mcpbeat

Compdf Convert Images To Documents

compdfkit/compdf-convert-images-to-documents

Convert image files into Word, Excel, PPT, PDF, HTML, RTF, CSV, TXT, or JSON with ComPDF. Use for screenshots, scans, receipts, forms, and photo-based business documents that need editable or structured output.

59k tokens
context cost
the whole folder, loaded on every use
5
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
104
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/ComPDFKit/compdf-skills --skill compdf-convert-images-to-documents

What comes with it

232 694 bytes besides the instruction
agents/openai.yaml
references/endpoint-index.md
references/official-api-reference.md
scripts/sync_official_api_reference.py

The instruction itself

7 sections, as written by the author

ComPDF Convert Images to Documents

Overview

ComPDF Convert Images to Documents helps AI agents transform screenshots, scans, receipts, forms, and photo-based business files into editable or structured outputs. It supports image-to-Word, image-to-Excel, image-to-PPT, image-to-PDF, image-to-HTML, image-to-RTF, image-to-CSV, image-to-TXT, and image-to-JSON workflows, making it easy to bridge visual files into searchable, reusable content.

Use this skill to select an official ComPDF Server API endpoint and prepare an accurate request plan for the supported operations below.

Supported Operations

| Operation | Official page or index section |

| --- | --- |

| Image to Word | image-to-word |

| Image to Excel | image-to-excel |

| Image to PPT | image-to-ppt |

| Image to PDF | img-to-pdf |

| Image to HTML | image-to-html |

| Image to RTF | image-to-rtf |

| Image to CSV | image-to-csv |

| Image to TXT | image-to-txt |

| Image to JSON | image-to-json |

Scope

Accept image sources only. Route PDF sources and document-to-PDF requests to their focused skills.

Workflow

  • Identify the source file type, desired output, and requested operation.
  • Read references/endpoint-index.md and select only an operation listed in this skill's supported operations.
  • Read the matching heading in references/official-api-reference.md. Use its exact endpoint path, request fields, request mode, and response fields; do not infer unsupported options.
  • Prefer synchronous mode for small interactive work. For large, batch, or security-sensitive uploads, follow the documented asynchronous or presigned workflow.
  • Resolve the API key before preparing the request. Read the first non-empty line from COMPDF_API_KEY_FILE when set. Otherwise read %USERPROFILE%\.compdf\api_key on Windows, or ~/.config/compdf/api_key on macOS and Linux. Pass the value only as the x-api-key header; never put it in code, logs, examples, or output.
  • Before an operation that overwrites, deletes, decrypts, applies permanent protection, or sends a document externally, identify affected files and obtain confirmation unless the user has already authorized it.
  • Return the endpoint, method, content type, complete request fields, expected task/result fields, and the next polling or download step. Preserve original files unless replacement is explicitly requested.

API Key

Use one local, private key file so later ComPDF tasks do not require pasting an API key into chat. The file must contain only the API key on its first non-empty line. Do not create, commit, upload, or display this file.

When the selected file is absent, unreadable, or empty, direct the user to obtain a key at https://www.compdf.com/compdf-portal/signin?utm_source=github&utm_medium=referral&utm_campaign=compdf_skills_repo_en&ref_platform_id=github_compdfkit_skills_en, save it in the selected file, and retry.

Maintainer

Refresh the local official snapshot before release, then inspect the diff for renamed endpoints, changed fields, and changed enum values:

python scripts/sync_official_api_reference.py

How to use it

Copy the folder

Take compdfkit/compdf-convert-images-to-documents from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.