iLovePDF

View saved version →

---
name: ilovepdf-compress-pdf
description: |
  Compress PDF files to reduce their size while preserving quality.
  Use this skill whenever the user wants to make a PDF smaller, reduce file size,
  or optimize a PDF for sharing or uploading.
---

# iLovePDF — Compress PDF

Reduces PDF file size while preserving visual quality. Ideal for sharing via email,
uploading to platforms with size limits, or general storage optimization.

## When to Use

- "Compress this PDF"
- "Make this PDF smaller"
- "Reduce the file size of this PDF"
- "Optimize this PDF for email"

## Tool to Call

Use the `ilovepdf` or `ilovepdf_attach` MCP tool with `tool: "compress-pdf"`.

Use `ilovepdf_attach` when the user has attached a file to the chat message.
Use `ilovepdf` when the user provides a file URL.

## Accepted File Types

`.pdf`

## Options

| Option              | Type   | Values                              | Default         |
| ------------------- | ------ | ----------------------------------- | --------------- |
| `compression_level` | string | `"recommended"`, `"extreme"`, `"low"` | `"recommended"` |

- **recommended** — Best balance of size reduction and quality.
- **extreme** — Maximum compression; may reduce visual quality noticeably.
- **low** — Minimal compression; preserves quality with modest size reduction.

Only pass `compression_level` if the user explicitly stated a preference.
Default to `"recommended"` otherwise.

## Example Calls

```json
// User attaches a PDF and asks to compress it
{
  "tool": "compress-pdf",
  "options": { "compression_level": "recommended" }
}

// User asks for maximum compression
{
  "tool": "compress-pdf",
  "options": { "compression_level": "extreme" }
}
```

## Notes

- The widget handles the upload, processing, and download — do not attempt to
  process the file yourself or claim the operation is done before the widget confirms.
- Do not ask the user for compression options before calling the tool unless they
  volunteered a preference. The widget provides a fallback UI for those who want to adjust.

View saved version →

---
name: ilovepdf-image-to-pdf
description: |
  Convert JPG, PNG, or TIFF images into a PDF document.
  Use this skill whenever the user wants to turn one or more images into a PDF,
  create a PDF from photos, or combine images into a single PDF file.
---

# iLovePDF — Image to PDF

Converts one or more images (JPG, PNG, TIFF) into a PDF document. Multiple images
can be merged into a single PDF or kept as individual PDFs.

## When to Use

- "Convert this image to PDF"
- "Turn these photos into a PDF"
- "Create a PDF from my JPG files"
- "Combine these images into one PDF"

## Tool to Call

Use the `ilovepdf` or `ilovepdf_attach` MCP tool with `tool: "image-to-pdf"`.

Use `ilovepdf_attach` when the user has attached files to the chat message.
Use `ilovepdf` when the user provides file URLs.

## Accepted File Types

`.jpg`, `.jpeg`, `.png`, `.tif`, `.tiff`

## Options

| Option        | Type    | Values                   | Default      |
| ------------- | ------- | ------------------------ | ------------ |
| `merge_after` | boolean | `true`, `false`          | `true`       |
| `orientation` | string  | `"portrait"`, `"landscape"` | `"portrait"` |
| `margin`      | number  | `0`–`100` (pixels)       | `0`          |
| `pagesize`    | string  | `"fit"`, `"A4"`, `"letter"` | `"fit"`  |

- **`merge_after: true`** — Combines all images into a single PDF (default).
- **`merge_after: false`** — Produces one PDF per image.
- **`pagesize: "fit"`** — Page dimensions match the image dimensions exactly.

Only pass options the user explicitly stated. The widget collects remaining preferences
in-card as a fallback.

## Example Calls

```json
// Convert a single JPG to PDF (defaults)
{ "tool": "image-to-pdf", "options": {} }

// Combine multiple images into one PDF, landscape, A4
{
  "tool": "image-to-pdf",
  "options": { "merge_after": true, "orientation": "landscape", "pagesize": "A4" }
}

// One PDF per image
{ "tool": "image-to-pdf", "options": { "merge_after": false } }
```

## Notes

- The widget handles the upload, processing, and download — do not claim the operation
  is complete before the widget confirms.
- All options are collected by the widget if not provided — do not interrogate the user
  before calling the tool.

View saved version →

---
name: ilovepdf-merge-pdf
description: |
  Combine multiple PDF files into a single PDF.
  Use this skill whenever the user wants to join, merge, combine, or concatenate
  two or more PDF files into one document.
---

# iLovePDF — Merge PDF

Combines multiple PDF files into a single document, preserving the order in which
files are provided.

