srbijavoz

Check official Srbija Voz notices, station matches, and timetable metadata. Use when verifying live train delays, cancellations, stoppages, or replacement bus service in Serbia.

3,891 stars

Best use case

srbijavoz is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Check official Srbija Voz notices, station matches, and timetable metadata. Use when verifying live train delays, cancellations, stoppages, or replacement bus service in Serbia.

Teams using srbijavoz should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/srbijavoz-timetable/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/atomashevic/srbijavoz-timetable/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/srbijavoz-timetable/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How srbijavoz Compares

Feature / AgentsrbijavozStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Check official Srbija Voz notices, station matches, and timetable metadata. Use when verifying live train delays, cancellations, stoppages, or replacement bus service in Serbia.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Srbija Voz Status

Check official public Srbija Voz passenger-information endpoints and summarize whether a route has a live disruption, a timetable-only change, or no current issue.

## When to Use

- The user asks whether a Srbija Voz route currently has delays, cancellations, stoppages, or replacement bus service.
- The user wants current notices from the official Srbija Voz passenger-information site.
- The user needs station autocomplete matches from the timetable app.
- The user wants to confirm whether a notice is a live disruption or recurring timetable information.
- The user asks specifically about the Novi Sad - Petrovaradin corridor.

## Safe Scope

- Use only the official public passenger-information endpoints bundled in `scripts/srbvoz_scraper.py`.
- Treat this skill as read-only transit information lookup.
- Do not log in, solve challenges, bypass limits, or imitate protected user activity.
- If the public API stops working, use the timetable page fallback only for passive metadata checks.

## Check Current Notices

Run the bundled script first:

```bash
python3 scripts/srbvoz_scraper.py --limit 20
```

Filter notices when the user mentions a specific issue:

```bash
python3 scripts/srbvoz_scraper.py --query "kašnjenje" --limit 20
python3 scripts/srbvoz_scraper.py --query "Petrovaradin" --limit 20
```

The output JSON is the source of truth for current notices. Use notice title, content, date, and link in the final answer.

## Resolve Station Names

When the user gives a partial station name, call the station endpoint through the same script:

```bash
python3 scripts/srbvoz_scraper.py --station "Beograd"
```

Return the best matching station names and codes. Do not guess station names without checking the API first.

## Inspect Timetable Metadata

When the user asks whether something is a timetable artifact rather than a fresh notice, inspect the timetable page metadata:

```bash
python3 scripts/srbvoz_scraper.py --timetable-info
python3 scripts/srbvoz_scraper.py --station "Novi Sad" --timetable-info
```

Use this only to support interpretation. Prefer live notices over timetable-page hints.

## Classify the Result

Scan notice titles and bodies for disruption cues. Read `references/keyword-cues.md` when you need the full cue list.

Classify each relevant result as one of:

- `delay`
- `stopped`
- `canceled`
- `operational_change`
- `replacement_bus_service`
- `no_disruption_found`

On the Novi Sad - Petrovaradin corridor, treat recurring bus-service notices as timetable information unless the notice explicitly says service changed, stopped, or was canceled.

## Answer Format

Default to a short, rider-friendly summary.

Lead with the practical answer in plain language, for example:
- `No current issue found for Novi Sad -> Beograd.`
- `There is an issue on Novi Sad -> Beograd this morning.`
- `Only a recurring bus-transfer notice is present, no fresh disruption found.`

Then include only the useful operational details:
- whether there is a current issue or not
- affected route / train / departure times if known
- whether it looks current today, ongoing, or just a recurring timetable arrangement
- what the passenger should do, if obvious, for example use replacement bus, expect delay, or check the next departure

Do not include classifier jargon like `disruption type` unless the user asks for it.
Do not quote trigger phrases or explain the internal classification unless the user asks.
Mention `live notice` versus `recurring timetable notice` only when it helps disambiguate whether the issue is fresh.

If nothing relevant appears, say that no matching current notice was found.

## Handle Failures

- If the API request fails, the script can fall back to the public timetable page unless `--no-fallback` is set.
- If both API and fallback fail, say that the official public endpoints were unavailable at lookup time.
- If the user asks for exact timetable calculations, explain that this skill only checks public notices, station lookup, and timetable metadata.

## Tips

- Prefer route-specific queries like `Petrovaradin`, `Beograd centar`, or `Novi Sad` over generic searches.
- Quote the exact Serbian phrase that triggered the classification instead of paraphrasing the whole notice.
- A recurring bus notice on the Petrovaradin corridor is not enough by itself to claim a fresh disruption.
- Use `--station` before answering ambiguous station-name questions.
- Use `--timetable-info` only as supporting evidence, not as the primary source when live notices exist.
- Keep the final answer short and operational: what happened, where, and whether it appears current.

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation