f1-cli

Query Formula 1 data using the f1-cli command-line tool (wraps OpenF1 API). Use when the user asks about F1 race results, lap times, driver standings, pit stops, telemetry, weather, team radio, overtakes, tire strategy, or any Formula 1 statistics. Also use when asked to compare drivers, analyze race performance, look up session data, or retrieve real-time F1 information. Triggers on mentions of F1, Formula 1, Grand Prix, specific driver names (Verstappen, Hamilton, Norris), or racing data queries. Even casual questions like "who won the last race" or "how fast was Max's fastest lap" should use this skill.

3,891 stars

Best use case

f1-cli is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Query Formula 1 data using the f1-cli command-line tool (wraps OpenF1 API). Use when the user asks about F1 race results, lap times, driver standings, pit stops, telemetry, weather, team radio, overtakes, tire strategy, or any Formula 1 statistics. Also use when asked to compare drivers, analyze race performance, look up session data, or retrieve real-time F1 information. Triggers on mentions of F1, Formula 1, Grand Prix, specific driver names (Verstappen, Hamilton, Norris), or racing data queries. Even casual questions like "who won the last race" or "how fast was Max's fastest lap" should use this skill.

Teams using f1-cli 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/f1-cli/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/barronlroth/f1-cli/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/f1-cli/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How f1-cli Compares

Feature / Agentf1-cliStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Query Formula 1 data using the f1-cli command-line tool (wraps OpenF1 API). Use when the user asks about F1 race results, lap times, driver standings, pit stops, telemetry, weather, team radio, overtakes, tire strategy, or any Formula 1 statistics. Also use when asked to compare drivers, analyze race performance, look up session data, or retrieve real-time F1 information. Triggers on mentions of F1, Formula 1, Grand Prix, specific driver names (Verstappen, Hamilton, Norris), or racing data queries. Even casual questions like "who won the last race" or "how fast was Max's fastest lap" should use this skill.

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

# f1-cli — Formula 1 Data CLI

A Go CLI wrapping the [OpenF1 API](https://openf1.org) for querying F1 telemetry, timing, and session data.

## Installation

```bash
brew tap barronlroth/tap
brew install f1-cli
```

Or from source:
```bash
go install github.com/barronlroth/f1-cli/cmd/f1@latest
```

The binary name is `f1`.

## Quick Reference

### Global Flags (apply to all commands)

| Flag | Description |
|---|---|
| `--json` | Output as JSON (default: table) |
| `--csv` | Output as CSV |
| `--session KEY` | Session key — number or `latest` |
| `--meeting KEY` | Meeting key — number or `latest` |
| `--driver DRIVER` | Driver number (44) or 3-letter acronym (HAM) |
| `--limit N` | Limit results returned |
| `--filter EXPR` | Raw API filter, repeatable (e.g. `speed>=300`) |

### Commands → API Endpoints

| Command | Endpoint | What it returns |
|---|---|---|
| `f1 drivers` | `/drivers` | Driver info: name, team, number, acronym |
| `f1 sessions` | `/sessions` | Session list (FP1-3, Quali, Sprint, Race) |
| `f1 meetings` | `/meetings` | Grand Prix weekends (extra: `--year`, `--country`) |
| `f1 laps` | `/laps` | Lap times, sector times, speed traps |
| `f1 telemetry` | `/car_data` | Speed, RPM, gear, throttle, brake, DRS at ~3.7 Hz |
| `f1 pit` | `/pit` | Pit stop timing and duration |
| `f1 positions` | `/position` | Position changes throughout session |
| `f1 intervals` | `/intervals` | Gap to leader and car ahead (race only) |
| `f1 standings drivers` | `/championship_drivers` | Driver championship points (race sessions) |
| `f1 standings teams` | `/championship_teams` | Constructor standings (race sessions) |
| `f1 weather` | `/weather` | Track temp, air temp, humidity, wind, rain |
| `f1 race-control` | `/race_control` | Flags, safety car, incidents |
| `f1 radio` | `/team_radio` | Team radio recording URLs |
| `f1 stints` | `/stints` | Tire compound and stint laps |
| `f1 overtakes` | `/overtakes` | Position exchanges between drivers |
| `f1 location` | `/location` | Car XYZ position on track (~3.7 Hz) |
| `f1 doctor` | — | API connectivity check |