## When to Use

- "Merge these PDFs"
- "Combine these two files into one"
- "Join my PDF attachments"
- "Concatenate these PDFs in order"

## Tool to Call

Use the `ilovepdf` or `ilovepdf_attach` MCP tool with `tool: "merge-pdf"`.

Use `ilovepdf_attach` when the user has attached files to the chat message.
Use `ilovepdf` when the user provides file URLs.

**Requires at least 2 PDF files.** If only one file is provided, ask the user for the
additional file(s) before calling the tool.

## Accepted File Types

`.pdf` (all files must be PDFs)

## Options

No configurable options. Files are merged in the order they are provided.

## Example Calls

```json
// User attaches two PDFs and asks to merge them
{
  "tool": "merge-pdf",
  "options": {}
}
```

## Notes

- Preserve the attachment order when passing files — the user's stated order is respected.
- The widget handles the upload, processing, and download — do not claim the operation
  is complete before the widget confirms.
- Do not ask the user for merge settings before calling the tool; there are no options
  to configure.

View saved version →

---
name: ilovepdf-office-to-pdf
description: |
  Convert Microsoft Office documents (Word, Excel, PowerPoint) to PDF.
  Use this skill whenever the user wants to turn a .doc, .docx, .xls, .xlsx,
  .ppt, or .pptx file into a PDF.
---

# iLovePDF — Office to PDF

Converts Microsoft Office documents to PDF format. Supports Word, Excel, and
PowerPoint files.

## When to Use

- "Convert this Word document to PDF"
- "Turn this Excel spreadsheet into a PDF"
- "Export this PowerPoint as PDF"
- "Convert my .docx to PDF"

## Tool to Call

Use the `ilovepdf` or `ilovepdf_attach` MCP tool with `tool: "office-to-pdf"`.

Use `ilovepdf_attach` when the user has attached a file to the chat message.
Use `ilovepdf` when the user provides a file URL.

## Accepted File Types

| Format      | Extensions           |
| ----------- | -------------------- |
| Word        | `.doc`, `.docx`      |
| Excel       | `.xls`, `.xlsx`      |
| PowerPoint  | `.ppt`, `.pptx`      |

## Options

No configurable options. The conversion uses iLovePDF defaults.

## Example Calls

```json
// Convert an attached Word document to PDF
{ "tool": "office-to-pdf", "options": {} }
```

## Notes

- The widget handles the upload, processing, and download — do not claim the operation
  is complete before the widget confirms.
- If the user provides a file type that is not in the accepted list (e.g., `.odt`),
  inform them that only the formats listed above are supported.

View saved version →

---
name: ilovepdf-pagenumber
description: |
  Add page numbers to a PDF document.
  Use this skill whenever the user wants to number the pages of a PDF, add a footer
  or header with page numbers, or customize how page numbers appear.
---

# iLovePDF — Add Page Numbers

Adds page numbers to a PDF. Supports full control over position, format, font,
color, and whether to skip the cover page.

## When to Use

- "Add page numbers to this PDF"
- "Number the pages starting from 2"
- "Add a footer with page numbers, skip the first page"
- "Put page numbers at the top right"

## Tool to Call

Use the `ilovepdf` or `ilovepdf_attach` MCP tool with `tool: "pagenumber"`.

Use `ilovepdf_attach` when the user has attached a file to the chat message.
Use `ilovepdf` when the user provides a file URL.

## Accepted File Types

`.pdf`

## Options

| Option                | Type    | Values / Format                             | Default          |
| --------------------- | ------- | ------------------------------------------- | ---------------- |
| `pages`               | string  | `"all"`, `"1-5"`, `"3-end"`, etc.          | `"all"`          |
| `starting_number`     | number  | First displayed number                      | `1`              |
| `text`                | string  | Format string — `{n}` = current, `{p}` = total | `"{n}"`      |
| `first_cover`         | boolean | `true` to skip numbering page 1             | `false`          |
| `vertical_position`   | string  | `"top"`, `"bottom"` only                    | `"bottom"`       |
| `horizontal_position` | string  | `"left"`, `"center"`, `"right"`             | `"center"`       |
| `font_family`         | string  | See list below                              | `"Arial Unicode MS"` |
| `font_size`           | number  | Point size                                  | `12`             |
| `font_color`          | string  | Hex color e.g. `"#000000"`                  | `"#000000"`      |
| `facing_pages`        | boolean | Book-style: odd right, even left            | `false`          |

