SkillAgentSearch skills...

tesla-fleet-api

Control Tesla vehicles through the official Tesla Fleet API: lock/unlock, remote start, charge control, preconditioning, honk, trunk. Trigger phrases: tesla car, tesla vehicle, lock my tesla, precondition tesla, tesla charge.

Install / Use

npx skills add Anil-matcha/awesome-muse-connectors --skill tesla-fleet-api

Installs into whichever agent you are using.

About this skill
๐Ÿ“„

SKILL.md

Installable skill definition

Quality Score

88/100

Supported Platforms

Universal

Our assessment of tesla-fleet-api

tesla-fleet-api scores 88/100 on our quality scale, 1990th of 4,592 Development & Engineering skills we index (top 44%).

Its SKILL.md is 6.6 KB long, well organised into 10 sections with 1 code example: a thorough specification that gives an agent plenty to work with.

With 1,321 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
29/30
Structure
17/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 20 days ago, so tesla-fleet-api is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit โ€” read the skill file before letting an agent act on it.

tesla-fleet-api compared with similar skills

All 4 of these similar skills score higher than tesla-fleet-api; compare them before choosing.

SkillScoreStarsUpdatedFormat
tesla-fleet-api (this skill)by Anil-matcha881.3k20d agoSKILL.md
taste-skillby Leonxlnx100102.3ktodayCLAUDE.md
Agent-Reachby Panniantong100102.2ktodayCLAUDE.md
headroomby headroomlabs-ai10077.8k1d agoCLAUDE.md
ai-job-searchby ai-job-search-dev10065.4k4d agoCLAUDE.md

Frequently asked questions

How do I install tesla-fleet-api?
Run npx skills add Anil-matcha/awesome-muse-connectors --skill tesla-fleet-api. The install tabs above show the steps for each supported agent.
Which AI agents does tesla-fleet-api work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is tesla-fleet-api safe to use?
It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is tesla-fleet-api still maintained?
The repository was last updated 20 days ago, so tesla-fleet-api is actively maintained.

name: "tesla-fleet-api" description: "Control Tesla vehicles through the official Tesla Fleet API: lock/unlock, remote start, charge control, preconditioning, honk, trunk. Trigger phrases: tesla car, tesla vehicle, lock my tesla, precondition tesla, tesla charge." metadata: { "includeInPrompt": true } tagline: "Control Tesla vehicles through the official Tesla Fleet API: read live vehicle state, wake a sleeping car, and send signed commands (lock/unlock, keyless drive, charge control, preconditioning, honk/flash, trunk, sentry/valet, speed limit, navigation). Use when the user mentions their Tesla car or asks for vehicle actuation." catalog_auth: "provider OAuth 2.0 via the secure credential flow" catalog_hosts: ["fleet-api.prd.na.vn.cloud.tesla.com", "fleet-api.prd.eu.vn.cloud.tesla.com", "fleet-api.prd.cn.vn.cloud.tesla.com"]

Tesla Fleet API (vehicles)

Purpose

Control Tesla vehicles through the official Tesla Fleet API: read live vehicle state, wake a sleeping car, and send signed commands (lock/unlock, keyless drive, charge control, preconditioning, honk/flash, trunk, sentry/valet, speed limit, navigation). Use when the user mentions their Tesla car or asks for vehicle actuation.

This connector covers vehicles only and is fully separate from tesla-powerwall (energy devices): separate credential, separate scope set, separate CLI.

Tooling

All commands go through bin/tesla-fleet-api.py. --region selects the API region (na, eu, cn; default na). --vehicle is the vehicle tag, usually the VIN.

bin/tesla-fleet-api.py auth                                       # verify the OAuth token
bin/tesla-fleet-api.py vehicles                                   # list vehicles
bin/tesla-fleet-api.py vehicle-data --vehicle YOUR_VIN              # live state (charge, location, climate, doors)
bin/tesla-fleet-api.py vehicle-data --vehicle YOUR_VIN --endpoints charge_state
bin/tesla-fleet-api.py wake --vehicle YOUR_VIN                      # wake a sleeping car (metered)

# HIGH actuations: --confirm "<exact effect>" required on EVERY call
bin/tesla-fleet-api.py command --vehicle YOUR_VIN --action door_lock \
    --confirm "lock all vehicle doors"
bin/tesla-fleet-api.py command --vehicle YOUR_VIN --action door_unlock \
    --confirm "unlock all vehicle doors"
bin/tesla-fleet-api.py command --vehicle YOUR_VIN --action remote_start_drive \
    --confirm "enable keyless driving for 2 minutes"

