Skip to content
Agentmart
Submit a tool

berlin-starkregen-wfs

Read Berlin Starkregen flood model areas from the official Geoportal Berlin WFS.

Skill by thecolab-ai

IndexedMIT★ 34
Write a review

Chalk Labs

Need help deploying berlin-starkregen-wfs?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/thecolab-ai-berlin-starkregen-wfs

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Read Berlin Starkregen flood model areas from the official Geoportal Berlin WFS. Use for Starkregengefahrenkarte feature types and bounded Modellgebiete names such as Neukölln. Does not download velocity-layer geometry.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 4

  • codeload.github.com · found in install command
  • example.invalid · found in code
  • gdi.berlin.de · found in code
  • github.com · found in code

Files it touches

  • ~/.claude/skills/berlin-starkregen-wfs

What's inside

Skill name
berlin-starkregen-wfs
Description
Read Berlin Starkregen flood model areas from the official Geoportal Berlin WFS. Use for Starkregengefahrenkarte feature types and bounded Modellgebiete names such as Neukölln. Does not download velocity-layer geometry.
License
MIT
Compatibility
Requires Python 3.10+ and network access for live data
Metadata
thecolab.auth: none · thecolab.pack: nz-public-data · thecolab.risk: low · thecolab.health: healthy · thecolab.writes: false · thecolab.browser: false · thecolab.category: environment · thecolab.cache_ttl: none · thecolab.data_class: public · thecolab.maintainer: @adam91holt · thecolab.skill_type: public-api · thecolab.source_url: https://gdi.berlin.de/services/wfs/ua_srgk · thecolab.access_mode: public-api · thecolab.source_type: official · thecolab.source_owner: Senatsverwaltung für Stadtentwicklung, Bauen und Wohnen Berlin · thecolab.last_verified: 2026-10-11 · thecolab.schema_version: 1 · thecolab.allowed_domains: gdi.berlin.de
Instructions
47 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (12)

  • SKILL.md
  • source-notes.md · references/
  • cli.py · scripts/
  • provenance.py · scripts/
  • smoke_test.py · scripts/
  • test_contract.py · scripts/
  • area-neukoelln.xml · tests/fixtures/
  • capabilities.xml · tests/fixtures/
  • contract.json · tests/fixtures/
  • empty-collection.xml · tests/fixtures/
  • exception-report.xml · tests/fixtures/
  • hits.xml · tests/fixtures/

SKILL.md (first lines)

# Berlin Starkregen WFS

Read model-area names from the official Starkregengefahrenkarte WFS with the
Python CLI in `scripts/cli.py`. Velocity-layer geometry is listed by `types`
and is not downloaded.

## Commands

```bash
python3 skills/berlin-starkregen-wfs/scripts/cli.py types --json
python3 skills/berlin-starkregen-wfs/scripts/cli.py areas --count 1 --json
```

- `types` sends one GetCapabilities request and returns each feature type name,
  title, default CRS, and whether this skill can query it.
- `areas` sends one GetFeature request for `ua_srgk:a_modellgebiete`. `--count`
  defaults to 1 and cannot exceed 8. The service had 8 model areas when last
  verified. The command does not follow the WFS next link.
- Only `ua_srgk:a_modellgebiete` has `query` `areas`. The three
  Fließgeschwindigkeit types stay `query` `none`.

JSON output is `{"meta": {...}, "results": [...]}`. `meta` includes
`source_url`, `publisher`, `retrieved_at`, `licence`, and the Quellenvermerk
`attribution`. Area rows include id, name, CRS, and an envelope in source-CRS
metres. They do not include polygon coordinates. `latest_data` is omitted
because the feature does not state a survey date. The WFS `timeStamp` is a
response time and is not a data vintage.

## Limits and failures

Each command waits at most 10 seconds, stays on `gdi.berlin.de`, and refuses a
redirect to any other host. Capabilities are capped at 256 KiB and a model-area
response at 1 MiB. An empty body, malformed XML, an exception report, a missing
name, or a page that ignores `--count` is a schema failure. A well-formed
collection with `numberMatched` 0 is an empty result. A hits-style collection
that matches areas but returns none is a schema failure, not an empty success.
Licence or access text that is no longer the confirmed CC BY 4.0 statement
fails closed.

Exit codes follow `docs/contracts.md`: 2 invalid input, 4 blocked or
rate-limited, 5 upstream unavailable, 6 schema failure, 7 over the byte cap.

Read `references/source-notes.md` for the licence sentence, the observed area
names, and the dataset page that was not read. Run `scripts/test_contract.py`
for deterministic checks and `scripts/smoke_test.py` for the bounded live probe.

From thecolab-ai/.skills, MIT.

More from thecolab-ai/.skills

Signals

Stars
34
Forks
7
Open issues
10
Last commit (this folder)
Oct 11, 2026 (19 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from thecolab-ai

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get berlin-starkregen-wfs running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying berlin-starkregen-wfs?

CallGet help
Cite this page

berlin-starkregen-wfs skill. Agent Mart. https://agentmart.dev/skills/thecolab-ai-berlin-starkregen-wfs (last updated 2026-10-24)