Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Aidenwu0209/PaddleOCR-Skills --skill paddleocr-skills-setupgit clone --depth 1 https://github.com/Aidenwu0209/PaddleOCR-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aidenwu0209/paddleocr-skills/paddleocr-skills-setup)<a href="https://agentmods.dev/skills/aidenwu0209/paddleocr-skills/paddleocr-skills-setup"><img src="https://agentmods.dev/badge/skills/aidenwu0209/paddleocr-skills/paddleocr-skills-setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aidenwu0209/paddleocr-skills/paddleocr-skills-setup"><img src="https://agentmods.dev/badge/skills/aidenwu0209/paddleocr-skills/paddleocr-skills-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 38 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 41 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00102 | $0.00595 |
| Opus 5 | $0.00051 | $0.00298 |
| Sonnet 5 | $0.00020 | $0.00119 |
| Haiku 4.5 | $0.00010 | $0.00060 |
Grade A, and why
paddleocr-skills-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Set up PaddleOCR Skills
Install and verify the two skills from the linked repository. Treat this setup skill as an installer guide; run OCR with the installed target skills.
Use this setup skill when the request mentions PaddleOCR installation or Agent Skills, or asks for 图片转文字 / 截图识字 / 扫描件 OCR / PDF 转 Markdown / 表格提取 / 公式识别 / 版面分析. It installs:
paddleocr-text-recognitionfor screenshots, photos, scans, PDFs, CJK text, line-level OCR, and optional bounding boxes.paddleocr-doc-parsingfor structured Markdown/JSON, tables, formulas, figures, multi-column layout, and correct reading order.
Install
-
Confirm the user wants a global, user-level installation.
-
Check Node.js/npx, Python 3.9+, and
uv. Explain any missing prerequisite before using its official installer. Do not usesudoor change unrelated system settings without permission. -
Run:
npx skills add Aidenwu0209/PaddleOCR-Skills --skill '*' -g -y -
Run
npx skills list -g --jsonand confirm bothpaddleocr-text-recognitionandpaddleocr-doc-parsing, including their actual install paths.
Configure safely
- Use https://www.paddleocr.com for the official API and token flow.
- Ask the user to provide the OCR or document-parsing endpoint only when that target skill needs it.
- Never invent, print, or store
PADDLEOCR_ACCESS_TOKENin chat, command history, source files, or logs. - Report incomplete configuration instead of claiming the OCR service works.
Finish
Report prerequisite versions, commands executed, installed skill names and paths, and any configuration still required from the user.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 58 lines · 102 tokens per session scan A eb690667c4b5
paddleocr-skills-setup is a skill published in the GitHub repository Aidenwu0209/PaddleOCR-Skills (34 stars, last pushed 27d ago), licensed Apache-2.0. It adds 102 tokens to every session and 595 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
paddleocr-doc-parsing
A document-parsing tool configuration for extracting structured Markdown or JSON from complex PDFs and document images, including tables, formulas, charts, and multi-column pages.
paddleocr-text-recognition
An optical character recognition tool configuration for extracting text from images, photos, scans, screenshots, and scanned PDFs. OCR means converting text visible in an image into machine-readable text.
kreuzberg
Extract text, tables, metadata, and images from 91+ document formats (PDF, Office, images, HTML, email, archives, academic) using Kreuzberg. Use when writing code that calls Kreuzberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output…
format-specific-extraction
ZIP archive → Security validation → XML parsing → Text + tables + metadata.
paddleocr-mcp
Use the local PaddleOCR MCP SDK v2 server for image OCR, PDF/document parsing, screenshots, tables, and structured text extraction.
ade
Parse documents and extract schema-shaped data with the ADE (Agentic Document Extraction) v2 APIs through the ade CLI. A local job-item store makes every run idempotent, resumable, and citable — repeat runs are free, interrupted runs resume, and every answer can cite element ids with visual evidence.