### Format String Examples

| `text` value      | Output on page 3 of 10 |
| ----------------- | ---------------------- |
| `"{n}"`           | `3`                    |
| `"Page {n}"`      | `Page 3`               |
| `"{n} of {p}"`    | `3 of 10`              |
| `"- {n} -"`       | `- 3 -`                |

### Supported Font Families

`Arial`, `Arial Unicode MS`, `Verdana`, `Courier`, `Times New Roman`,
`Comic Sans MS`, `WenQuanYi Zen Hei`, `Lohit Marathi`

Similar font names are auto-matched (e.g. "Times" → "Times New Roman").

> ⚠️ `vertical_position` supports `"top"` and `"bottom"` only — `"middle"` is not
> supported by the iLovePDF API and will be substituted with `"bottom"`.

## Example Calls

```json
// Default page numbers at the bottom center
{ "tool": "pagenumber", "options": {} }

// Page numbers at top right, skip cover, format "Page N of P"
{
  "tool": "pagenumber",
  "options": {
    "vertical_position": "top",
    "horizontal_position": "right",
    "first_cover": true,
    "text": "Page {n} of {p}"
  }
}
```

## Notes

- The widget handles the upload, processing, and download — do not claim the operation
  is complete before the widget confirms.
- Excluding only the last page in `pages` is not supported by the iLovePDF API.
- Only pass options the user explicitly stated; the widget collects remaining settings in-card.

View saved version →

---
name: ilovepdf-pdf-ocr
description: |
  Extract and make searchable the text in scanned PDFs using OCR (Optical Character Recognition).
  Use this skill whenever the user wants to make a scanned PDF searchable, extract text
  from an image-based PDF, or run OCR on a document.
---

# iLovePDF — OCR PDF

Runs Optical Character Recognition (OCR) on a scanned or image-based PDF, producing
a searchable PDF where the text can be selected, copied, and indexed.

## When to Use

- "Run OCR on this scanned PDF"
- "Make this PDF searchable"
- "Extract text from this scanned document"
- "OCR this PDF in Spanish"
- "Convert this image PDF to a text-selectable PDF"

## Tool to Call

Use the `ilovepdf` or `ilovepdf_attach` MCP tool with `tool: "pdf-ocr"`.

Use `ilovepdf_attach` when the user has attached a file to the chat message.
Use `ilovepdf` when the user provides a file URL.

## Accepted File Types

`.pdf`

## Options

| Option          | Type            | Description                                     | Default      |
| --------------- | --------------- | ----------------------------------------------- | ------------ |
| `ocr_languages` | array of string | Language codes for OCR engine                   | `["eng"]`    |

### Language Codes

Pass `ocr_languages` when the user has stated the document language. Default is English.

Common codes:

| Language   | Code  |
| ---------- | ----- |
| English    | `eng` |
| Spanish    | `spa` |
| French     | `fra` |
| German     | `deu` |
| Italian    | `ita` |
| Portuguese | `por` |
| Chinese (Simplified) | `chi_sim` |
| Chinese (Traditional) | `chi_tra` |
| Japanese   | `jpn` |
| Korean     | `kor` |
| Arabic     | `ara` |
| Russian    | `rus` |

Multiple languages can be combined: `["spa", "eng"]`.

Full list of supported codes: `afr, amh, ara, asm, aze, bel, ben, bod, bos, bul,
cat, ces, chi_sim, chi_tra, dan, deu, ell, eng, epo, est, eus, fas, fil, fin, fra,
gla, gle, glg, guj, heb, hin, hrv, hun, hye, ind, isl, ita, jpn, kan, kat, kaz,
khm, kor, lao, lat, lav, lit, mal, mar, mkd, mlt, mon, msa, mya, nep, nld, nor,
pan, pol, por, ron, rus, sin, slk, slv, spa, sqi, srp, swa, swe, tam, tel, tgl,
tha, tur, ukr, urd, vie, yid`

## Example Calls

```json
// OCR in English (default)
{ "tool": "pdf-ocr", "options": { "ocr_languages": ["eng"] } }

// OCR in Spanish + English
{ "tool": "pdf-ocr", "options": { "ocr_languages": ["spa", "eng"] } }

// OCR in Japanese
{ "tool": "pdf-ocr", "options": { "ocr_languages": ["jpn"] } }
```

## Notes

- The widget handles the upload, processing, and download — do not claim the operation
  is complete before the widget confirms.
- If the user does not mention a language, default to `["eng"]` and let the widget
  provide a language selector as fallback.
- OCR works on scanned/image PDFs. A PDF that already has a text layer may not benefit
  from this operation.

