Give Claude Code access to Europe's electricity data

If you work with European electricity market data, you’ve probably written scripts to pull prices, generation, or cross-border flows from the ENTSO-E Transparency Platform. What if your AI coding assistant could do that directly from the terminal?

python-entsoe ships with a CLI and a Claude Code skill file — a markdown document that teaches Claude how to use the CLI. Drop it into your project, and Claude can query day-ahead prices, compare generation mixes across countries, analyze transmission flows, and run pandas expressions — all without you writing a single line of code.

What’s a Claude Code skill?

A skill is a markdown file that Claude Code reads automatically when it’s relevant to your question. It contains instructions, command references, and conventions — everything Claude needs to use a tool correctly.

If you want to learn more about skills, check out our python-esios skill tutorial which covers the concept in depth. Here we’ll focus on what’s specific to ENTSO-E.

The python-entsoe skill teaches Claude:

• The full CLI command reference across 5 namespaces (prices, load, generation, transmission, balancing)
• Country codes for 30+ European countries and bidding zones
• PSR type reference for generation queries (solar, wind, nuclear, gas, etc.)
• Output formats (table, CSV, JSON) and the exec command for ad-hoc pandas expressions

Setup

1. Install the library

pip install --upgrade python-entsoe

This installs the Python library and the entsoe CLI command.

2. Set your API key

Request a free API key from the ENTSO-E Transparency Platform, then:

Option A — persistent config (recommended):

entsoe config set api-key your-key-here

This stores the key in ~/.config/entsoe/config.toml so you don’t need to export it every session.

Option B — environment variable:

export ENTSOE_API_KEY=your-key-here

3. Add the skill to your project

Copy the skill file into your project’s .claude/skills/ directory:

mkdir -p .claude/skills/entsoe
curl -o .claude/skills/entsoe/SKILL.md \
  https://raw.githubusercontent.com/datons/python-entsoe/main/src/entsoe/.agents/skills/entsoe/SKILL.md

That’s it. Next time you open Claude Code in this project, it will automatically discover the skill.

What Claude can do now

Query day-ahead prices

You: “What were electricity prices in France last week?”

Claude runs:

entsoe prices day-ahead -s 2024-06-01 -e 2024-06-08 --country FR

┌─────────────────────────┬──────────┬──────────┬────────────┐
│ timestamp               │ value    │ currency │ price_unit │
├─────────────────────────┼──────────┼──────────┼────────────┤
│ 2024-06-01 00:00:00     │  28.54   │ EUR      │ MWH        │
│ 2024-06-01 01:00:00     │  24.12   │ EUR      │ MWH        │
│ 2024-06-01 02:00:00     │  21.30   │ EUR      │ MWH        │
│ ...                     │  ...     │ ...      │ ...        │
└─────────────────────────┴──────────┴──────────┴────────────┘
Showing 50 of 168 rows

Compare countries

You: “Compare day-ahead prices between France and Spain for the first week of June”

entsoe prices day-ahead -s 2024-06-01 -e 2024-06-08 --country FR --country ES

Multi-country queries add a country column, so Claude can group, pivot, or compare the data downstream.

Analyze generation mix

You: “What’s the solar and wind generation in Germany this week?”

entsoe generation actual -s 2024-06-01 -e 2024-06-08 --country DE_LU --psr solar --psr wind_onshore

The --psr flag accepts human-readable names (solar, wind_onshore, gas, nuclear) or ENTSO-E codes (B16, B19).

Check cross-border flows

You: “Show me the physical flows from France to Spain”

entsoe transmission flows -s 2024-06-01 -e 2024-06-08 --from FR --to ES

Transmission commands use --from and --to instead of --country.

Run pandas expressions

This is the power move. The exec command fetches data and evaluates any pandas expression — no script needed:

You: “What were the average daily prices in France last week?”

entsoe exec prices day-ahead -s 2024-06-01 -e 2024-06-08 -c FR \
  -x "df.groupby(df['timestamp'].dt.date)['value'].mean().round(2)"

You: “Show me descriptive statistics”

entsoe exec prices day-ahead -s 2024-06-01 -e 2024-06-08 -c FR -x "df.describe()"

You: “Export it to CSV”

entsoe prices day-ahead -s 2024-06-01 -e 2024-06-08 --country FR \
  --format csv --output prices.csv

Real workflow: comparing France and Spain prices

Here’s what a real conversation looks like. You ask one question, Claude handles the rest:

You: “Compare the average daily electricity prices between France and Spain for June 2024. Which country was more expensive on average?”

Claude:

1. Fetches the data:

entsoe exec prices day-ahead -s 2024-06-01 -e 2024-06-30 -c FR -c ES \
  -x "df.groupby(['country', df['timestamp'].dt.date])['value'].mean().round(2).unstack(0)" \
  --format csv --output /tmp/fr_es_prices.csv

2. Analyzes:

entsoe exec prices day-ahead -s 2024-06-01 -e 2024-06-30 -c FR -c ES \
  -x "df.groupby('country')['value'].describe().round(2)"

3. Summarizes: “France averaged 32.15 EUR/MWh while Spain averaged 28.90 EUR/MWh in June 2024. France was more expensive on 22 out of 30 days, with the largest gap on June 15 (45.20 vs 18.30 EUR/MWh) during a low-wind period.”

No script. No notebook. Just a question and an answer backed by real data.

The 5 namespaces at a glance

Every command supports --format table|csv|json and --output file.csv.

Tips for writing good prompts

• Be specific about dates: “June 2024” is better than “last month” — Claude knows the exact --start and --end flags
• Use country codes: “FR” is unambiguous; “France” works too but codes are faster
• Name the PSR type: “solar generation” triggers the right --psr solar flag
• Ask for exports: Claude will use --format csv --output automatically
• Chain analysis: “fetch generation data, compute daily totals by type, find the peak solar day” — Claude chains exec calls

Conclusions

With the python-entsoe skill, Claude Code becomes a European electricity market analyst:

• entsoe prices day-ahead — day-ahead prices for any country
• entsoe load actual|forecast — system load data
• entsoe generation actual|forecast|capacity|per-plant — full generation breakdown with PSR type filtering
• entsoe transmission flows|exchanges|capacity — cross-border data
• entsoe balancing prices|volumes — imbalance data
• entsoe exec — run pandas expressions on any query without writing scripts

The skill file is the bridge: it gives Claude the knowledge to use these commands correctly, with the right flags, country codes, and conventions.

Resources

• GitHub: datons/python-entsoe
• PyPI: python-entsoe
• python-esios skill tutorial — covers skill concepts in depth
• ENTSO-E Transparency Platform
• Claude Code skills documentation