Install
$ agentstack add skill-datalayer-agent-skills-pdf ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
PDF Skill
Required Environment Variables
- None required.
Invocation Contract
- Call
run_skill_scriptwith: skill_name:pdfscript_name: one ofcheck_fillable_fields,extract_form_field_info,fill_fillable_fields,convert_pdf_to_images,check_bounding_boxes,create_validation_image,fill_pdf_form_with_annotations- These scripts are positional-argument based. Use
args, notkwargs, for required parameters.
Scripts API
script_name: check_fillable_fields
args:[""]- Output: prints whether the PDF has fillable fields.
script_name: extract_form_field_info
args:["", ""]- Output: JSON file with discovered fields and metadata.
script_name: fill_fillable_fields
args:["", "", ""]- Input contract: field values JSON structure documented in
forms.md.
script_name: convert_pdf_to_images
args:["", ""]- Output: PNG images (one per page).
script_name: check_bounding_boxes
args:[""]- Input contract:
fields.jsonformat documented informs.md. - Output: validation messages.
script_name: create_validation_image
args:["", "", "", ""]- Output: image with overlay boxes for inspection.
script_name: fill_pdf_form_with_annotations
args:["", "", ""]- Input contract: annotated form JSON schema in
forms.md.
run_skill_script Examples
- Extract field info:
{
"skill_name": "pdf",
"script_name": "extract_form_field_info",
"args": ["form.pdf", "fields.json"]
}
- Fill fillable fields:
{
"skill_name": "pdf",
"script_name": "fill_fillable_fields",
"args": ["form.pdf", "field_values.json", "filled.pdf"]
}
Direct CLI Examples
python agent_skills/skills/pdf/scripts/check_fillable_fields.py form.pdf
python agent_skills/skills/pdf/scripts/extract_form_field_info.py form.pdf fields.json
python agent_skills/skills/pdf/scripts/fill_fillable_fields.py form.pdf field_values.json filled.pdf
python agent_skills/skills/pdf/scripts/convert_pdf_to_images.py form.pdf out_images/
python agent_skills/skills/pdf/scripts/check_bounding_boxes.py fields.json
python agent_skills/skills/pdf/scripts/create_validation_image.py 1 fields.json out_images/page_1.png validated.png
python agent_skills/skills/pdf/scripts/fill_pdf_form_with_annotations.py form.pdf fields.json annotated.pdf
References
forms.md: required JSON structures for form workflows.reference.md: additional PDF workflow guidance.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: datalayer
- Source: datalayer/agent-skills
- License: BSD-3-Clause
- Homepage: https://agent-skills.datalayer.tech
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.