site-condition-assessment

Analyzes photos or videos of plantation staff quarters via vision model to produce structured condition assessments.

1|Updated Jun 21, 2026
One-click install
npx skills add https://github.com/tapway/shogun-os --skill site-condition-assessment-tapway
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: site-condition-assessment
Source: https://github.com/tapway/shogun-os/tree/main/industries/plantation/skills/site-condition-assessment
Command: npx skills add https://github.com/tapway/shogun-os --skill site-condition-assessment-tapway

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Plantation managers need consistent, structured evaluations of staff quarters but manual inspections are slow and inconsistent. This Skill turns a photo or video sent via Telegram into a standardized assessment covering furniture inventory, cleanliness, site condition, and safety hazards. ## Core Features & Use Cases - Vision-Based Assessment: Uses the vision_analyze tool with a structured prompt to inventory furniture, rate cleanliness, evaluate site condition, and detect safety hazards. - Multi-Image and Video Support: Merges results across multiple photos of the same location and handles video tours natively, structuring output by room or area. - Standardized Rubric: Applies the cleanliness and habitability scales defined in references/assessment-rubric.md for consistent ratings. - Use Case: A supervisor photographs a staff quarter and sends it via Telegram; the Skill returns a JSON assessment listing furniture counts, cleanliness ratings, hazards, and the top three priority actions. ## Quick Start Send a photo of a staff quarter and ask the agent to inspect the room and assess its furniture, cleanliness, and condition.

Frequently Asked Questions about site-condition-assessment

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I assess staff quarters condition from a photo?

Send the photo via Telegram and the Skill runs vision_analyze with a structured prompt covering furniture inventory, cleanliness, site condition, and safety hazards. It returns a JSON assessment with ratings and priority actions.

How to inspect a room using a vision model?

Provide an image or video file and the Skill prompts the vision model to list furniture with quantities and condition, rate cleanliness of floors, walls, and bedding, check structural elements, and flag hazards like exposed wiring.

Can I analyze multiple photos of the same location?

Yes. Each photo is analyzed separately, furniture counts are merged with deduplication, and the worst cleanliness or condition rating across photos is used. The output notes which photo each issue appeared in.

Does the assessment support video input?

Yes. Video files are passed directly to vision_analyze with a prompt to describe each room or area, the furniture in each, and overall condition. The response is structured by room or area.

Does this Skill store the inspection report?

No. This Skill only produces the structured assessment. Storing the report is handled separately by the site-inspection-storage Skill.

What are the limitations of photo-based condition assessment?

Single-angle photos may hide furniture, so counts are reported as 'at least N' when uncertain. If the floor is not visible, cleanliness is marked as not visible rather than guessed.