No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by landing-ai · Agent Tool · ★ 64
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ade-document-processing-skills safe to install? View the security audit →
ADE Document Processing Skills An agent skill for LandingAI's Agentic Document Extraction (ADE): production-ready document AI that converts complex, real-world documents into accurate, structured data with full auditability and traceability. The skill teaches agentic coding assistants (Claude, Cursor, Roo Code, or any agent supporting the Agent Skills convention) how to parse, extract, classify, and split documents, and how to compose those operations into processing pipelines, using the ADE REST APIs or the official Python and TypeScript libraries. No templates or ML training required. Prerequisites A VISIONAGENTAPIKEY from LandingAI (free trial, no credit card required) A Python environment (e.g. uv or venv) if your agent writes Python; the skill installs and other dependencies as needed Installation For Claude Code agents Manual installation Clone the repository: Copy the skill i
| Stars | 64 |
| Forks | 17 |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 71.2680125933381/100 |
| Last Updated | 2026-09-04 |
| Created | 2026-03-13 |
| Platforms | claude-code |
| Est. Tokens | ~17k |
These tools work well together with ade-document-processing-skills for enhanced workflows:
Looking for a ade-document-processing-skills alternative? If you're comparing ade-document-processing-skills with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An MCP server that gives your AI agent agentic RAG over your PDFs, one file or a whole folder: hybrid semantic
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Python, LlamaIndex, LangChain, 15 Property Graph, 4 RDF , 10 Vector, OpenSearch, Elasticsearch, Alfresco, Nuxe
Transform your codebase into an intelligent knowledge base for AI-powered development with Cursor IDE, Google
Claude Code and Codex SKILLs for PDF, Excel, Word, and PowerPoint manipulation — extraction, forms, formulas,
Explore other popular agent tool tools:
ade-document-processing-skills is Agent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants. It is categorized as a Agent Tool with 64 GitHub stars.
You can find installation instructions and usage details in the ade-document-processing-skills GitHub repository at github.com/landing-ai/ade-document-processing-skills. The project has 64 stars and 17 forks, indicating an active community.
ade-document-processing-skills is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ade-document-processing-skills on Agent Skills Hub include pdf-mcp, deepcontext-mcp, claudepro-directory. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: