zai-orgzai-orgOfficial·17 Agent Skills Included

GLM-skills

Document OCR, image generation, and visual content conversion

Extracts text, tables, formulas, and handwriting from images and PDFs, then converts documents into slides, websites, and written reports. Generates images from text prompts, captions visual content, screens resumes, and produces multi-source stock analysis reports. Eliminates manual data entry, reformatting, and repetitive document work through ready-to-run scripts powered by GLM models.
npx skills add zai-org/GLM-skills --all -g -y

All Skills in This Repository (17)

Pure Emerald Level Indicators
📦 In Repo
zai-orgzai-org

glmocr-handwriting

Recognize handwritten text from images and PDFs via GLM-OCR layout parsing.

Official
Intermediate
📦 In Repo
zai-orgzai-org

glm-image-gen

Generate images from text prompts via the GLM-Image API.

Official
Intermediate
📦 In Repo
zai-orgzai-org

glmocr

Extract Markdown-formatted text and layout details from images and PDFs via API key authentication.

Official
Intermediate
📦 In Repo
zai-orgzai-org

glmv-pdf-to-ppt

Convert PDFs into multi-slide HTML presentations with outline JSON and summary markdown.

Official
Advanced
📦 In Repo
zai-orgzai-org

glmv-grounding

Extract normalized grounding coordinates and visualizations from images and videos.

Official
Advanced
📦 In Repo
zai-orgzai-org

glmv-prompt-gen

Generate detailed text prompts from images and videos for AI synthesis.

Official
Intermediate
📦 In Repo
zai-orgzai-org

glmv-stock-analyst

Integrate multi-source data into structured multimodal stock reports.

Official
Advanced
📦 In Repo
zai-orgzai-org

glm-master-skill

Catalog official GLM skills and installation methods with source links.

Official
Basic
📦 In Repo
zai-orgzai-org

glmocr-sdk

Extract structured text, tables, formulas, and labeled regions from images and PDFs.

Official
Intermediate
📦 In Repo
zai-orgzai-org

glmocr-formula

Extract mathematical formulas from images and PDFs into LaTeX format.

Official
Intermediate
📦 In Repo
zai-orgzai-org

glmv-caption

Generate captions and summaries for images, videos, and documents via the GLM-V API.

Official
Intermediate
📦 In Repo
zai-orgzai-org

glmv-pdf-to-web

Convert PDFs into self-contained one-page websites with outline.json.

Official
Advanced

Frequently Asked Questions

FAQPage Schema
How to install GLM-skills?

Run `npx skills add zai-org/GLM-skills --all -g -y` in your terminal to install all skills globally. Most skills also require a free ZHIPU_API_KEY from bigmodel.cn.

What can GLM-skills do with documents?

It extracts text, tables, formulas, and handwriting from images and PDFs, and converts PDFs into slide decks, academic websites, or written reports.

Does GLM-skills work with Claude Code and OpenClaw?

Yes. All skills follow the standard SKILL.md format and run in Claude Code, OpenClaw, OpenCode, and similar coding agents.

Can I generate images from text prompts?

Yes. The glm-image-gen skill creates high-quality images from text descriptions with control over size, quality, and watermarks.

Do I need coding experience to use GLM-skills?

No. Once installed with your API key, your agent runs the underlying scripts automatically based on plain-English requests.

Related Repositories in Content & Communication

View All in Content & Communication