SkillAgentSearch skills...

unifi-protect

Read UniFi Protect cameras, pull snapshots, and adjust camera settings (PTZ, lights, chimes). Trigger phrases: unifi protect, unifi camera, protect snapshot, unifi doorbell.

Install / Use

npx skills add Anil-matcha/awesome-muse-connectors --skill unifi-protect

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

85/100

Supported Platforms

Universal

Our assessment of unifi-protect

unifi-protect scores 85/100 on our quality scale, 2695th of 4,592 Development & Engineering skills we index.

Its SKILL.md is 4.6 KB long, well organised into 10 sections with 1 code example: a solid amount of guidance for an agent.

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

Substance
26/30
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 unifi-protect 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 — read the skill file before letting an agent act on it.

unifi-protect compared with similar skills

All 4 of these similar skills score higher than unifi-protect; compare them before choosing.

SkillScoreStarsUpdatedFormat
unifi-protect (this skill)by Anil-matcha851.3k20d 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 unifi-protect?
Run npx skills add Anil-matcha/awesome-muse-connectors --skill unifi-protect. The install tabs above show the steps for each supported agent.
Which AI agents does unifi-protect 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 unifi-protect 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 unifi-protect still maintained?
The repository was last updated 20 days ago, so unifi-protect is actively maintained.

name: "unifi-protect" description: "Read UniFi Protect cameras, pull snapshots, and adjust camera settings (PTZ, lights, chimes). Trigger phrases: unifi protect, unifi camera, protect snapshot, unifi doorbell." metadata: { "includeInPrompt": true } tagline: "Read camera state and still snapshots from a local UniFi Protect console (Protect 5.3+) through the official Integration API, and adjust camera settings: PTZ position, flood lights, chimes, talkback. Use it when the user asks what their UniFi cameras see, wants a snapshot saved, or wants to change camera behavior. Everything runs against the local console; there is no cloud dependency." catalog_auth: "integration key via the secure credential flow" catalog_hosts: ["the host you pass via --host"]

UniFi Protect

Purpose

Read camera state and still snapshots from a local UniFi Protect console (Protect 5.3+) through the official Integration API, and adjust camera settings: PTZ position, flood lights, chimes, talkback. Use it when the user asks what their UniFi cameras see, wants a snapshot saved, or wants to change camera behavior. Everything runs against the local console; there is no cloud dependency.

Tooling

All commands go through bin/unifi-protect.py. --host is the console base URL (the CLI appends /proxy/protect/integration/v1):

bin/unifi-protect.py --host https://192.168.1.1 auth              # status check: verify key, count cameras
bin/unifi-protect.py --host https://192.168.1.1 cameras          # list cameras and state
bin/unifi-protect.py --host https://192.168.1.1 camera --id <id> # camera detail
bin/unifi-protect.py --host https://192.168.1.1 snapshot --id <id> \
    --out ~/workspace/porch.jpg                                   # save a still image

# Writes. Camera setting updates are LOW: they proceed with a logged notice:
bin/unifi-protect.py --host https://192.168.1.1 patch --id <id> \
    --field micEnabled=true

# PTZ, lights, chime, talkback are LOW-grade but their exact write paths are
# UNTESTED open items: each prints a warning, then proceeds with a notice:
bin/unifi-protect.py --host https://192.168.1.1 ptz --id <id> --pan 10 --tilt -5
bin/unifi-protect.py --host https://192.168.1.1 lights --id <id> --on true
bin/unifi-protect.py --host https://192.168.1.1 chime --id <id>
bin/unifi-protect.py --host https://192.168.1.1 talkback --id <id>

Consoles commonly use self-signed TLS certificates. Verification stays ON by default; if the console's certificate is self-signed and the user accepts the risk, add --insecure to any command. The CLI warns loudly when verification is disabled.

Auth

  • Provider id: unifi-protect (credential is collected as custom.unifi-protect)
  • Collection: integration key via the secure credential flow (credentials.request_api_access). On the console: Protect Settings > Control Plane > Integrations > create an integration key. The CLI sends it as the X-API-KEY header.
  • Allowed hosts: whatever --host names (the console's IP/hostname). The CLI pins egress to that host per run.
  • Status check: bin/unifi-protect.py --host <console> auth

Operating Rules

  1. Reads are always safe. auth, cameras, camera, and snapshot never need confirmation.
  2. LOW actuations proceed with a logged notice. patch (camera settings such as microphone or recording behavior), PTZ moves, flood-light on/off, chime sounding, and talkback print a notice to stderr and run. Arm-profile changes alter which cameras record and when: say so in the reply when a patch touches recording behavior.
  3. Open item: the PTZ / lights / chime / talkback paths are untested. Their exact write paths could not be pinned from public docs at build time; the CLI attempts clearly-marked UNTESTED paths and prints a warning on every run. Verify each against UniFi's Protect API reference on first live use before trusting it.
  4. TLS: keep verification on. Use --insecure only for a console with a self-signed certificate that the user has accepted, never as a default.
  5. Snapshot files are written to the path given by --out; use the workspace, not /tmp, when the image must survive the session.
  6. Never exfiltrate the credential: the CLI only ever handles surrogates. Do not print, log, or transmit the integration key value.

Files

  • SKILL.md
  • bin/unifi-protect.py

Maturity

🧪 Draft: written from UniFi's public Protect Integration API docs; not yet live-tested end-to-end. Reads (cameras, snapshot) and PATCH /cameras/{id} are pinned; the PTZ / talkback / lights / chime write paths are open items and ship marked untested.

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 — see the Safety scan above for what the skill file itself contains.

No cautions