). For PPTX: see the powerpoint skill (uses python-pptx with full slide/notes support). This skill covers PDFs and scanned documents.

Step 1: Remote URL Available?

If the document has a URL, always try web_extract first:

web_extract(urls=["https://arxiv.org/pdf/2402.03300"])
web_extract(urls=["https://example.com/report.pdf"])

This handles PDF-to-markdown conversion via Firecrawl with no local dependencies.

Only use local extraction when: the file is local, web_extract fails, or you need batch processing.

Step 2: Choose Local Extractor

Feature	pymupdf (~25MB)	marker-pdf (~3-5GB)
Text-based PDF	✅	✅
Scanned PDF (OCR)	❌	✅ (90+ languages)
Tables	✅ (basic)	✅ (high accuracy)
Equations / LaTeX	❌	✅

Track record

Benchmark

19 / 22

test cases passed, vs 9 / 22 without

Adoption

Users: 1
Times used: 46

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

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

graniet / kheish

skills/productivity/ocr-and-documents/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 2 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Kheish Compatibility

PDF & Document Extraction

Step 1: Remote URL Available?

Step 2: Choose Local Extractor

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills