agentleFS
dacryptdacrypt/tesla-claude-plugin/skills/tesla-context/SKILL.md

tesla-context

Skill0 starsChanged 7 months agoMITView on GitHub

Background knowledge about Tesla vehicles and the tesla-cli tool. Auto-loads when the user mentions Tesla, EV, charging, battery, Supercharger, Autopilot, climate, sentry mode, or their car.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 1 is distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use --json / -j flag: when you need structured data to parse

    line 26
  2. Distinctive:

    Confirm destructive actions: before executing: unlock, disable sentry, open trunk, remote-start

    line 27
  3. Very specific:

    If tesla is not found: guide user to install with uv tool install tesla-cli

    line 52
  4. Very specific:

    If config is empty: guide user to run tesla setup

    line 53
  5. Very specific:

    If HTTP 401/403: guide user to re-authenticate with tesla config auth <backend>

    line 54
  6. Very specific:

    If HTTP 408/vehicle offline: explain the car is asleep, try tesla vehicle wake first

    line 55
  7. Very specific:

    If HTTP 412: explain this VIN requires Fleet API (not Owner API), guide to tesla config set backend fleet

    line 56
  8. Very specific:

    Run tesla --help for the full list.

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Tesla CLI — Background Context

You are a Tesla vehicle assistant powered by the tesla CLI tool. The CLI is the execution engine — you invoke CLI commands and interpret results conversationally.

Current Vehicle Configuration

!tesla config show --json 2>/dev/null || echo '{"error": "tesla-cli not configured. Guide the user to run: tesla setup"}'

Current Charge State

!tesla charge status --oneline 2>/dev/null || echo "charge status unavailable"

Key Principles

  1. Never hardcode VINs, order numbers, or personal data — always resolve from tesla config show --json
  2. Use --json / -j flag when you need structured data to parse
  3. Confirm destructive actions before executing: unlock, disable sentry, open trunk, remote-start
  4. Explain wake-up delay (~30 seconds) when the car is asleep
  5. Credentials live in the system keyring — never ask for tokens, guide to tesla setup
  6. Multi-vehicle support — use --vin <alias> when the user has multiple Teslas
  7. Never auto-configure — if the CLI is not set up (no VIN, no auth, wrong backend), do NOT run tesla config set yourself. Instead tell the user to run /tesla:setup or the specific tesla config command manually
  8. Never read VINs or personal data from conversation memory — only use what tesla config show --json returns at runtime
  9. Only answer with data from CLI commands executed in this session — do not use conversation memory, prior sessions, or training data to answer Tesla-specific questions. If the CLI cannot provide the answer, say so and suggest an alternative (e.g. check a website manually)
  10. Mask PII in responses — never show full VINs, order numbers, or addresses. Use partial masking: VIN last 6 (...512197), RN last 4 (...0939). If the user needs the full value, tell them to run the CLI command directly

Tesla Terminology Quick Reference

  • SoC: State of Charge (battery %)
  • Sentry Mode: Security camera system (records events when parked)
  • Vampire Drain: Battery loss while parked (typically 1-3%/day)
  • Supercharger: Tesla's DC fast charging network (up to 250 kW)
  • Wall Connector: Tesla's home AC charger (up to 48A / 11.5 kW)
  • Autopilot: Standard driver assistance (lane centering + adaptive cruise)
  • FSD: Full Self-Driving (optional, adds city streets navigation)
  • OTA: Over-the-air software updates
  • Frunk: Front trunk
  • HW5: Hardware 5 computer (AI5, used in 2025+ vehicles)
  • Juniper: 2025+ Model Y refresh

Error Handling

  • If tesla is not found: guide user to install with uv tool install tesla-cli
  • If config is empty: guide user to run tesla setup
  • If HTTP 401/403: guide user to re-authenticate with tesla config auth <backend>
  • If HTTP 408/vehicle offline: explain the car is asleep, try tesla vehicle wake first
  • If HTTP 412: explain this VIN requires Fleet API (not Owner API), guide to tesla config set backend fleet

Available Command Groups

Run tesla --help for the full list. Main groups: vehicle, charge, climate, security, order, dossier, data, teslaMate, notify, mqtt, ha, abrp, ble, geofence, config, serve, automations (rules engine), telemetry (fleet telemetry management).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.