Satellite OSINT & Land Analysis

Name: Satellite OSINT & Land Analysis
Author: 0-CYBERDYNE-SYSTEMS-0

Engineering Verified v1.0

Repo stars 0
Author updated Live
Author repo FarmFriend-Terminal-React

Fluxly profile Facts only: domain, agents, trust score, runtime, permissions and network

Domain: Engineering
Compatible agents: Claude Code
Cursor
Cline
Codex
Windsurf
Gemini CLI

+20
Trust score: 92 / 100 · audit passed
Author / version / license: @0-CYBERDYNE-SYSTEMS-0 · v1.0 · no license declared
Token usage: Lean
Setup complexity: Guided setup
External API key: Required · Google
Operating systems: macOS
Runtime requirements: No special requirements
Permissions: Read-only
Write / modify
Shell exec
Network behavior: External requests
Install commands: 26 variants

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview satellite-osint-land-analysis.preview

---
name: Satellite OSINT & Land Analysis
description: Open satellite imagery using deeplinks with coordinates and zoom levels via bash `open` command.…
category: engineering
runtime: no special runtime
---

# Satellite OSINT & Land Analysis output preview

## PART A: Task fit
- Use case: Open satellite imagery using deeplinks with coordinates and zoom levels via bash `open` command. Capture screenshots at multiple zoom levels for land analysis, building inventory, structure identification, and agricultural planning. Use when user needs satellite imagery, aerial view, farm analysis, land survey, building detection, structure inventory, property boundaries, coordinates lookup, or OSINT of any location. Triggers on requests for overhead views, map screenshots, or geographic reconnaissance..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “🚀 CRITICAL: Address-First Approach (FASTEST METHOD) / Apple Maps (Preferred - Native macOS, Fastest) / Google Maps (Alternative - Browser-based)” and do not present inference as author intent.

## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Open satellite imagery using deeplinks with coordinates and zoom levels via bash `open` command. Capture screenshots at multiple zoom levels for land analysis, building inventory, structure identification, and agricultural planning. Use when user needs satellite imagery, aerial view, farm analysis, land survey, building detection, structure inventory, property boundaries, coordinates lookup, or OSINT of any location. Triggers on requests for overhead views, map screenshots, or geographic reconnaissance.”.
- **02** When the source has headings, the agent prioritizes “🚀 CRITICAL: Address-First Approach (FASTEST METHOD) / Apple Maps (Preferred - Native macOS, Fastest) / Google Maps (Alternative - Browser-based)” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; may access external network resources; requires Google API keys.

## Running Rules
- read files, write/modify files, run shell commands; may access external network resources; requires Google API keys.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.

SKILL.md SKILL.md

---
name: Satellite OSINT & Land Analysis
description: Open satellite imagery using deeplinks with coordinates and zoom levels via bash `open` command.…
category: engineering
source: 0-CYBERDYNE-SYSTEMS-0/FarmFriend-Terminal-React
---

# Satellite OSINT & Land Analysis

## When to use
- Open satellite imagery using deeplinks with coordinates and zoom levels via bash `open` command. Capture screenshots a…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.

## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.

## Execution rules
- Organize steps around “🚀 CRITICAL: Address-First Approach (FASTEST METHOD) / Apple Maps (Preferred - Native macOS, Fastest) / Google Maps (Alternative - Browser-based)” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; may access external network resources; requires Google API keys.
- Validate with a small sample before expanding the task.

## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.

Evidence boundary and execution chain

The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.

skill "Satellite OSINT & Land Analysis" {
  input      -> user goal + target files + boundaries + acceptance criteria
  context    -> 🚀 CRITICAL: Address-First Approach (FASTEST METHOD) / Apple Maps (Preferred - Native macOS, Fastest) / Google Maps (Alternative - Browser-based)
  rules      -> SKILL.md triggers / order / output contract
  runtime    -> no special runtime | read files, write/modify files, run shell commands | may access external network resources
  guardrails -> requires Google API keys + small-sample validation + diff/log review
  output     -> copyable result + checklist + next iteration
}

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Open satellite imagery using deeplinks with coordinates and zoom levels via bash open command. Capture screenshots at multiple…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “🚀 CRITICAL: Address-First Approach (FASTEST METHOD)”, “Apple Maps (Preferred - Native macOS, Fastest)”, “Google Maps (Alternative - Browser-based)”, “Force Satellite View with AppleScript”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name Satellite OSINT & Land Analysis directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “🚀 CRITICAL: Address-First Approach (FASTEST METHOD) / Apple Maps (Preferred - Native macOS, Fastest) / Google Maps (Alternative - Browser-based)” before expanding.

