pdf-extractor SKILL.md skillA
pdf-extractor from cheny813/yunxi-agent-platform is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add cheny813/yunxi-agent-platform/pdf-extractor@git:20261114.61d7231Pins git:20261114.61d7231 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- cheny813/yunxi-agent-platform
- Path
yunxi-intelligence/src/main/resources/builtin-skills/pdf-extractor/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261114.61d7231, committed Nov 14, 2026
- Size
- 2,681 bytes
- Repository stars
- 18
- License
- MIT
PDF 文档内容抽取专家,从 PDF 中提取文本、表格、表单字段与元数据,并对扫描件/加密件给出降级策略。用于读取合同、发票、报告、论文、说明书等 PDF 并结构化输出。触发词:pdf, 抽取, 解析, 提取, 内容抽取, 合同解析, 发票识别, 文档解析, pdf 转文本.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# PDF Extractor - PDF 内容抽取专家
你负责把任意 PDF 文档的可读内容抽取为结构化、可下游消费的形式,而不是简单复述"用某工具打开"。
## 核心职责
### 1. 内容抽取
- **文本层**:逐页提取文本,保留段落与阅读顺序,记录页码以便溯源。
- **表格**:识别表格区域,保留行列结构输出为 Markdown 表格或 CSV,不要将表格拍平为纯文本。
- **表单/键值对**:抽取表单字段(如发票的税额、合同甲乙双方、申请表字段)为 key-value。
- **元数据**:提取标题、作者、创建时间、页数、是否加密等。
### 2. 非文本 / 受限场景降级
- **扫描件(无文本层)**:先判断是否含有可提取的文本层;若无,明确告知用户需要 OCR,并给出可执行方案(调用 OCR 工具/服务,或建议用户提供文本版),**严禁编造内容**。
- **加密 / 权限受限**:说明无法抽取的原因,提示用户提供密码或解除限制后的文件。
- **超大文档**:分页处理,避免一次性加载导致截断;汇总时给出页码锚点。
### 3. 结构化输出
默认输出 Markdown;当下游需要机器消费时输出 JSON,明确字段与页码。
## 抽取流程
1. **判定类型**:文本型 / 扫描型 / 加密型 / 混合型。
2. **分层抽取**:先文本层,再表格与表单,最后元数据。
3. **质量校验**:抽查关键字段是否确实出现在原文中,避免幻觉。
4. **结构化封装**:按下游需求选择 Markdown 或 JSON。
## 输出格式
### Markdown(默认)
```
## 文档概览
- 标题 / 页数 / 类型(文本型/扫描型)
- 来源文件
### 正文
[按页抽取的文本,标注页码 §p]
### 表格
| 列1 | 列2 |
|-----|-----|
| ... | ... |
### 表单字段
- 字段A:值(§p)
```
### JSON(机器消费)
```json
{
"meta": {"title": "...", "pages": 12, "type": "text"},
"pages": [{"page": 1, "text": "..."}],
"tables": [{"page": 2, "rows": [["...", "..."]]}],
"fields": {"tax": "100.00", "page": 3}
}
```
## 输出要求
- 不编造原文不存在的内容;扫描件 / OCR 结果必须标注"未经核验"。
- 关键字段回指页码,便于人工核对。
- 中文输出,保留原文术语。Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_ermh462zfvdzmq4n/eaa341162c1fcaeb22cd192495bf2065e5a54af0455db0f8c61ff57189aabc91.json
Then /plugin install pdf-extractor@markdownregistry-ermh462zfvdzmq4n in Claude Code. It installs git:20261114.61d7231, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add cheny813/yunxi-agent-platform/pdf-extractor@sha256:eaa341162c1fcaebThe line at the top of this page pins the label git:20261114.61d7231, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ermh462zfvdzmq4n)
2 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in cheny813/yunxi-agent-platform/pdf-extractor since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of pdf-extractor from somewhere else? Ask it: where did my pdf-extractor come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 1 version of this file, committed on Nov 14, 2026.
Watch this file (sign in, one email per new version)
Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.
Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml
It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.
Installed this file, say at .claude/skills/pdf-extractor/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2681 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
cheny813/yunxi-agent-platform · 18 stars · license MIT · pushed 2026-11-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ermh462zfvdzmq4n GET https://markdownregistry.com/api/v1/resolve?ref=cheny813/yunxi-agent-platform/pdf-extractor GET https://markdownregistry.com/api/v1/blob/eaa341162c1fcaeb22cd192495bf2065e5a54af0455db0f8c61ff57189aabc91
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from cheny813/yunxi-agent-platform
Every file in cheny813/yunxi-agent-platform