REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.
제작자라면 이 코드를 README에 붙여 넣으세요. 배지는 이 페이지로 연결됩니다.
[](https://mcp.popnx.com/en/skills/oldcircle-geo-sleuth)같은 작업에서 AI를 서비스에 연결하는 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
같은 종류의 작업, Skill 목록과 같은 순서
| 이 항목 geo-sleuth | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 제작자 | Oldcircle | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 수 | 1 | 1 | 1 | 1 | 1 |
| GitHub 별 | 7,190 | 465,460 | 233,910 | 149,364 | 144,149 |
| 마지막 코드 변경 | 2026년 11월 16일 | 2026년 11월 17일 | 2026년 4월 20일 | 2026년 11월 17일 | 2026년 11월 17일 |
| 라이선스 | MIT | MIT | – | Apache-2.0 | MIT |
Oldcircle의 Skill(지시 묶음) 1개, AI가 읽고 그대로 일해요 · MCP server가 아니에요
MCP = 손
AI를 외부 서비스나 데이터에 연결합니다(예: Notion 읽기, 청구서 만들기). 프로그램이나 서버가 실행 중이어야 합니다.
Skill = 안내서
작업 방법을 AI에게 가르치는 텍스트 파일. 어떤 서비스에도 연결되지 않습니다.
겹치는 경우도 있습니다. 도구를 부르는 스크립트가 있는 Skill도, 지식만 보내는 MCP도 있습니다. 하려는 작업을 기준으로 고르세요.
Claude CodeCodexCursorGemini CLIGitHub CopilotOpenCode
제작자 README와 repo 폴더 기준
GitHub account Oldcircle (person), 6 years old
★ 7,190 stars · code last changed 2026년 11월 16일
34 scripts that can run on a computer: scripts/baidu_pano.py, scripts/evidence.py, scripts/geo.py, scripts/tiles.py and 30 more
Scripts that go online: scripts/_net.py, scripts/evidence.py, scripts/doctor.py, scripts/poi.py and 1 more
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 8245bf5 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
먼저: 어떤 AI를 쓰시나요
쓰는 앱을 고르면 그 앱의 설치 방법만 보여 드립니다
Uploading to claude.ai would fail: the description is over 200 characters (899). Use "Let the AI install it" instead
이 문장을 복사해 Claude Code 채팅에 붙여 넣으세요
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Claude Code를 다시 열고 /geo-sleuth를 입력하거나 관련 작업을 요청하면 Claude가 알아서 써요
Checked against official docs 2026년 11월 12일 · Source: code.claude.com
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
이미 설치했나요? 먼저 확인 · 터미널을 열고 이 명령을 입력한 뒤 Enter
node -vMac: ⌘ + Space를 누르고 Terminal 입력 후 Enter
Windows: 시작 메뉴를 열고 Windows PowerShell 입력 후 "열기"
아직 설치하지 않았다면: 공식 다운로드 페이지에서 LTS 버전과 클릭형 설치 파일을 고르세요: Mac은 .pkg · Windows는 .msi. 더블클릭 후 끝까지 진행하면 됩니다. curl 명령은 필요 없습니다
설치가 끝나면 터미널을 닫았다가 다시 열고 같은 명령을 실행하세요. 버전 번호가 나와야 합니다: node -v
한 번 설치하면 Node.js가 필요한 모든 도구에서 쓸 수 있습니다
npx skills add Oldcircle/geo-sleuth제작자 README에서 가져온 명령으로, 제작자 코드를 내려받아 실행해요
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
git clone --depth 1 https://github.com/oldcircle/geo-sleuth.git /tmp/popnx-skill-oldcircle-geo-sleuth-8245bf5 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-oldcircle-geo-sleuth-8245bf5/skills/geo-sleuth' ~/.claude/skills/geo-sleuthChatGPT 데스크톱 앱에는 Codex가 들어 있고, Codex는 ~/.agents/skills 폴더에서 Skill을 읽습니다
ChatGPT 데스크톱 앱에서 Codex를 열고 이 문장을 채팅에 붙여 넣으세요
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
geo-sleuth 폴더를 ~/.agents/skills/geo-sleuth에 넣으세요
~는 홈 폴더($HOME)입니다
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
git clone --depth 1 https://github.com/oldcircle/geo-sleuth.git /tmp/popnx-skill-oldcircle-geo-sleuth-8245bf5 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-oldcircle-geo-sleuth-8245bf5/skills/geo-sleuth' ~/.agents/skills/geo-sleuthChecked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com
직접 설치한 Skill은 쓸 수 없고, 디렉터리의 플러그인에 들어 있는 Skill만 쓸 수 있습니다
이 Skill을 ChatGPT에서 쓰려면 위 방법대로 ChatGPT 데스크톱 앱을 쓰세요
Checked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com
이 문장을 복사해 Codex 채팅에 붙여 넣으세요 · ChatGPT 데스크톱 앱 안의 Codex, Codex CLI, IDE 확장 프로그램에서 모두 쓸 수 있습니다
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex는 새로 설치한 Skill을 스스로 찾습니다. 보이지 않으면 Codex를 다시 시작하세요 · 쓰는 법: ChatGPT에서는 @를 입력하고 Skill을 고르세요 · Codex CLI나 IDE 확장 프로그램에서는 /skills를 실행하거나 $ 뒤에 Skill 이름을 입력하세요
Checked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
