Programmatic PDF work inside any agent chat: extract tables, fill forms, merge, annotate, generate from templates. The boring-but-daily document tasks, automated.
$npx skills add anthropics/pdfInstalls into the current project.
Run `npx skills use "https://github.com/anthropics/skills" --skill "pdf-skill"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/anthropics/skills" that are relevant to the current task. Run `npx skills add "https://github.com/anthropics/skills"` and select the relevant skills, then follow their instructions.
| 1 | |
| 2 | Programmatic PDF workflows: extract, fill forms, |
| 3 | merge, annotate, generate from templates. |