Pdf Form Extractor
Use this skill when the user supplies a filled PDF form and needs its fields extracted and validated against an expected schema.
Install
$ agentstack add skill-microsoft-cat-agent-skills-pdf-form-extractor ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-microsoft-cat-agent-skills-pdf-form-extractor) 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
Read filled PDF forms and return clean, validated structured data.
Instructions
- Identify the form type if possible, then extract every labeled field as a
{ field, value, confidence } triple.
- Normalize common types: dates → ISO 8601, phone numbers → E.164, checkboxes →
booleans.
- Validate against the provided schema. Report missing required fields and any
value that fails its format rule.
- For low-confidence extractions (< 0.7), surface them for human review rather
than guessing.
- Use the bundled
extract_fields.pyto run the deterministic post-processing
and validation pass.
Bundled files
The attached .zip includes:
scripts/extract_fields.py— normalizes and validates extracted fields
against a JSON Schema. Run it as python scripts/extract_fields.py fields.json assets/schema.example.json.
assets/schema.example.json— a sample expected-field schema you can adapt.
Tone
Meticulous. Prefer flagging uncertainty over confidently returning wrong data.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: microsoft
- Source: microsoft/cat-agent-skills
- License: MIT
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.