Glmocr

What it does

When your agent uses it

• The user wants to extract text from images
• Perform OCR on pictures
• Convert images to text
• Process any image files to get their textual content

Example prompts

• “/glmocr”

Requirements

• Python 3
• A credential in ZHIPU_API_KEY
• A credential in YOUR_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1ONLY use GLM-OCR API - Execute the script python scripts/glm_ocr_cli.py
2. 2NEVER parse documents directly - Do NOT try to extract text yourself
3. 3NEVER offer alternatives - Do NOT suggest "I can try to analyze it" or similar
4. 4IF API fails - Display the error message and STOP immediately
5. 5NO fallback methods - Do NOT attempt text extraction any other way

What it can do on your machine

Read from SKILL.md and the folder at commit 2ecd31c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 3 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • bigmodel.cn

  Also links to:

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • ZHIPU_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Glmocr loads about 1.1k tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 89 tokens; SKILL.md has 332 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~89

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from zai-org/GLM-skills at commit 2ecd31c, republished under its Apache-2.0 licence (© zai-org). 332 words, ~1,051 tokens.

name

glmocr

description

Extract text from images using GLM-OCR API. Supports images and PDFs with high accuracy OCR, table recognition, formula extraction, and handwriting recognition. Use this skill whenever the user wants to extract text from images, perform OCR on pictures, scan documents, convert images to text, or process any image files to get their textual content.

python scripts/glm_ocr_cli.py --file-url "URL provided by user"

python scripts/glm_ocr_cli.py --file /path/to/image.jpg

python scripts/glm_ocr_cli.py --file-url "URL" --output result.json

python {baseDir}/scripts/glm_ocr_cli.py (--file-url URL | --file PATH) [--output FILE] [--pretty]

{
  "ok": true,
  "text": "# Extracted text in Markdown...",
  "layout_details": [[...]],
  "result": { "raw_api_response": "..." },
  "error": null,
  "source": "/path/to/file.jpg",
  "source_type": "file"
}

Error: ZHIPU_API_KEY not configured. Get your API key at: https://www.bigmodel.cn/usercenter/proj-mgmt/apikeys

© zai-org, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references) in skills/glmocr of zai-org/GLM-skills.

• SKILL.md
• references/output_schema.md
• scripts/config_setup.py
• scripts/glm_ocr_cli.py
• scripts/requirements.txt

Open the folder on GitHubat commit 2ecd31c