# Send Pdfreader to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "pdfreader",
    "name": "Pdfreader",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/nantes/pdfreader",
    "canonicalUrl": "https://clawhub.ai/nantes/pdfreader",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/pdfreader",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pdfreader",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "pdf_reader.py",
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "pdfreader",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T00:33:49.375Z",
      "expiresAt": "2026-05-14T00:33:49.375Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pdfreader",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pdfreader",
        "contentDisposition": "attachment; filename=\"pdfreader-1.0.3.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "pdfreader"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/pdfreader"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/pdfreader",
    "downloadUrl": "https://openagent3.xyz/downloads/pdfreader",
    "agentUrl": "https://openagent3.xyz/skills/pdfreader/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pdfreader/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pdfreader/agent.md"
  }
}
```
## Documentation

### PDF Reader Skill for OpenClaw

Extract and read text from PDF files using PyMuPDF.

### Installation

pip install pymupdf

### Usage

# Extract text (first 10 pages by default)
python pdf_reader.py "path/to/file.pdf" 10

# Output to JSON file (for reading)
python pdf_reader.py "path/to/file.pdf" 10 --output=extracted.json

# Read specific number of pages
python pdf_reader.py "path/to/file.pdf" 5

### Features

Extracts text from any PDF
Supports large files
Outputs JSON for AI reading
Handles encoding issues
Shows metadata (title, author, etc.)

### Security Restrictions

For safety, the script enforces:

Input files: Must be .pdf files within the current working directory
Output files: Must be .json files within the current working directory
No path traversal (../) allowed
Files can only be read/written in the directory where the script runs

### Files

pdf_reader.py - Main Python script
SKILL.md - This documentation
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: nantes
- Version: 1.0.3
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-07T00:33:49.375Z
- Expires at: 2026-05-14T00:33:49.375Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/pdfreader)
- [Send to Agent page](https://openagent3.xyz/skills/pdfreader/agent)
- [JSON manifest](https://openagent3.xyz/skills/pdfreader/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/pdfreader/agent.md)
- [Download page](https://openagent3.xyz/downloads/pdfreader)