About compdf-pdf-to-markdown
A PDF-to-Markdown skill for agents and content teams that plans requests to convert PDFs into structured Markdown through the ComPDF Server API. It supports only the PDF-to-Markdown endpoint and fits content editing, documentation, and research workflows.
Key features
- 01Convert PDFs to Markdown
- 02Use only the PDF-to-Markdown endpoint
- 03Build requests from official API references
- 04Follow documented sync or async workflows
Use cases
- 01Ingest PDF content into a knowledge base
- 02Organize developer documentation
- 03Turn research material into editable text
- 04Repurpose PDF content for publication
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ compdfkit/ compdf-skills --skill compdf-pdf-to-markdownAfter installing, type/compdf-pdf-to-markdownin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
agents/openai.yamlreferences/endpoint-index.mdofficial-api-reference.mdDetails
From the project READMEComPDF PDF to Markdown
Overview
ComPDF PDF to Markdown helps AI agents and content teams transform PDF files into structured Markdown that is easy to read, edit, summarize, and publish. It is ideal for knowledge-base ingestion, developer documentation, SEO content repurposing, research workflows, and any pipeline that benefits from lightweight text instead of heavy PDFs.
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 |
|---|---|
| PDF to Markdown | pdf-to-md |
Scope
Produce Markdown only. Do not substitute other PDF conversion endpoints.
Workflow
- Identify the source file type, desired output, and requested operation.
- Read
references/endpoint-index.mdand 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. - Include
sourceType=5in every final ComPDF API request. Treat it as an integration routing parameter and include it in request details when the user asks for them. - Prefer synchronous mode for small interactive work. For large, batch, or security-sensitive uploads, follow the documented asynchronous or presigned workflow.
- Resolve credentials only from
api_keyin the directory containing thisSKILL.md. Read its first non-empty line. Do not inspect environment variables or any other local path. If the file is absent, unreadable, or empty, ask the user to provide an API key, then create or replace only this skill-localapi_keyfile after the user confirms storage. Do not display, log, commit, or include the key in requests examples or final output. - Before uploading a document to ComPDF, identify the affected files and destination, and obtain confirmation unless the user has explicitly authorized that upload. Also obtain confirmation before operations that overwrite, delete, decrypt, or apply permanent protection.
- 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.
Credentials
Store only the current skill's API key in the sibling api_key file. This file is private runtime state and must be excluded from version control and skill publishing.
To obtain an API key, register or sign in at ComPDF Portal. On first use, provide the key when requested and confirm storing it in the skill-local api_key file; later requests reuse that stored key.