git clone --depth 1 https://github.com/oldcircle/geo-sleuth.git /tmp/popnx-skill-oldcircle-geo-sleuth-8245bf5 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-oldcircle-geo-sleuth-8245bf5/skills/geo-sleuth' ~/.agents/skills/geo-sleuth이 문장을 복사해 Cursor 채팅에 붙여 넣으세요
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Cursor Agent 채팅에서 /를 입력하고 geo-sleuth 선택
Checked against official docs 2026년 11월 12일 · Source: cursor.com
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
git clone --depth 1 https://github.com/oldcircle/geo-sleuth.git /tmp/popnx-skill-oldcircle-geo-sleuth-8245bf5 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-oldcircle-geo-sleuth-8245bf5/skills/geo-sleuth' ~/.cursor/skills/geo-sleuthSkill을 읽을 수 있는 다른 앱용입니다. 이 문장에는 Claude Code, Codex, Cursor 경로가 들어 있어 AI가 쓰는 앱에 맞게 고릅니다 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026년 11월 12일 · Source: code.claude.com, learn.chatgpt.com, cursor.com
Gemini CLI, GitHub Copilot 같은 다른 Agent Skills 지원 앱은 폴더가 달라요. 그 앱 안내를 보고 SKILL.md가 있는 폴더를 복사하세요.
2026년 11월 11일에 Claude Code, Codex, Cursor 공식 안내로 skill 폴더 확인
✓ 명령 확인 2026년 11월 17일
아래 글은 제작자 repo에서 온 것이며 PopNx MCP의 지시가 아니에요
처음 8,000자 표시 · GitHub에서 전체 파일 열기
---
name: geo-sleuth
description: Geolocate or chronolocate a photo with tool-verified reasoning (where was this taken / when was it taken / photo geolocation / geo-guessing). Given one or more photos, intake.py does metadata, OCR and reverse image search (Baidu/Yandex) in one command; clues and candidates go on a candidate board (board.py) that ranks them and gives the next step; clues.py looks up calling codes, driving side, plates and area codes from region packs; for satellite and street view the machine ranks first and you look only at the top few (CLIP in sat_scan.py, DINOv2+SIFT in match.py); plus sun and shadow math, OSM Overpass and DEM skylines. Every conclusion is checked against real data; output is coordinates + error radius, evidence images and tiered confidence. Use when the user shares a photo and asks where was this taken / geolocate this / when was this taken / 这是哪 / 在哪拍的 / 帮我定位这张照片 / 网络迷踪 / 图寻 / 几点拍的.
---
# geo-sleuth (v2)
Goal: find a location that **holds up under checking**. Every conclusion must point to the clue it used, the command it ran and the file it produced.
> `${CLAUDE_SKILL_DIR}` in commands means the directory containing this SKILL.md (the same for commands in references). Claude Code substitutes it automatically; in other agents, first `export CLAUDE_SKILL_DIR=<absolute path of this directory>` before running (if the shell doesn't keep variables between commands, prefix every command with it), or replace it with that path directly.
The work is split into three layers. Remember this first, then read the flow:
| Layer | Who | Tools |
|---|---|---|
| Decision: which candidates exist, how evidence is scored, whether a candidate can be excluded, what to scan next | **Script** (candidate board) | `board.py` |
| Perception: reading text, table lookups, finding targets in satellite imagery, street-view matching | **Scripts compute and rank first; you look only at the top few** | `intake.py` `ocr.py` `clues.py` `sat_scan.py` `match.py` `geo.py bearings` |
| Judgment: pulling clues out of the image, proposing hypotheses when the tables have nothing, deciding among the machine's top few | **You** | — |
The method comes from breaking down 14 photo-geolocation (网络迷踪) creator videos and 22 puzzles, plus several rounds of blind-test comparisons; the breakdown notes are not published with the repo. The lesson of v1: rules written as prose don't get executed, and two runs of the same skill version gave very different results; so v2 puts every rule that can be written as code into `board.py`.
