Ready to supercharge your AI agents?

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

Get Started Free →

GLM-OCR Multimodal Deep Analysis · berabuddies | DecimalAI

Registry skillby berabuddies

GLM-OCR Multimodal Deep Analysis

berabuddies/pdf-ocr-layout

Source berabuddies/semia ↗License Apache-2.0

Multimodal document deep analysis tool based on Zhipu GLM-OCR, GLM-4.7, and GLM-4.6V.

SkillScore96Maintained

Automatic

AI Engineer pack

Last verified 8/16/2026

What it changes

Passed 21 of 22 test cases with the skill, and 5 of 22 without it.

Without skill22%

With skill96%

Checks it passed that the model alone missed

Invokes `python scripts/glm_ocr_pipeline.py`.
Identifies `--file_path` as the CLI parameter flag.
Includes zhipuai in the list of Python dependencies.

and 19 more in the full report

17 fixed5 passed either way1 still failing0 broke

Pass-rate lift: +74 pp
Tokens: -14%
Agent turns: 0%
Response time: -66%

Model gemini-3.6-flashMeasured 8/16/2026v122 of 23 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/berabuddies-pdf-ocr-layout/SKILL.md https://app.decimal.ai/s/berabuddies-pdf-ocr-layout/SKILL.md

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

decimalai skills add berabuddies-pdf-ocr-layout

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

curl -fsSL --create-dirs -o .claude/skills/berabuddies-pdf-ocr-layout/SKILL.md https://app.decimal.ai/s/berabuddies-pdf-ocr-layout/SKILL.md

Raw file: /s/berabuddies-pdf-ocr-layout/SKILL.md ↗ · machine-readable summary at /s/berabuddies-pdf-ocr-layout.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 17

Prompt

If a multi-page document at `/data/annual_report.pdf` is passed into `scripts/glm_ocr_pipeline.py` without script modifications, which pages are processed by default?

What was checked, without and with the skill
Checked	Without skill	With skill
States that only the first page of the PDF is processed by default.	Missed	Passed

case-10 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md81 linessingle file

GLM-OCR Multimodal Deep Analysis

This tool builds a high-precision document parsing pipeline: using GLM-OCR for layout element extraction, calling GLM-4.7 for logical interpretation of table data, and calling GLM-4.6V for multimodal visual interpretation of images and charts.

Pipeline Implementation Architecture

This Skill consists of two core script stages, orchestrated through glm_ocr_pipeline.py:

1. Extraction Stage (`scripts/glm_ocr_extract.py`)

Core Model: GLM-OCR
Function: Responsible for physical layout analysis of documents
Output: Extract table HTML and clean to Markdown, automatically crop independent chart image files based on Bbox coordinates, and generate intermediate JSON containing full page reading order

2. Understanding Stage (`scripts/glm_understanding.py`)

Core Model: GLM-4.7 (text) / GLM-4.6V (visual)
Function: Responsible for deep semantic reasoning of content
Logic:
- Tables: Combine full text context, use GLM-4.7 to analyze business meaning of Markdown table data
- Charts: Combine full text context + cropped images, use GLM-4.6V for multimodal visual analysis

Invocation Methods

Command Line Invocation

# Run complete pipeline: extraction -> cropping -> understanding analysis, supports input in .pdf, .jpg, .png and other formats
python scripts/glm_ocr_pipeline.py \
  --file_path "/data/report_page.jpg" \
  --output_dir "/data/output"

API Parameter Description

Parameter	Type	Required	Description
file_path	string	✅	Absolute path to input file (supports .pdf, .png, .jpg)
output_dir	string	✅	Result output directory (used to save cropped images and JSON reports)

Track record

Benchmark

21 / 22

test cases passed, vs 5 / 22 without

Adoption

Users: 0
Times used: 0

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

berabuddies / semia

tests/fixtures/skills/baokui/pdf-ocr-layout/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

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

GLM-OCR Multimodal Deep Analysis

Pipeline Implementation Architecture

1. Extraction Stage (scripts/glm_ocr_extract.py)

2. Understanding Stage (scripts/glm_understanding.py)

Invocation Methods

Command Line Invocation

API Parameter Description

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills

1. Extraction Stage (`scripts/glm_ocr_extract.py`)

2. Understanding Stage (`scripts/glm_understanding.py`)