yj-ocr-parser

yj-ocr-parser is a skill for Claude Code, Codex from UnicomAI/wanwu. It costs 153 tokens per session (1,550 once invoked), scanned A, original, Apache-2.0.

A document parser that converts PDF files and JPG, PNG, or JPEG images into structured Markdown text. It can preserve headings, tables, mathematical formulas, and links to extracted images.

In plain words
What is it for?
Use it to extract editable text, tables, formulas, and images from PDFs and supported image files.
Why use it?
It removes the need to copy text and table contents manually from documents or scanned images.

Skill for Claude CodeCodex

About the project

Wanwu is an enterprise platform for building AI agents, workflows, retrieval-augmented applications, and managing models in multi-tenant environments. It is designed for developers and enterprise teams delivering AI applications and integrations. The catalogue entries provide skills and agents for using the platform.

UnicomAI/wanwu · 2,456 stars · on GitHub

Install

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.

agentmods
npx agentmods add skills/unicomai/wanwu/yj-ocr-parser
Any agent
npx skills add UnicomAI/wanwu --skill yj-ocr-parser
Clone the repo
git clone --depth 1 https://github.com/UnicomAI/wanwu

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for yj-ocr-parser

README.md
[![agentmods](https://agentmods.dev/badge/skills/unicomai/wanwu/yj-ocr-parser.svg)](https://agentmods.dev/skills/unicomai/wanwu/yj-ocr-parser)
Your own site
<a href="https://agentmods.dev/skills/unicomai/wanwu/yj-ocr-parser"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/yj-ocr-parser.svg" alt="Measured on agentmods" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,550 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00153 $0.01550
Opus 5 $0.00077 $0.00775
Sonnet 5 $0.00031 $0.00310
Haiku 4.5 $0.00015 $0.00155

Measured yesterday against content hash ad7c95e515b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

yj-ocr-parser scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. **调用 API**:使用 curl 发送 multipart/form-data 请求
configs/microservice/bff-service/configs/agent-skills/ontology/yj-ocr-parser/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

文档解析技能(yj-ocr-parser)

本技能调用文档解析模型 API,将 PDF 文件和图片(jpg/png/jpeg)解析为结构化的 Markdown 格式内容,支持标题层级、表格、公式、图片等复杂元素的提取与转换。

适用场景

  • 用户需要解析 PDF 文档或图片(jpg/png/jpeg)并获取 Markdown 格式内容
  • 用户需要提取 PDF/图片中的表格、公式、图片等信息
  • 用户需要将 PDF 文档或图片内容转换为可编辑的文本格式
  • 用户提到"解析文档"、"PDF转MD"、"提取文档内容"、"图片解析"、"图片转文字"等需求

变量要求

  • 本技能需要 MaaS_model_token,其值为文档解析 API 的访问令牌(Access Token)
  • 平台会把已配置的技能变量注入到系统提示中,形如 MaaS_model_token = <token>,位于"已为当前技能配置"的变量列表里。请直接使用系统提示中提供的该变量值,不要依赖 shell 环境变量(沙箱中不会导出 $MaaS_model_token
  • 如系统提示中未提供该变量,需提醒用户:请在技能变量中配置 MaaS_model_token,值为有效的 API 访问令牌

使用步骤

  1. 确认文件:确认用户提供了本地 PDF 或图片(jpg/png/jpeg)文件路径
  2. 检查格式:验证文件扩展名是否为支持的格式(pdf、jpg、jpeg、png),不支持 SVG 等矢量图格式
  3. 获取变量值:从系统提示中"已为当前技能配置"的变量列表读取 MaaS_model_token 的值
  4. 调用 API:使用 curl 发送 multipart/form-data 请求
  5. 返回结果:将解析结果呈现给用户

API 调用方式

使用以下 curl 命令调用文档解析 API:

curl --location 'https://maas-api.ai-yuanjing.com/openapi/v1/rag/model_parser_file' \
  --header 'Authorization: Bearer {MaaS_model_token}' \
  -F 'file=@"{本地文件路径}"' \
  -F 'file_name={文件名}'

注:{MaaS_model_token} 需替换为系统提示中"已为当前技能配置"列出的该变量值,而非 shell 环境变量展开($MaaS_model_token 在沙箱中为空)。

参数说明

参数名 必选 类型 说明
file multipart file 需解析的文件本地路径,支持 PDF 和图片(jpg/jpeg/png),以文件流形式上传
file_name string 文档名称,例如:test.pdf、image.jpg

认证方式

请求头中需携带 Authorization: Bearer {MaaS_model_token},其中 {MaaS_model_token} 取自系统提示中为本技能配置的变量值(直接填入该值,不要使用 shell 环境变量)。

执行流程

当用户请求解析 PDF 文档或图片时,按以下步骤执行:

  1. 获取用户提供的文件路径,验证文件存在且为支持的格式(pdf、jpg、jpeg、png)
  2. 若文件为不支持的格式(如 SVG、gif、bmp 等),提示用户仅支持 PDF 和图片(jpg/jpeg/png)
  3. 从系统提示中"已为当前技能配置"的变量列表读取 MaaS_model_token 的值,若未提供则提示用户在技能变量中配置
  4. 提取文件名(从路径中获取文件名部分)
  5. 执行 curl 命令调用 API
  6. 检查返回结果:
    • code"200" 表示成功,返回 content 字段中的 Markdown 内容
    • code"400" 表示请求参数错误,提示用户检查文件和参数
    • code"429" 表示令牌限流,提示用户稍后重试
    • code"500" 表示服务内部错误,提示用户稍后重试
  7. 将解析出的 Markdown 内容呈现给用户

返回结果处理

API 成功返回时的响应结构:

{
  "code": "200",
  "status": "success",
  "message": "文档处理完成",
  "content": "解析出的Markdown内容",
  "trace_id": "请求追踪ID"
}

Read the full file on GitHub · 120 lines

Changes

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.

  1. yesterday First seen · 120 lines · 153 tokens per session scan A ad7c95e515b3

Subscribe to this mod's changes

yj-ocr-parser is a skill published in the GitHub repository UnicomAI/wanwu (2,456 stars, last pushed today), licensed Apache-2.0. It adds 153 tokens to every session and 1,550 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

design-drawing-svg-md

Use when converting vector PDF engineering drawings (steel-structure shop drawings, A0 drawings, linework-only PDFs without a text layer) into LLM-consumable dual-carrier records — semantic Markdown reading thread plus layered SVG geometry archive linked by shared IDs and crosswalk.

znlgis/opengis-skills · 61 tokens

Book2Skill

Convert one or more TXT, Markdown, DOCX, or PDF documents into a reusable skill zip backed by normalized Markdown, extracted images, and a grounded JSONL knowledge index. Invoke this skill before inspecting task files, then execute its workflow directly without listing directories.

zhimaAi/chatwiki · 56 tokens

adding-knowledge

Use when an agent needs to search documents, PDFs, or reference material — covers R2R collection setup, document ingestion, Knowledge MCP wiring, per-tenant collection scoping, and knowledge package architecture.

Artesiana/agent2 · 44 tokens

pdf

PDF files: create, read, merge, fill, OCR, edit text.

NousResearch/hermes-agent · 18 tokens

markitdown

Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

K-Dense-AI/scientific-agent-skills · 61 tokens

pdf-toolkit

Structured .pdf operations: extract text/tables, merge pages from multiple PDFs, split a PDF by page ranges, fill PDF form fields, and generate fresh PDFs from JSON. Trigger when the user wants programmatic PDF work without natural-language rewriting — examples: pull tables from a report, combine three PDFs, extract…

opensquilla/opensquilla · 127 tokens