Boundaries And Review

Dependencies: Prepare Google API keys before running a full task.
Permissions: Declared permissions include read / write / shell-exec; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Satellite OSINT & Land Analysis

Open satellite maps via deeplinks. Capture at multiple zoom levels. Analyze land/structures.

🚀 CRITICAL: Address-First Approach (FASTEST METHOD)

ALWAYS try the address directly in the URL first. Both Google Maps and Apple Maps auto-geocode addresses - no parsing needed!

Apple Maps (Preferred - Native macOS, Fastest)

# Satellite view with address (Apple Maps auto-geocodes)
open "maps://?q=110+Clover+St+Cedar+Creek+Texas&t=h"

# Satellite view with coordinates and zoom
open "maps://?t=h&ll=30.0872,-97.5014&z=18"

Google Maps (Alternative - Browser-based)

# Satellite view with address (Google Maps auto-geocodes)
open "https://www.google.com/maps/search/110+Clover+St+Cedar+Creek+Texas/@?layer=satellite"

# Satellite view with coordinates and zoom
open "https://www.google.com/maps/@30.0872,-97.5014,18z/data=!3m1!1e3"

Force Satellite View with AppleScript

# Activate Maps and set to satellite view (Cmd+3)
osascript -e 'tell app "Maps" to activate' \
  -e 'delay 1' \
  -e 'tell app "System Events" to keystroke "3" using command down'

Only Geocode If:

❌ You need exact lat/lon for calculations
❌ The address format is unusual or international
❌ You're doing multi-location analysis with coordinates

NEVER waste tool calls geocoding when the address works directly in the URL!

Obtaining Coordinates

From Address (Geocoding - No API Key)

# Nominatim/OpenStreetMap - replace spaces with +
ADDRESS="123+Main+St,+Des+Moines,+Iowa"
curl -s "https://nominatim.openstreetmap.org/search?q=${ADDRESS}&format=json" | jq -r '.[0] | "\(.lat),\(.lon)"'

From Device Location (macOS)

# Requires Location Services enabled in System Settings > Privacy
osascript -e 'tell application "System Events" to get the value of location'

# Alternative: Use CoreLocation via swift (more reliable)
swift -e 'import CoreLocation; let m=CLLocationManager(); if let l=m.location { print("\(l.coordinate.latitude),\(l.coordinate.longitude)") }'

From IP (Approximate - Fallback)

curl -s "https://ipapi.co/json" | jq -r '"\(.latitude),\(.longitude)"'

Manual Lookup

Google Maps: Right-click location → "What's here?" → coordinates appear at bottom
Apple Maps: Long-press to drop pin → tap pin → coordinates in info panel
What3Words: Convert 3-word address at what3words.com

From Property Address (Google Geocoding)

# If you have Google API key
curl -s "https://maps.googleapis.com/maps/api/geocode/json?address=123+Farm+Rd,+Iowa&key=YOUR_KEY" | jq -r '.results[0].geometry.location | "\(.lat),\(.lng)"'

URL Patterns (Use with bash `open` command)

Google Maps Satellite

https://www.google.com/maps/@{LAT},{LON},{ZOOM}z/data=!3m1!1e3

ZOOM: 1-21 (21=max detail, 18=buildings clear, 15=property, 12=region)

Google Earth Web

https://earth.google.com/web/@{LAT},{LON},{ALT}a,35y,0h,0t,0r

ALT: altitude in meters (500=high detail, 2000=overview)

Bing Maps Aerial

https://www.bing.com/maps?cp={LAT}~{LON}&lvl={ZOOM}&style=a

Sentinel Hub (Agricultural/NDVI)

https://apps.sentinel-hub.com/eo-browser/?zoom={ZOOM}&lat={LAT}&lng={LON}

ESRI World Imagery

https://www.arcgis.com/home/webmap/viewer.html?center={LON},{LAT}&level={ZOOM}

Execution Examples

Method 1: Direct Address (FASTEST)

