ai-pdf

ai-pdf PDF Organizer Assistant

Overview

The PDF Organizer Assistant is used to answer "What are the key points of the PDF," document processing, material review, and summarization. It is suitable for operations, product, marketing, and technical personnel to call after clarifying business objectives, content materials, or analysis targets. It combines inputs such as PDF body text or excerpts, pasteable PDF OCR text, table of contents, key chapters, table excerpts, or content the user has already copied... to organize key context and output summaries, diagnostic conclusions, action recommendations, and reusable deliverables, making it easy to continue execution, review, or delivery.

When to Use

Applicable Scenarios

When users ask questions such as "What are the key points of the PDF" and need to quickly break down objectives, determine priorities, and form executable results
When operations, product, marketing, and technical personnel need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the PDF Organizer Assistant
When the user has already prepared the reading objective (for example, quickly understand, risk screening, pre-investment reading, preliminary contract screening, material transcription, or generating an external briefing.), report readers (explain who will read this PDF review result, such as management, clients, legal, research teams, or internal colleagues.), and public PDF link (enter a PDF link that can be accessed without login; for permission-protected files, upload or paste the body text instead.), and wants to organize it into executable analysis or optimization results
When users need to turn materials related to the PDF Organizer Assistant into clear conclusions, priorities, and next-step actions

How to Call

Call the AI Skills API directly through the exported Python runner:

Command Examples

Basic Call

python3 scripts/run.py --params '{}'

Call with Common Parameters

python3 scripts/run.py --params '{"goal":"阅读目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
`goal`	string	No	-	For example, quickly understand, risk screening, pre-investment reading, preliminary contract screening, material transcription, or generating an external briefing
`audience`	string	No	-	Explain who will read this PDF review result, such as management, clients, legal, research teams, or internal colleagues
`materialUrl`	string	No	-	Enter a PDF link that can be accessed without login; for permission-protected files, upload or paste the body text instead; must be a complete accessible URL
`materialFile`	string	No	-	Upload the PDF file that needs summarization, review, key point extraction, or conversion into a briefing
`materialText`	string	No	-	Can paste PDF OCR text, table of contents, key chapters, table excerpts, or paragraphs the user has already copied
`brandRequirements`	string	No	-	Supplement terminology preferences, sensitive information handling, page number clues that must be retained, content that cannot be shared externally, and output tone

See the complete machine-readable parameter structure at references/form-schema.json。

Parameter Value Reference

The current skill has no categorical parameters that require additional table lookup.

Supported Input Formats

The current skill directly accepts JSON parameters; if a parameter contains a link field, pass a complete, accessible URL.

Example Request

The following example parameters can be passed directly to scripts/run.py, and the runner will send them to the AI Skills API.

python3 scripts/run.py --params '{"goal":"阅读目标"}'

Equivalent --params JSON：

{
  "goal": "阅读目标"
}

Example return result

{
  "success": true,
  "data": {
    "message": "示例结果请以技能真实返回结构为准。"
  },
  "meta": {
    "executionTime": 842,
    "cached": false
  }
}

Deliverables

Summary, diagnostic conclusions, action recommendations, and reusable deliverables: organize the core results around the user's goals that can be directly read, reviewed, or delivered.
Interpretation of input materials: combined with the reading goal (for example, quick understanding, risk screening, pre-investment reading, initial contract screening, material transcription, or generating an external briefing.), report readers (explain who will read this PDF review result, for example, management, clients, legal, research teams, or internal colleagues.), public PDF link (enter a PDF link that can be accessed without logging in; for files protected by permissions, please upload or paste the main text instead.) to extract key context and the basis for judgment.
Next steps: provide priorities, execution suggestions, or a content framework that can be further processed.

Suggestions for using the results

First determine whether the output answers the user's core questions about the "PDF Organization Assistant".
Then check whether the results cover the summary, diagnostic conclusions, action recommendations, and reusable deliverables, and whether clear next steps are provided.
If there is little input material, it is recommended to have the user supplement the goals, audience, constraints, or original materials before running.

Preparation before running

AISKILLS_BASE_URL: default https://ai-skills.ai
AISKILLS_API_KEY: required, used for authenticated calls
AISKILLS_TENANT_ID: default default