View saved version →

---
name: ilovepdf-pdf-to-jpg
description: |
  Convert PDF pages to JPEG images, or extract embedded images from a PDF.
  Use this skill whenever the user wants to turn a PDF into images, screenshot PDF pages,
  or extract images that are embedded inside a PDF.
---

# iLovePDF — PDF to JPG

Converts a PDF to JPEG images. Can produce one image per page, or extract images
that are embedded within the PDF's content.

## When to Use

- "Convert this PDF to images"
- "Turn each page of this PDF into a JPG"
- "Extract the images from this PDF"
- "Convert PDF to JPG in high quality"

## Tool to Call

Use the `ilovepdf` or `ilovepdf_attach` MCP tool with `tool: "pdf-to-jpg"`.

Use `ilovepdf_attach` when the user has attached a file to the chat message.
Use `ilovepdf` when the user provides a file URL.

## Accepted File Types

`.pdf`

## Options

| Option        | Type   | Values              | Default      |
| ------------- | ------ | ------------------- | ------------ |
| `pdfjpg_mode` | string | `"pages"`, `"extract"` | `"pages"` |
| `quality`     | string | `"Normal"`, `"High"`   | iLovePDF default |

### Mode

- **`pages`** — Renders each PDF page as a separate JPEG image. Use for "convert to images".
- **`extract`** — Extracts images embedded within the PDF content. Use for "extract images from PDF".

### Quality

- **`Normal`** — 150 dpi output.
- **`High`** — 300 dpi output, larger files.

Only pass `quality` if the user explicitly mentioned quality or resolution.

## Example Calls

```json
// Convert each page to JPG (default)
{ "tool": "pdf-to-jpg", "options": { "pdfjpg_mode": "pages" } }

// High quality page conversion
{ "tool": "pdf-to-jpg", "options": { "pdfjpg_mode": "pages", "quality": "High" } }

// Extract embedded images
{ "tool": "pdf-to-jpg", "options": { "pdfjpg_mode": "extract" } }
```

## Notes

- The widget handles the upload, processing, and download — do not claim the operation
  is complete before the widget confirms.
- `quality` only applies to `pdfjpg_mode: "pages"`. It has no effect in extract mode.

View saved version →

---
name: ilovepdf-split-pdf
description: |
  Split a PDF into multiple files by page range, fixed chunk size, or by removing pages.
  Use this skill whenever the user wants to divide, extract pages from, or remove pages
  from a PDF.
---

# iLovePDF — Split PDF

Splits a single PDF into multiple files. Supports splitting by custom page ranges,
fixed chunk sizes, removing specific pages, or splitting by file size.

## When to Use

- "Split this PDF into individual pages"
- "Extract pages 3 to 7 from this PDF"
- "Remove page 5 from this PDF"
- "Split every 2 pages into a separate file"

## Tool to Call

Use the `ilovepdf` or `ilovepdf_attach` MCP tool with `tool: "split-pdf"`.

Use `ilovepdf_attach` when the user has attached a file to the chat message.
Use `ilovepdf` when the user provides a file URL.

## Accepted File Types

`.pdf`

## Options

| Option         | Type    | Values / Format                                   | Default    |
| -------------- | ------- | ------------------------------------------------- | ---------- |
| `split_mode`   | string  | `"fixed_range"`, `"ranges"`, `"remove_pages"`, `"filesize"` | —    |
| `fixed_range`  | number  | Pages per chunk (e.g. `1` for individual pages)   | —          |
| `ranges`       | string  | Page ranges e.g. `"1-3,4-6,7-end"`               | —          |
| `remove_pages` | string  | Pages to remove e.g. `"2,5,8-12"`                | —          |
| `merge_after`  | boolean | Re-merge all ranges into one PDF after split      | `false`    |

### Split Mode Guide

| Mode            | Use When                                                        |
| --------------- | --------------------------------------------------------------- |
| `fixed_range`   | "Split every N pages" — pass `fixed_range: N`                  |
| `ranges`        | "Extract pages X to Y" — pass `ranges: "X-Y"`                  |
| `remove_pages`  | "Remove pages X, Y, Z" — pass `remove_pages: "X,Y,Z"`          |
| `filesize`      | "Split by file size" — collected in-widget                      |

**Keywords:** `"first"` and `"last"` are valid in `ranges` (e.g. `"first-5"`, `"6-last"`).
`"last"` is **not** valid in `fixed_range` or `remove_pages`.