# Apple Maps - Single command for address + satellite + screenshot
open "maps://?q=110+Clover+St+Cedar+Creek+Texas&t=h"
sleep 4
screencapture -x ~/Desktop/satellite_capture.png

Method 2: Address with Multi-Zoom (Apple Maps)

ADDRESS="110+Clover+St+Cedar+Creek+Texas"

# Regional view (zoom 12)
open "maps://?q=${ADDRESS}&t=h&z=12"
sleep 4
screencapture -x ~/Desktop/overview_z12.png

# Property level (zoom 16)
open "maps://?q=${ADDRESS}&t=h&z=16"
sleep 4
screencapture -x ~/Desktop/property_z16.png

# Structure detail (zoom 19)
open "maps://?q=${ADDRESS}&t=h&z=19"
sleep 4
screencapture -x ~/Desktop/structures_z19.png

Method 3: Coordinates with Multi-Zoom (Google Maps)

LAT=37.7749; LON=-122.4194

# Regional context
open "https://www.google.com/maps/@${LAT},${LON},12z/data=!3m1!1e3"
sleep 4
screencapture -x ~/Desktop/z12.png

# Property level
open "https://www.google.com/maps/@${LAT},${LON},16z/data=!3m1!1e3"
sleep 4
screencapture -x ~/Desktop/z16.png

# Structure detail
open "https://www.google.com/maps/@${LAT},${LON},19z/data=!3m1!1e3"
sleep 4
screencapture -x ~/Desktop/z19.png

Method 4: With AppleScript for Reliable Satellite View

# Uses AppleScript to force satellite mode and fullscreen for better quality
osascript <<'EOF'
property theAddress : "110 Clover St, Cedar Creek, Texas"

-- Open Apple Maps with satellite view
do shell script "open 'maps://?q=" & theAddress & "&t=h'"

tell application "Maps"
    activate
end tell

delay 2

-- Force satellite view (Cmd+3)
tell application "System Events"
    tell process "Maps"
        keystroke "3" using command down
    end tell
end tell

delay 4

-- Fullscreen for better screenshot
tell application "System Events"
    tell process "Maps"
        keystroke "f" using {command down, control down}
    end tell
end tell

delay 1

-- Capture
do shell script "screencapture -x ~/Desktop/satellite_" & (do shell script "date +%Y%m%d_%H%M%S") & ".png"
EOF

Screenshot commands

screencapture -x ~/Desktop/capture.png          # Silent full screen
screencapture -i ~/Desktop/selection.png        # Interactive select
screencapture -T 5 -x ~/Desktop/delayed.png     # 5 second delay

Visual Verification (CRITICAL STEP)

After opening the map, ALWAYS verify you're looking at the correct location!

# After capture, analyze the screenshot to confirm the address
# Use image analysis to check that the location markers and labels are correct
# If location is wrong:
#   1. Check the address spelling
#   2. Try full address with ZIP code
#   3. Use explicit coordinates instead
#   4. Re-open map and re-capture

Why This Matters:

Last session used approximate town coordinates (Cedar Creek center) instead of actual property
Result: 4 wrong screenshots wasted before discovery
Prevention: Analyze first screenshot to confirm correct location before multi-zoom sequence

Complete Workflow (Agent Must Follow)

Step 1: Detect Input Type

- User provides ADDRESS → Use directly in URL (Method 1 or 2)
- User provides COORDINATES → Use in URL (Method 3)
- User says "my location" → Get device location first

Step 2: Open Map with Address/Coordinates

# Preferred: Apple Maps (faster, native)
open "maps://?q=ADDRESS&t=h"

# Alternative: Google Maps (browser-based)
open "https://www.google.com/maps/search/ADDRESS/@?layer=satellite"

Step 3: Wait for Tiles

sleep 4  # Allow satellite imagery to load fully

Step 4: Capture Screenshot

screencapture -x ~/Desktop/satellite_$(date +%Y%m%d_%H%M%S).png

Step 5: Visual Verification

# Analyze the screenshot:
# - Does it show the correct address?
# - Are the location labels visible?
# - Is the satellite view active (not road view)?
# If NO → Adjust and re-open map