# MEDIUM actuations: --confirm "<exact effect>" on first use per vehicle, then proceed
bin/tesla-fleet-api.py command --vehicle YOUR_VIN --action charge_start \
    --confirm "start EV charging"
bin/tesla-fleet-api.py command --vehicle YOUR_VIN --action set_charge_limit \
    --params '{"percent": 80}' --confirm "change the charge limit"

# LOW actuations: no confirmation
bin/tesla-fleet-api.py command --vehicle YOUR_VIN --action honk_horn
bin/tesla-fleet-api.py command --vehicle YOUR_VIN --action auto_conditioning_start
bin/tesla-fleet-api.py command --vehicle YOUR_VIN --action actuate_trunk --params '{"which_trunk": "rear"}'

Available actions: door_lock, door_unlock, remote_start_drive, charge_start, charge_stop, set_charge_limit, honk_horn, flash_lights, auto_conditioning_start, auto_conditioning_stop, actuate_trunk, set_sentry_mode, set_valet_mode, speed_limit_activate, speed_limit_set_limit, navigation_gps_request, schedule_software_update. Extra command parameters go in --params as a JSON object.

MEDIUM first-use confirmations are recorded locally (~/.cache/muse-connectors/tesla-fleet-api/confirmed.json); HIGH actions always ask.

Auth

  • Provider id: tesla-fleet-api (credential is collected as custom.tesla-fleet-api)
  • Collection: provider OAuth (OAuth 2.0 third-party tokens) via the secure credential flow (credentials.request_api_access); same OAuth pattern as the slack and x connectors
  • Required scopes: openid, offline_access, vehicle_device_data, vehicle_cmds, vehicle_charging_cmds, vehicle_location
  • Allowed hosts: fleet-api.prd.na.vn.cloud.tesla.com, fleet-api.prd.eu.vn.cloud.tesla.com, fleet-api.prd.cn.vn.cloud.tesla.com (selected with --region)
  • Status check: bin/tesla-fleet-api.py auth (must return "ok": true)
  • Signed commands need two things beyond the token: the developer app's public key hosted on a verified domain, and the vehicle paired to the app's virtual key. Without pairing, commands are rejected by the car.
  • Onboarding burden: heaviest of this batch. Developer app approval needs legal business details, verified domain ownership, and a hosted public key, plus per-vehicle virtual-key pairing. Say so up front.

Operating Rules

  1. HIGH actuations need explicit confirmation every time, naming the exact physical effect: door_lock / door_unlock change physical access to the car; remote_start_drive opens a 2-minute window where the car can be driven without a key. The CLI refuses to run without the exact --confirm text. No standing permission, no exceptions.
  2. MEDIUM actuations (charge start/stop/limit, sentry/valet mode, speed limit) need --confirm naming the exact effect on first use per vehicle; reads and LOW actuations (honk, flash, trunk, preconditioning, navigation destination, software-update scheduling) need no confirmation.
  3. Cost warning: Tesla bills pay-per-use. Roughly $1 per 1,000 commands, $1 per 500 data requests, $1 per 50 wakes; a $10/month credit covers light individual use. wake and frequent vehicle-data polling spend real money: poll sparingly and say the cost when the user asks for repeated checks.
  4. vehicle-data without --endpoints pulls the full state; pass --endpoints (semicolon-separated, e.g. charge_state;climate_state) to keep responses small and cheaper.
  5. The signed_command envelope in the CLI follows the official Fleet API reference and is untested in this build. If the car rejects a command with a pairing error, the fix is virtual-key pairing; retrying will not help.
  6. Never exfiltrate the credential: the CLI only ever handles surrogates. Do not print, log, or transmit the token value.

Files

  • SKILL.md
  • bin/tesla-fleet-api.py

Maturity

๐Ÿงช Draft: written from Tesla's public Fleet API docs; not yet live-tested end-to-end.

Honesty flags: the vehicles, vehicle_data, wake_up, and signed_command paths are pinned in the official docs. The signed-command request envelope (routineName plus action parameters) follows the official reference but has not been exercised here, and signed commands cannot work at all until the app's public key is hosted and the vehicle pairs the virtual key. remote_start_drive and lock/unlock are HIGH and confirmation-gated in the CLI on every call.

Related Skills

View on GitHub
GitHub Stars1.3k
CategoryDevelopment
Updated20d ago
Forks305

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit โ€” see the Safety scan above for what the skill file itself contains.

No cautions
tesla-fleet-api โ€” Universal Skill: Install & Safety Check | SkillAgent