← Back to Skills Marketplace
unixweb

Foto Webcam

by unixweb · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
1242
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install foto-webcam
Description
Liste und Snapshot-Abruf von Webcams (insb. foto-webcam.eu). Verwende diese Skill-Anleitung, wenn John „webcam <nummer>“ schreibt, eine Webcam-Favoritenliste pflegen will, oder wenn ein aktuelles Snapshot-Bild von einer foto-webcam.eu Webcam als JPG im Chat gesendet werden soll.
README (SKILL.md)

Foto-Webcam Snapshots

Ziel: Aus einer gespeicherten Favoritenliste (Nummer -> Webcam-Seite) ein aktuelles Bild holen und an John schicken.

Datenquelle (Favoriten)

Standard-Datei im Workspace:

  • docs/webcams/favorites-muenchen.json

Format (Beispiel):

  • items[].id (int)
  • items[].name (string)
  • items[].page (URL zur Webcam-Seite)
  • optional items[].image (direkte Bild-URL)

Typische Nutzerbefehle

  • webcam 1
  • webcam 3+4+5
  • liste
  • liste webcams
  • fuege \x3Cname> \x3Curl> hinzu

Workflow: webcam N -> Bild senden

  1. Lade Favoritenliste aus docs/webcams/favorites-muenchen.json.
  2. Suche Eintrag mit id gleich N.
  3. Erzeuge Snapshot Bild
    • Wenn image gesetzt ist lade diese Bild URL
    • Sonst page URL nehmen und daraus current 1200 jpg ermitteln
  4. Speichere Bild nach /tmp/webcam N jpg
  5. Sende Bild im Chat als Attachment Caption Format Webcam N Name

Workflow: webcam 3+4+5 -> mehrere Bilder

  1. Parse die IDs als Liste von Integers in der Reihenfolge
  2. Fuer jede ID
    • Snapshot holen
    • Ein Bild senden
  3. Maximal 6 Bilder pro Anfrage, wenn mehr gefragt wird erst nachfragen

Workflow: liste -> Favoritenliste schicken

Sende eine Text Liste Webcam 1 Name Webcam 2 Name usw

Keine Formatierung, nur Plain Text

Ermittlung der Bild-URL (foto-webcam.eu)

Für eine Webcam-Seite wie:

  • https://www.foto-webcam.eu/webcam/zugspitze/

existiert meist ein direktes „current“ Bild:

  • https://www.foto-webcam.eu/webcam/zugspitze/current/1200.jpg

Praktisch: HTML mit User-Agent laden und nach einem Link auf .../current/\x3Cdigits>.jpg suchen.

Script

Nutze das Script:

  • skills/public/foto-webcam/scripts/foto_webcam_snapshot.py

Beispiele:

  • Snapshot über Favoriten-ID:

    • python3 skills/public/foto-webcam/scripts/foto_webcam_snapshot.py --favorites docs/webcams/favorites-muenchen.json --id 4 --out /tmp/webcam4.jpg

  • Snapshot über URL:

    • python3 skills/public/foto-webcam/scripts/foto_webcam_snapshot.py --url https://www.foto-webcam.eu/webcam/zugspitze/ --out /tmp/zugspitze.jpg

Pflege / Ergänzen

  • Neue Webcam hinzufügen: ergänze favorites-muenchen.json (neue id, name, page).
  • Wenn eine Quelle instabil ist, kann image gesetzt werden (direkter JPG-Link).

Wichtig: Antworten im Chat nur als Plain Text (kein Markdown). Für Audio nur „clean speech“ (keine Sonderzeichen/Formatierung).

Usage Guidance
This skill appears internally consistent and performs only web fetches and local file I/O. Before installing, verify the favorites JSON (docs/webcams/favorites-muenchen.json) to ensure it doesn't contain unwanted or internal-network URLs, ensure the runtime has the Python 'requests' package available, and be aware the skill will make outbound HTTP(S) requests to the page/image URLs contained in the favorites. If you need to restrict network scope, sanitize the favorites file or run the skill in a restricted environment. The script may print error JSON and re-raise exceptions on failure, so expect error output if a fetch fails.
Capability Analysis
Type: OpenClaw Skill Name: foto-webcam Version: 1.0.0 The skill bundle is designed to fetch and display webcam snapshots from foto-webcam.eu. The `SKILL.md` file clearly outlines the purpose, workflows, and explicit script usage, without any instructions that could lead to prompt injection against the agent. The `foto_webcam_snapshot.py` script uses standard Python libraries (`requests`, `os`, `re`) to download images from specified URLs and save them to a temporary local path (`/tmp/`). There is no evidence of data exfiltration, malicious execution, persistence, or obfuscation; all actions are directly aligned with the stated purpose of retrieving webcam images.
Capability Assessment
✓ Purpose & Capability
Name/description match the actual behavior: reading a favorites list, resolving a current image URL (preferably on foto-webcam.eu), downloading the JPEG and writing it out. No extraneous credentials or unrelated binaries are requested.
ℹ Instruction Scope
The SKILL.md and script instruct the agent to read a workspace file (docs/webcams/favorites-muenchen.json), perform HTTP requests to the webcam page(s) and image URLs, and write output to a local path (e.g., /tmp). This is consistent with the stated purpose, but the favorites file controls which URLs get fetched — if that file contains arbitrary or internal URLs the skill will attempt to contact them.
✓ Install Mechanism
Instruction-only skill with no install spec. No packages are pulled at install time. The script depends on the Python 'requests' library but no install action is declared (operational dependency only).
✓ Credentials
The skill requests no environment variables, credentials, or config paths. The network access it requires is proportionate to fetching remote images; there are no unrelated secrets requested.
✓ Persistence & Privilege
always:false and no modifications to other skills or global agent config. The skill only writes image output to a specified local path and prints JSON metadata — no elevated persistence or privileges are requested.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install foto-webcam
  3. After installation, invoke the skill by name or use /foto-webcam
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initiale Version: Favoritenliste + Snapshot-Abruf per 'webcam N'
Metadata
Slug foto-webcam
Version 1.0.0
License —
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Foto Webcam?

Liste und Snapshot-Abruf von Webcams (insb. foto-webcam.eu). Verwende diese Skill-Anleitung, wenn John „webcam <nummer>“ schreibt, eine Webcam-Favoritenliste pflegen will, oder wenn ein aktuelles Snapshot-Bild von einer foto-webcam.eu Webcam als JPG im Chat gesendet werden soll. It is an AI Agent Skill for Claude Code / OpenClaw, with 1242 downloads so far.

How do I install Foto Webcam?

Run "/install foto-webcam" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Foto Webcam free?

Yes, Foto Webcam is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Foto Webcam support?

Foto Webcam is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Foto Webcam?

It is built and maintained by unixweb (@unixweb); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments