Skill registry
Business operationsPublic skills

PDF Document Management

The complete PDF operating layer for AI agents — 57 tools for inspecting, extracting, generating, converting, manipulating, securing, and filling PDFs. Pure Rust, zero dependencies, local-only.

What this skill teaches

A reusable playbook for a specific kind of work.

An MCP server tells an agent which actions are available. A skill adds the judgment around those actions: how to recognize the job, which sequence to follow, what to avoid, and how to decide that the result is complete.

Orchestrate PDF operations — inspect structure, extract text/tables/metadata, generate business documents (invoices, contracts, certificates), convert between formats, manipulate pages, secure with encryption/redaction, and fill forms. Use when working with PDFs, creating invoices, extracting data from documents,…

Architecture

How PDF Document Management guides an ADK-Rust agent.

The skill stays readable and portable because it contains instructions rather than service credentials or business data. ADK-Rust supplies it to the agent, the agent chooses from its reviewed tool boundary, and the connected MCP server performs the authenticated operation.

01

User request

The agent receives a goal expressed in ordinary language.

02

PDF Document Management skill

Matches intent, supplies the decision guide, and narrows the tool boundary.

03

ADK-Rust agent

Plans the workflow and streams each meaningful step through the runtime.

04

mcp-pdf

Executes authenticated operations against the system that owns the capability.

05

Verified result

The skill's completion rules shape the evidence returned to the user.

Portable instructions: SKILL.md · Capability boundary: mcp-pdf · Allowed tools: 57

Decision guide

How the agent turns a request into the right action.

These routes come directly from the skill instructions. They help the model recognize intent and select a focused tool or workflow instead of improvising across the entire capability surface.

01

"what is this PDF", "inspect", "info"?

WORKFLOW 1: Inspect & Classify

02

"extract", "get text", "tables", "data from PDF"?

WORKFLOW 2: Extract Data

03

"create", "generate", "invoice", "contract", "certificate"?

WORKFLOW 3: Generate Document

04

"convert", "to markdown", "to HTML", "to PDF"?

WORKFLOW 4: Convert

05

"merge", "split", "rotate", "compress", "watermark"?

WORKFLOW 5: Manipulate

06

"encrypt", "redact", "secure", "PII", "sensitive"?

WORKFLOW 6: Secure

07

"fill form", "form fields", "submit"?

WORKFLOW 7: Forms

08

Unclear?

inspect_pdf first to understand what we're working with

Proven workflows

Repeatable sequences for useful outcomes.

A workflow joins several tool calls into a task the user actually recognizes. The skill explains the sequence and the intended result while ADK-Rust streams the agent's progress through the shared runtime.

012-4 calls

Inspect & Classify

Understand any PDF (type, health, features)

022-3 calls

Extract Data

Text, tables, metadata, key-values from PDFs

031-2 calls

Generate Documents

Professional invoices, contracts, certificates

041 calls

Convert Formats

PDF ↔ Markdown, HTML, JSON, CSV, Images

051-2 calls

Manipulate Pages

Merge, split, rotate, compress, watermark

062-3 calls

Secure & Protect

PII scan, redaction, encryption, sanitization

Tool boundary

The skill may use 57 documented tools.

This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-pdf retains responsibility for authentication, validation, and the connected system.

inspect_pdf
classify_pdf
health_check_pdf
detect_features
profile_complexity
get_page_count
get_info
repair_pdf
extract_text
extract_page_text
extract_metadata
extract_tables
extract_images
extract_bookmarks
extract_annotations
extract_key_values
create_invoice
create_receipt
create_quote
create_statement
create_purchase_order
create_letter
create_certificate
create_report
create_contract
pdf_to_markdown
pdf_to_html
pdf_to_json
pdf_to_csv
markdown_to_pdf
images_to_pdf
merge_pdfs
split_pdf
split_by_bookmarks
rotate_pages
crop_pages
reorder_pages
delete_pages
compress_pdf
add_watermark
add_headers_footers
add_page_numbers
add_bates_numbers
hash_pdf
encrypt_pdf
decrypt_pdf
set_permissions
scan_sensitive_data
redact_pdf
sanitize_pdf
remove_metadata
detect_active_content
detect_form_fields
fill_form
flatten_form
fill_flat_form
describe_form_layout

Working rules

What the agent should do.

  • Follow the decision guide, use the declared tool boundary, and verify the result before responding.

Operating boundaries

What the agent should avoid.

  • Review the complete SKILL.md before enabling this skill for production work.

Install and connect

Add the skill beside the capability it expects.

Install the repository where your ADK-Rust skill loader can discover it, connect mcp-pdf, and confirm the declared tools are available before asking the agent to use the workflow.

Install the skill
git clone https://github.com/zavora-ai/skill-pdf-document-management.git \
  ~/.skills/skills/pdf-document-management
ADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("pdf-document-management").await?;

let agent = LlmAgentBuilder::new("agent")
    .instruction(skill.instructions())
    .tools(skill.allowed_tools(toolset)?)
    .build()?;

The repository's compatibility statement: Requires mcp-pdf server connected. Pure Rust, zero system dependencies, local-only (no cloud calls).

Official documentation

Read the complete skill package.

The repository remains authoritative for its exact instructions, examples, helper scripts, assets, MCP requirements, license, and later updates.

Source record

Repository metadata for this skill entry.

View public repository ↗
License
Apache-2.0
Allowed tools
57
References
3
Revision
3e49cedb3c91
Updated
May 31, 2026