Step 6: Multi-Zoom Analysis (Optional)

# If more detail needed, repeat steps 2-5 at different zoom levels:
# - zoom 12 (regional)
# - zoom 16 (property)
# - zoom 19 (structures)

Zoom Level Reference

Zoom	View Level	Use Case
10-12	County/Region	Context, neighboring properties
13-15	Township	Property boundaries, road access
16-17	Property	Field layout, major structures
18-19	Buildings	Structure identification
20-21	Detail	Roof condition, equipment

Provider Selection

Need	Best Provider
General/Buildings	Google Maps
3D/Terrain	Google Earth
Crop health/NDVI	Sentinel Hub
Alternative imagery	Bing Maps
Historical	Google Earth timeline

Farm Analysis Workflow

Overview (zoom 12): Regional context, access roads
Property (zoom 16): Boundaries, field divisions
Structures (zoom 19): Building inventory
Crop Analysis: Use Sentinel for vegetation indices

Coordinate Format

Use Decimal Degrees (DD):

Latitude: -90 to 90 (negative = South)
Longitude: -180 to 180 (negative = West)
Example: 37.7749, -122.4194

Output Organization

Save captures to organized folders:

~/Desktop/farm_analysis/
├── overview/    (zoom 10-14)
├── property/    (zoom 15-17)
├── structures/  (zoom 18-21)

Integration

Use bash tool to execute open commands. Use sleep 3-5 between URL and screenshot to allow tiles to load. Maximize browser window for best capture quality.

Install command

One-click installPick a runner, click Copy, paste into your terminal, press enter

npx skills add 0-CYBERDYNE-SYSTEMS-0/FarmFriend-Terminal-React/skills/satellite-osint -y

Open general install guide

View skill source

Works with

Claude Code
Cursor
Cline
Codex
Windsurf
Gemini
OpenCode
Roo Code
AAide
+Augment
GitHub Copilot
OpenClaw
KKiro
Junie
WWarp
Goose
Trae
Kilo Code
OpenHands
Amp
Zencoder
CContinue
AIAider
CodeBuddy
CodeGeeX
Replit Agent

Security audit

92 / 100

Verified

未声明 license/许可。
未限定 allowed-tools，默认拥有全部工具权限。

Metadata

Source: github
0-CYBERDYNE-SYSTEMS-0/FarmFriend-Terminal-React
Version: 1.0
中文

More by @0-CYBERDYNE-SYSTEMS-0

Category & tags

Category Engineering

Decide Fit First

Design Intent

How To Use It

Boundaries And Review

Satellite OSINT & Land Analysis

🚀 CRITICAL: Address-First Approach (FASTEST METHOD)

Apple Maps (Preferred - Native macOS, Fastest)

Google Maps (Alternative - Browser-based)

Force Satellite View with AppleScript

Only Geocode If:

Obtaining Coordinates

From Address (Geocoding - No API Key)

From Device Location (macOS)

From IP (Approximate - Fallback)

Manual Lookup

From Property Address (Google Geocoding)

URL Patterns (Use with bash open command)

Google Maps Satellite

Google Earth Web

Bing Maps Aerial

Sentinel Hub (Agricultural/NDVI)

ESRI World Imagery

Execution Examples

Method 1: Direct Address (FASTEST)

Method 2: Address with Multi-Zoom (Apple Maps)

Method 3: Coordinates with Multi-Zoom (Google Maps)

Method 4: With AppleScript for Reliable Satellite View

Screenshot commands

Visual Verification (CRITICAL STEP)

Complete Workflow (Agent Must Follow)

Step 1: Detect Input Type

Step 2: Open Map with Address/Coordinates

Step 3: Wait for Tiles

Step 4: Capture Screenshot

Step 5: Visual Verification

Step 6: Multi-Zoom Analysis (Optional)

Zoom Level Reference

Provider Selection

Farm Analysis Workflow

Coordinate Format

Output Organization

Integration

Discussion

URL Patterns (Use with bash `open` command)