When to Use This Skill

Activate this skill when any of the following conditions are met:

The user sends a PDF link of a checkup report and asks to analyze or interpret it
The user says things like "help me analyze my checkup report", "look at my health report", "interpret this medical report", or similar requests (in any language)
The user mentions checkup report analysis needs and provides a PDF URL

Note: This skill requires a publicly accessible PDF URL. If the user only sends text content or images (not a PDF link), prompt them to provide a PDF link instead.

⚠️ Privacy Warning

IMPORTANT - READ BEFORE INSTALLING:

This skill uploads your checkup report PDF URL to WiseDiag's cloud servers for AI-powered health analysis.

Do NOT use with sensitive or confidential medical documents unless:

You trust WiseDiag's data handling policies
You accept that file contents will be transmitted and processed remotely

For sensitive documents, use offline/local checkup report analysis tools instead.

WiseAnalyze Skill (powered by WiseDiag)

An AI-powered medical checkup report analysis tool. Submit a publicly accessible PDF URL of a checkup report, and the system will return a structured health interpretation including abnormal items, clinical explanations, lifestyle advice, and personalized recommendations.

The analysis uses an async task model with 4 separate sub-commands. You (the Agent) must call each step and handle polling yourself.

Installation

pip install -r requirements.txt

🔑 API Key Setup (Required)

Get your API key: 👉 https://console.wisediag.com/apiKeyManage

The API key MUST be set as an environment variable. The script reads it automatically.

export WISEDIAG_API_KEY=your_api_key

How to Analyze a Report (Step-by-Step)

NEVER call any API or HTTP endpoint directly. ONLY use the script sub-commands below.

⚠️ IMPORTANT: Each command makes HTTP requests to an external API and may take 10-30 seconds to complete. Do NOT kill or interrupt a running command — wait for it to finish. The script prints progress messages so you can see it is still working.

The workflow has 4 steps. You MUST follow them in order.

Step 1: Submit the PDF URL

cd scripts
python3 wise_analyze.py submit -u "https://example.com/checkup_report.pdf"

With optional health questionnaire (recommended for better results):

python3 wise_analyze.py submit -u "https://example.com/report.pdf" -q "occasional chest tightness, family history of hypertension, poor sleep quality"

With optional member ID to link to a health profile:

python3 wise_analyze.py submit -u "https://example.com/report.pdf" -m "HR1017911158367870xxxx"

Output: The script prints TASK_ID=<id>. Save this task ID for the next steps.

IMPORTANT: The PDF URL must be publicly accessible (no authentication required). URLs ending in .pdf are strongly recommended.

Step 2: Start interpretation

cd scripts
python3 wise_analyze.py start -t "<task_id>"

Output: Prints confirmation that interpretation has started.

Step 3: Poll for progress (YOU must repeat this)

⚠️ CRITICAL: You MUST NOT skip this step. Do NOT jump directly to Step 4.

cd scripts
python3 wise_analyze.py query -t "<task_id>"

Output: The script prints machine-readable status:

STATUS=processing
PROGRESS=50

Polling rules:

If STATUS=queued or STATUS=processing → tell the user the current progress percentage, wait 3-5 seconds, then run the query command again
If STATUS=finish → proceed to Step 4
If STATUS=failed → the task failed, inform the user

You MUST:

Keep calling the query command until STATUS is finish or failed. Do NOT give up after one check.
Report each polling result to the user so they can see the analysis progress (e.g. "Analysis progress: 50%..."). Do NOT silently poll without updating the user.
Never skip Step 3 and go directly to Step 4. The save command will fail if the task is not finished.

Step 4: Save the result

cd scripts
python3 wise_analyze.py save -t "<task_id>" -n "report_2025"

Output: Report saved to ~/.openclaw/workspace/WiseAnalyze/{name}.md (Markdown format).

If -n is not provided, the task ID is used as the filename.

Sub-commands Reference

submit

| Flag | Description | |------|-------------| | -u, --url | Publicly accessible URL of the PDF checkup report (required) | | -q, --questionnaire | Health questionnaire text: symptoms, family history, lifestyle (optional but recommended) | | -m, --member-id | Health profile member ID to link report to existing profile (optional) |

start

| Flag | Description | |------|-------------| | -t, --task-id | Task ID returned from the submit step (required) |

query

| Flag | Description | |------|-------------| | -t, --task-id | Task ID to check status (required) |

save

| Flag | Description | |------|-------------| | -t, --task-id | Task ID to save result (required) | | -n, --name | Output filename stem (default: taskId) | | -o, --output | Output directory (default: ~/.openclaw/workspace/WiseAnalyze) |

Data Privacy

What happens to your files:

The PDF URL is sent to WiseDiag's analysis API
The PDF is downloaded and processed on WiseDiag servers
AI-powered health interpretation results are returned to you
Files are not permanently stored on WiseDiag servers