If `split_mode` is not clear from the user's message, pass the tool call without it —
the widget will collect it in-card.

## Example Calls

```json
// Split into individual pages
{ "tool": "split-pdf", "options": { "split_mode": "fixed_range", "fixed_range": 1 } }

// Extract pages 2 to 5
{ "tool": "split-pdf", "options": { "split_mode": "ranges", "ranges": "2-5" } }

// Remove pages 3 and 7
{ "tool": "split-pdf", "options": { "split_mode": "remove_pages", "remove_pages": "3,7" } }
```

## Notes

- The widget handles the upload, processing, and download — do not claim the operation
  is complete before the widget confirms.
- Do not ask the user for split options before calling; the widget provides fallback UI
  for all parameters not supplied.

View saved version →

---
name: ilovepdf-watermark
description: |
  Add a text or image watermark to a PDF.
  Use this skill whenever the user wants to stamp, brand, or overlay text (e.g. "DRAFT",
  "CONFIDENTIAL") or an image onto a PDF document.
---

# iLovePDF — Add Watermark

Adds a text or image watermark to every page (or selected pages) of a PDF.
Supports full control over font, color, position, transparency, rotation, and tiling.

## When to Use

- "Add a DRAFT watermark to this PDF"
- "Stamp CONFIDENTIAL on every page"
- "Add our logo as a watermark"
- "Put a 50% transparent watermark centered on this PDF"

## Tool to Call

Use the `ilovepdf` or `ilovepdf_attach` MCP tool with `tool: "watermark"`.

Use `ilovepdf_attach` when the user has attached a file to the chat message.
Use `ilovepdf` when the user provides a file URL.

## Accepted File Types

`.pdf` (target document)  
For image watermarks: also provide a `.jpg` or `.png` as the watermark overlay.

## ⚠️ Important: Collect Watermark Text Before Calling

For **text mode**, always ask the user for the watermark text in chat **before** calling
the tool. Do not call the tool without it.

## Options

| Option                | Type    | Values / Format                           | Default      |
| --------------------- | ------- | ----------------------------------------- | ------------ |
| `mode`                | string  | `"text"` *(required)*,  `"image"`         | `"text"`     |
| `text`                | string  | Watermark text — **collect in chat first**| —            |
| `font_family`         | string  | See list below                            | —            |
| `font_size`           | number  | Point size                                | `14`         |
| `font_color`          | string  | Hex color e.g. `"#FF0000"`                | —            |
| `font_style`          | string  | `"Bold"`, `"Italic"`, or `null` (Regular) | `null`       |
| `transparency`        | number  | `0`–`100`                                 | `100`        |
| `rotation`            | number  | Degrees                                   | `0`          |
| `layer`               | string  | `"above"`, `"below"`                      | `"above"`    |
| `mosaic`              | boolean | Tile watermark across full page           | `false`      |
| `vertical_position`   | string  | `"top"`, `"middle"`, `"bottom"`           | `"middle"`   |
| `horizontal_position` | string  | `"left"`, `"center"`, `"right"`           | `"center"`   |
| `pages`               | string  | `"all"`, `"1-5"`, `"3-end"`, etc.        | `"all"`      |

### Supported Font Families

`Arial`, `Arial Unicode MS`, `Verdana`, `Courier`, `Times New Roman`,
`Comic Sans MS`, `WenQuanYi Zen Hei`, `Lohit Marathi`

Similar font names are auto-matched (e.g. "Times" → "Times New Roman").

## Example Calls

```json
// Text watermark: DRAFT, centered, 50% transparent
{
  "tool": "watermark",
  "options": {
    "mode": "text",
    "text": "DRAFT",
    "transparency": 50,
    "vertical_position": "middle",
    "horizontal_position": "center"
  }
}

// Diagonal CONFIDENTIAL stamp, red, rotated 45°
{
  "tool": "watermark",
  "options": {
    "mode": "text",
    "text": "CONFIDENTIAL",
    "font_color": "#FF0000",
    "rotation": 45,
    "transparency": 40
  }
}
```

## Notes

- The widget handles the upload, processing, and download — do not claim the operation
  is complete before the widget confirms.
- Excluding only the last page in `pages` is not supported by the iLovePDF API.
- For image watermarks, the user must provide the PDF and the watermark image in the same request.