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 AgenticAIPlan/AgenticAISkills --skill paddleocr-expertgit clone --depth 1 https://github.com/AgenticAIPlan/AgenticAISkillsWrote 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/agenticaiplan/agenticaiskills/paddleocr-expert)<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/paddleocr-expert"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/paddleocr-expert/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/agenticaiplan/agenticaiskills/paddleocr-expert"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/paddleocr-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00110 | $0.02308 |
| Opus 5 | $0.00055 | $0.01154 |
| Sonnet 5 | $0.00022 | $0.00462 |
| Haiku 4.5 | $0.00011 | $0.00231 |
Grade A, and why
paddleocr-expert 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PaddleOCR Expert
Turn to this skill when the user needs current, practical help with PaddleOCR 3.x, PaddleX-backed deployment, or PaddleOCR-VL. Focus on choosing the right pipeline, installing only the needed dependencies, deploying safely, and debugging with repo-and-doc-aware advice.
Quick Summary
This skill is a PaddleOCR and PaddleX field support copilot.
- Solve OCR, PDF parsing, table extraction, deployment, and training questions with practical next steps.
- Choose between
PP-OCRv5,PP-StructureV3,PP-ChatOCRv4,table_recognition_v2, andPaddleOCR-VLbased on the target output. - Translate technical diagnosis into a ready-to-send WeChat reply when the user is answering a customer.
- Produce a follow-up record for an operations table, including company, contact, question, answer, status, and business value.
Chinese summary:
paddleocr-expert 是一个面向 PaddleOCR / PaddleX 场景的技术支持与客户回访助手。它既能回答 OCR、表格、PDF、部署、微调和显存问题，也能在最后直接生成一条可复制发送的微信回复，以及一条可写入多维表格的回访记录。
Start Here
Infer the user's real goal before suggesting commands:
- Plain text OCR from images or screenshots: start with
PP-OCRv5/OCR. - Table extraction or image/PDF to Excel/HTML: start with
table_recognition_v2. - Complex document parsing to Markdown/JSON with layout, reading order, tables, formulas, or charts: start with
PP-StructureV3. - Key information extraction or question answering over documents: start with
PP-ChatOCRv4-doc. - Strongest multilingual document parsing, irregular layouts, cross-page table merging, or VLM-style parsing: start with
PaddleOCR-VLorPaddleOCR-VL-1.5.
If the user asks about serving, custom YAML, Triton-style deployment, or pipeline registration names, switch mental models from "PaddleOCR only" to "PaddleOCR on top of PaddleX."
If the user is relaying a customer question, also infer the commercial context:
- Who asked: company name, counterpart name or title, and whether the user wants a direct external reply.
- What stage: evaluation, pilot, deployment, fine-tuning, or production issue.
- What artifact is needed: internal diagnosis, external WeChat reply, follow-up record, or all of them.
What ships with it
5 files 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.
- 9d ago First seen · 195 lines · 110 tokens per session scan A f74832506cd2
paddleocr-expert is a skill published in the GitHub repository AgenticAIPlan/AgenticAISkills (11 stars, last pushed 3mo ago), licensed MIT. It adds 110 tokens to every session and 2,308 once invoked, about $0.0006 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.