Ready to supercharge your AI agents?

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

pdf · gulmezeren2-byte | DecimalAI

documentationby gulmezeren2-byte

pdf

gulmezeren2-byte/pdf

Source gulmezeren2-byte/claude-skills-doctor ↗License MIT

Extract text, tables and form fields from PDFs, including scanned pages routed through OCR, with page ranges and layout preserved.

NewMaintained

Automatic

Doc Ops pack

Last verified 8/3/2026

What it changes

Passed 11 of 18 test cases with the skill, and 12 of 18 without it.

Without skill68%

With skill59%

Checks it passed that the model alone missed

Uses csv.writer to output extracted rows
Checks len(page.extract_tables()) > 0 before parsing tables

2 fixed11 passed either way5 still failing4 broke

Pass-rate lift: -9 pp
Tokens: -9%
Agent turns: 0%
Response time: +3%

Model gemini-3.6-flashMeasured 8/3/2026v113 of 22 cases passed with skill · 18 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/gulmezeren2-byte-pdf/SKILL.md https://app.decimal.ai/s/gulmezeren2-byte-pdf/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add gulmezeren2-byte-pdf, 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/gulmezeren2-byte-pdf/ and pins it in .decimal/skills.lock

decimalai skills add gulmezeren2-byte-pdf

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

curl -fsSL --create-dirs -o .claude/skills/gulmezeren2-byte-pdf/SKILL.md https://app.decimal.ai/s/gulmezeren2-byte-pdf/SKILL.md

Raw file: /s/gulmezeren2-byte-pdf/SKILL.md ↗ · machine-readable summary at /s/gulmezeren2-byte-pdf.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

We need to parse `q3_earnings.pdf` and export all embedded tables directly into CSV files. What tool and code pattern accomplishes this table-to-CSV extraction?

What was checked, without and with the skill
Checked	Without skill	With skill
Uses csv.writer to output extracted rows	Missed	Passed
Calls page.extract_tables() to parse tables from q3_earnings.pdf	Passed	Passed

case-09 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md3 linessingle file

pdf

Extract text and tables from PDF documents.

Track record

Benchmark

11 / 18

test cases passed, vs 12 / 18 without

Adoption

Users: 1
Times used: 21

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

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

gulmezeren2-byte / claude-skills-doctor

examples/demo-home/.claude/skills/pdf-tools/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

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