Community연구 & 데이터 분석github.com

chronolocate

Work out when a photo or video was taken from shadows and the sun's position. Use when the user asks what time or date an image was captured, wants to check a claimed time against shadows, or mentions chronolocation, shadow analysis or SunCalc.

chronolocate란 무엇인가요?

chronolocate is a Claude Code agent skill that work out when a photo or video was taken from shadows and the sun's position. Use when the user asks what time or date an image was captured, wants to check a claimed time against shadows, or mentions chronolocation, shadow analysis or SunCalc.

지원 대상~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Ghongha007/osint-skills/tree/HEAD/skills/chronolocate

Installed? Explore more 연구 & 데이터 분석 skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

chronolocate은(는) 무엇을 하나요?

Estimate the time of day (and sometimes narrow the date) of an image whose location is already known, using the direction and length of shadows.

Before you start

You need three things. If one is missing, say which and stop guessing.

  1. Location as latitude and longitude. If the place is unknown, geolocate first.
  2. A shadow you can measure: cast by something vertical (pole, building edge, standing person) onto roughly flat ground.
  3. Either the date or the time. With the date you can solve for the time. With neither, you can only give a range of combinations.

Method

  1. Find north in the image. Match the image to satellite imagery and draw the shadow on the map. Read its compass direction: 0 is north, 90 east, 180 south, 270 west. Give your reading as a range (for example 60 to 70), not one number.

  2. Measure the ratio if you can. If the object's height and its shadow length can both be estimated (a person is roughly 1.6 to 1.8 m; count paving stones or lane widths for the shadow), note both.

  3. Run the script in this skill's scripts/ folder:

    python3 scripts/sun.py when --lat LAT --lon LON --date YYYY-MM-DD --tz +05:30 --shadow-azimuth 65 --tolerance 5
    python3 scripts/sun.py when --lat LAT --lon LON --date YYYY-MM-DD --tz +05:30 --height 1.7 --shadow-length 2.4
    python3 scripts/sun.py position --lat LAT --lon LON --time 2026-06-21T12:00+05:30
    

    --shadow-azimuth is the direction the shadow points. The script converts it to the sun's direction. Set --tolerance to half the width of your measured range.

  4. Check a claimed time with position: if the claim says 5 pm and the script puts the sun in the west-south-west at 20 degrees, shadows must point east-north-east and be about 2.7 times the object's height. Compare with the image.

  5. Cross-check with anything else visible: clocks, shop shutters, traffic, prayer or school times, weather records for that day, other footage of the same event.

How to report

  • Give a window, never a single minute: "between about 10:15 and 10:40 local time".
  • State what you measured, the range you used, and the assumed date.
  • Shadow length alone matches twice a day (morning and afternoon). Say which one you chose and why (which side the shadow falls on).
  • Say what would change the answer: sloping ground, a leaning object, lens distortion near the frame edge, an uncertain date.

Limits

  • The script ignores atmospheric refraction. Treat results as unreliable when the sun is within about 3 degrees of the horizon.
  • Near the equator around midday, shadows are too short to measure well.
  • Shadows fix the time on a given date, or a pair of dates for a given time (the sun repeats its path on either side of each solstice). They rarely fix a date on their own.
  • A matching shadow is consistent with a claim. It does not prove the claim.

Individual skills in this repo

This repo contains 2 individual skills — each has its own dedicated page.

관련 스킬