## Usage Patterns

### Finding the right session

Most commands need `--session`. Start with `latest` for the most recent session, or find a specific one:

```bash
# List sessions for the latest meeting
f1 sessions --meeting latest

# Find a specific Grand Prix
f1 meetings --year 2025 --country Singapore

# Then use the session_key from the output
f1 laps --session 9161 --driver VER
```

### Driver identification

The `--driver` flag accepts either a number or a 3-letter acronym. The CLI resolves acronyms automatically via the API.

```bash
# These are equivalent
f1 laps --session latest --driver 1
f1 laps --session latest --driver VER
```

Common driver acronyms: VER (Verstappen), NOR (Norris), HAM (Hamilton), LEC (Leclerc), PIA (Piastri), SAI (Sainz), RUS (Russell), ALO (Alonso).

### Filtering with comparison operators

The `--filter` flag passes raw query params to the API. Supports `>=`, `<=`, `>`, `<` operators. Can be repeated.

```bash
# Cars going over 315 km/h
f1 telemetry --session 9159 --driver 55 --filter "speed>=315"

# Pit stops under 2.5 seconds
f1 pit --session latest --filter "stop_duration<2.5"

# Combine multiple filters
f1 telemetry --session latest --driver VER --filter "speed>=300" --filter "throttle>=95"

# Laps under 90 seconds
f1 laps --session latest --filter "lap_duration<90"
```

### Output formats

```bash
# Default: aligned table
f1 drivers --session latest

# JSON for piping to jq or other tools
f1 telemetry --session latest --driver VER --json | jq '.[0].speed'

# CSV for spreadsheets
f1 laps --session latest --driver HAM --csv > hamilton_laps.csv
```

## Common Workflows

### "Who won the last race?"
```bash
# Always use standings for final race results
f1 standings drivers --session latest
```
**Do NOT use `f1 positions` for race results.** Positions is a time series — it records every position change throughout the session. Using `--limit` on positions gives you the *start* of the race, not the finish. Use `f1 standings drivers` for the final classification.

### "Compare two drivers' lap times"
```bash
f1 laps --session latest --driver VER --json > /tmp/ver.json
f1 laps --session latest --driver NOR --json > /tmp/nor.json
# Then compare the JSON files
```

### "What happened during the race?" (incidents, flags)
```bash
f1 race-control --session latest
```

### "Tire strategy breakdown"
```bash
f1 stints --session latest --driver VER
```

### "Weather conditions during the session"
```bash
f1 weather --session latest --limit 10
```

### "Fastest pit stops"
```bash
f1 pit --session latest --filter "stop_duration<3" --json | jq 'sort_by(.stop_duration)'
```

## Important Gotchas

- **`--limit` is client-side only.** The OpenF1 API does not support a `limit` query parameter. The CLI fetches all results then truncates locally. This means large telemetry/location queries still hit the API fully — use `--filter` to narrow server-side when possible.
- **`--filter` is server-side.** Filters like `speed>=300` are sent to the API and reduce the response. Always prefer `--filter` over `--limit` for performance.
- **`positions` is a time series, not a result.** It records every position change during a session. To get final race results, use `f1 standings drivers --session <key>`, not `f1 positions`. Using `positions --limit N` gives you lap 1 grid order, not the finish.
- **Driver numbers change between seasons.** Don't hardcode driver numbers — use acronyms (VER, HAM, NOR) which the CLI resolves automatically per session.
- **Norris is now #1.** For the 2026 season, Lando Norris drives car #1 (as reigning champion). Verstappen is #3.

## API Notes

- **Data availability:** Historical data from 2023 season onwards. No auth needed.
- **Rate limits:** 3 requests/second, 30 requests/minute (free tier). The CLI handles rate limiting internally with retry on 429.
- **`latest` keyword:** Works for both `--session` and `--meeting` to get the most recent.
- **Intervals and overtakes:** Only available during race sessions, not practice or qualifying.
- **Championship standings:** Only available for race sessions.
- **Telemetry and location:** High-frequency data (~3.7 Hz) — use `--filter` to narrow results server-side, then `--limit` to cap output.
- **Off-season:** `--session latest` returns 404 when no sessions exist. Use a known session_key from a past season instead.

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