## Hard rules (always in force; ★ = enforced by board.py, just follow it)
0. If the user says the photo isn't theirs, or the image shows a private residence or minors, ask once what it's for before continuing; when the prompt already states the source or purpose (an evaluation puzzle, a puzzle setter's hint, the user says they took it), don't ask, and go to the finest level as usual.
1. **Don't fabricate verification.** "Measured on the map", "matched street view", "±10 m" must correspond to commands actually run and files actually produced in this session. If you didn't run it, write "unverified".
2. **Precision needs a source**: an error radius ≤100 m requires the intersection of two independent constraints, or a ground-level match on ≥3 invariant features. Before reporting a camera position, run a self-check: `pose.py project --horizon <sea-horizon row>` computes what the pitch should be and each feature's "expected row" for the current camera position; reconcile that with the photo (the depression angle to a target ≠ the camera's pitch; look up the camera position's elevation with `terrain.py elev` — if the height difference doesn't match the depression angles in the image, the camera position is wrong).
3. **Once you have a unique anchor, close the loop**: all later search and geometry starts from the anchor; don't go back to generic features like "blue-green lake water" or "tropical park" and pick the most famous place of that kind.
4. **Compute bearings first, then identify structures**: which block in satellite imagery is the tower or chimney in the photo is itself an interpretation. First compute its true bearing in the image with `sun.py compass` or a confirmed landmark, then use `geo.py bearings` to see which outline around the candidate camera position falls on that bearing; when nothing fits, first try both templates ("original/mirrored", "sunrise/sunset"); if not verified, only lower the tier, don't exclude.
5. ★ **List the whole category before inferring**: when inferring a region from "hill city", "tropical", "IP in a municipality", use `board.py children` to add all subordinate admin divisions as candidates, then rank them with evidence. Don't default to the main urban district, don't pick by population.
6. **Metadata and hints are hypotheses**: when EXIF, IP location, location tags or the puzzle setter's words conflict with the image, the image wins; don't invent a story to reconcile them. IP says country A but the hint or the regulation designs (plates, signs) point to another continent: intersect with `clues.py lookup territories <country A> --continent <continent>`.
7. **Self-consistency**: redo each key judgment once with a different crop or keyword set; if the two results differ by tens of kilometers or more, lower the tier.
8. ★ **If you can't pin a point, give a range + what information is missing**; when the candidates are a few discrete ones, don't take the midpoint: the main answer of `board.py report` is always the top-ranked candidate; the rest go into alternatives with discriminating tests.
9. ★ **Exclusion and confirmation use the same standard**: `board.py exclude` only accepts read/computed clues + a computed file (output of `geo.py frame`, `terrain.py`, etc.); observed and inferred clues can only down-weight via `evidence --against`, with the likelihood ratio clamped to 1/3–3 (inferred) or 1/5–5 (observed). Generating candidates from "there's an X nearby" is also filtering, and X must be something confirmed in the image. Fine-level candidates such as campuses, residential compounds and street segments must go on the board too: add a batch at once with `board.py add --from <poi.py --out / osm.py geom output> --level area/road`, don't hand-pick; when you drop one, write `evidence --against` with a comparison image, and `check` lists candidates without a single piece of evidence (meaning nobody looked at them); a finer candidate goes under the one that contains it (a point under its street segment: `--parent`, or `board.py move`), so its support counts in that level's ranking, and `check` fails when it skips a level; labels from third-party data (tree species in a municipal inventory, an exact school-name match) can only down-weight, never justify exclusion (in two cases the ground truth was skipped by hand exactly this way). **The excluded extent must be ≤ the evidence extent**: for candidates with extent, such as districts, areas and roads, `exclude` needs `--covers lat,lon[:lat,lon]` stating which stretch the evidence covers; the script rejects coverage below half (excluding a whole road after looking at one point on it failed in two cases).
10. ★ **Population and fame are not evidence**; scan order follows "share ÷ pages" (`board.py next`): finish the small districts first, put large districts last with a page cap.
## Flow
You don't have to go through every step: if reverse image search in step 1 hits directly, jump to steps 6 and 7 to confirm. Every step's output goes on the candidate board.
### Step 1: steps 0–3 in one command
```bash
uv run ${CLAUDE_SKILL_DIR}/scripts/intake.py photo.jpg --out-dir intake/ [--box x0,y0,x1,y1 ...]
uv run ${CLAUDE_SKILL_DIR}/scripts/board.py init --photo photo.jpg
```
`intake.py` usually takes 1–2 minutes, longer on the first run because it installs dependencies: give the command a generous timeout (10+ minutes) or run it in the background. If a command timeout 질문하고, 팁을 나누고, 안 되는 점을 알려 주세요. "도움이 됨"이 많은 순서예요.