medical-content-compliance-review

medical-content-compliance-review risk review assistant

Quick start

More skills

Overview

The risk review assistant is used to answer "what risks are here," medical science popularization, compliance review, and health content. It is suitable for operations, marketing, healthcare, and education and training to call after clarifying business goals, content materials, or analysis targets. It combines inputs such as medical science popularization drafts, pasted titles, body text, citation bases, action recommendations, and target reader descriptions, organizes key context, and outputs summaries, diagnostic conclusions, action recommendations, and reusable deliverables for continued execution, review, or delivery.

When to use

Applicable scenarios

• The user raises questions such as "what risks are here" and needs to quickly break down goals, determine priorities, and form executable results
• Operations, marketing, healthcare, and education and training need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the risk review assistant
• The user has already prepared uploaded science popularization documents (upload science popularization drafts, review forms, citation materials, or promotional materials.), public science popularization links (fill in science popularization articles, official account previews, or official website pages that can be accessed without logging in.), and medical science popularization drafts (paste titles, body text, citation bases, action recommendations, and target reader descriptions.) and hopes to organize them into executable analysis or optimization results
• The user needs to convert materials related to the risk review assistant into clear conclusions, priorities, and next-step actions

How to call

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

Command example

Basic call

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

Call with common parameters

python3 scripts/run.py --params '{"healthArticleFile":"上传科普文档"}'

Parameter description

Parameter	Type	Required	Default	Description
healthArticleFile	string	No	-	Upload science popularization drafts, review forms, citation materials, or promotional materials
healthArticleLink	string	No	-	Fill in science popularization articles, official account previews, or official website pages that can be accessed without logging in; a complete accessible URL must be provided
healthArticleText	string	No	-	Paste titles, body text, citation bases, action recommendations, and target reader descriptions
claimEvidenceNotes	string	No	-	Supplement citation sources, qualification bases, and diagnostic-treatment-oriented or efficacy-oriented expressions that must not appear
medicalReviewFocus	string	No	风险表述	Choose the direction that needs the highest priority in this medical science popularization content compliance review; optional values:风险表述、证据依据、安全改稿、发布清单
targetReaderContext	string	No	-	Explain the reader population, publishing channel, disease/health topic, institution type, and regional restrictions

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 the parameters contain link fields, pass a complete, accessible URL.

Example request

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

python3 scripts/run.py --params '{"healthArticleFile":"上传科普文档"}'

Equivalent --params JSON：

{
  "healthArticleFile": "上传科普文档"
}

Example of returned results

{
  "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: core results organized around the user's goals that can be directly read, reviewed, or delivered.
• Interpretation of input materials: extract key context and judgment basis by combining uploaded popular science documents (uploaded popular science manuscripts, review forms, citation materials, or promotional materials.), public popular science links (fill in popular science articles, official account previews, or official website pages that can be accessed without logging in.), and medical popular science manuscripts (paste the title, body text, citation basis, action recommendations, and target reader description.).
• Next steps: provide priorities, execution recommendations, or a content framework that can continue to be refined.

Suggestions for using the results

• First determine whether the output answers the user's core questions about the "Risk Review 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