Agent skills for developers using AI agents with PDF4me. This repo currently includes the pdf4me-api skill, which helps an agent work with PDF, Word, Excel, and image processing tasks through the PDF4me REST API.
Install the pdf4me-api skill and select Codex when prompted:
npx skills add https://github.com/pdf4me/pdf4me-skills.git --skill pdf4me-apiStart a new Codex session after installation so the skill is discovered. You can
invoke it explicitly with $pdf4me-api, or describe a PDF4me task and let Codex
select it automatically.
This repo is also a Claude Code plugin marketplace. From inside Claude Code:
/plugin marketplace add pdf4me/pdf4me-skills
/plugin install pdf4me@pdf4me-plugin
If the install summary asks you to, run /reload-plugins to activate the skill.
To try it without installing:
claude --plugin-dir /path/to/pdf4me-skillsnpx skills add https://github.com/pdf4me/pdf4me-skills.git --skill pdf4me-apiOnce installed, the skill is automatically available to the agents you chose during installation. Do note: sometimes agents also require you to activate the skill after installation.
In Codex, invoke the skill explicitly with $pdf4me-api. In Claude Code the skill is namespaced by the plugin, so you can invoke it explicitly with /pdf4me:pdf4me-api. In either agent, you can also describe a PDF4me task and let the agent trigger the skill automatically.
- A PDF4me API key from
https://dev.pdf4me.com/dashboard/#/api-keys/ - Access to the PDF4me REST API at
https://api.pdf4me.com
The skill follows the Agent Skills format:
skills/pdf4me-api/SKILL.md- Skill manifest, routing, and usage guidanceskills/pdf4me-api/references/- API reference notes grouped by feature areaskills/pdf4me-api/scripts/- Executable helpers for common flows