Individual skill

Home Security AI Benchmark

LLM & VLM evaluation suite for home security AI applications

skills/analysis/home-security-benchmark/SKILL.md

Read pinned source

Source commit 933dcc7c90226cd1f92dc6ea7cee3b3c94790ad0

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 2, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

Standard SKILL.md format has not been attested at this commit. No installation command is available; inspect the source.

Repository context

Repository stars (not skill ratings): 3,135
Repository last updated: Sep 17, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

ai Repository topic
deep-learning Repository topic
face-recognition Repository topic
object-detection Repository topic
video-surveillance Repository topic
machine-learning Repository topic
python Repository topic
home-assistant Repository topic
camera Repository topic
computer-vision Repository topic
security Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

README.mddoc · 6,086 bytes
SKILL.mdcore · 5,974 bytes
SKILL.mdcore · 5,974 bytes
SKILL.mdcore · 5,974 bytes
SKILL.mdcore · 5,974 bytes
config.yamlasset · 342 bytes
fixtures/frames/backyard_animal.pngasset · 897,347 bytes
fixtures/frames/bicycle_sidewalk.pngasset · 853,113 bytes
fixtures/frames/box_carrier.pngasset · 722,896 bytes
fixtures/frames/condensation_lens.pngasset · 448,489 bytes
fixtures/frames/doorstep_package.pngasset · 811,277 bytes
fixtures/frames/driveway_full.pngasset · 874,109 bytes
fixtures/frames/fallen_person.pngasset · 766,313 bytes
fixtures/frames/fog_scene.pngasset · 472,689 bytes
fixtures/frames/front_door_person.pngasset · 763,923 bytes
fixtures/frames/front_porch_group.pngasset · 802,130 bytes
fixtures/frames/garden_path.pngasset · 1,022,353 bytes
fixtures/frames/garden_tool_person.pngasset · 873,229 bytes
fixtures/frames/glare_sunlight.pngasset · 593,716 bytes
fixtures/frames/headlights_night.pngasset · 783,921 bytes
fixtures/frames/hivis_worker.pngasset · 730,217 bytes
fixtures/frames/indoor_blocked_exit.pngasset · 625,254 bytes
fixtures/frames/indoor_child_cabinet.pngasset · 687,535 bytes
fixtures/frames/indoor_elec_cord.pngasset · 691,981 bytes
fixtures/frames/indoor_elec_powerstrip.pngasset · 729,383 bytes
fixtures/frames/indoor_fall_person.pngasset · 565,910 bytes
fixtures/frames/indoor_fall_shelf.pngasset · 680,310 bytes
fixtures/frames/indoor_fire_candle.pngasset · 695,209 bytes
fixtures/frames/indoor_fire_heater.pngasset · 667,724 bytes
fixtures/frames/indoor_fire_iron.pngasset · 725,958 bytes
fixtures/frames/indoor_fire_stove.pngasset · 518,112 bytes
fixtures/frames/indoor_trip_stairs.pngasset · 738,367 bytes
fixtures/frames/indoor_trip_wetfloor.pngasset · 653,137 bytes
fixtures/frames/jogger_sidewalk.pngasset · 713,884 bytes
fixtures/frames/living_room_empty.pngasset · 772,238 bytes
fixtures/frames/mailbox_delivery.pngasset · 762,476 bytes
fixtures/frames/motorcycle_driveway.pngasset · 781,503 bytes
fixtures/frames/multi_class_scene.pngasset · 652,757 bytes
fixtures/frames/multiple_animals.pngasset · 772,050 bytes
fixtures/frames/multiple_vehicles.pngasset · 607,197 bytes
fixtures/frames/night_motion.pngasset · 712,875 bytes
fixtures/frames/occluded_person.pngasset · 945,275 bytes
fixtures/frames/open_garage.pngasset · 790,335 bytes
fixtures/frames/parking_lot_vehicle.pngasset · 922,890 bytes
fixtures/frames/patio_furniture.pngasset · 762,287 bytes
fixtures/frames/pool_area.pngasset · 889,866 bytes
fixtures/frames/rain_scene.pngasset · 708,822 bytes
fixtures/frames/snow_scene.pngasset · 763,492 bytes
fixtures/frames/spider_web_lens.pngasset · 826,411 bytes
fixtures/frames/street_traffic.pngasset · 873,448 bytes
fixtures/frames/vehicle_detail.pngasset · 753,810 bytes
fixtures/frames/wheelchair_user.pngasset · 745,168 bytes
fixtures/frames/window_peeper.pngasset · 667,178 bytes
fixtures/tool-use-scenarios.jsonasset · 22,888 bytes
package-lock.jsonasset · 874 bytes
package.jsonruns · 308 bytes
scripts/generate-report.cjsruns · 50,797 bytes
scripts/run-benchmark.cjsruns · 162,454 bytes
scripts/test-model-config.cjsruns · 10,039 bytes

Read excerpt


# Home Security AI Benchmark

Comprehensive benchmark suite evaluating LLM and VLM models on **143 tests** across **16 suites** — context preprocessing, tool use, security classification, prompt injection resistance, alert routing, knowledge injection, VLM-to-alert triage, and scene analysis.

## Setup

**Requires `npm install`.** This skill has a `package.json` with dependencies (e.g. `openai` SDK). The deployment agent should check for `package.json` and run `npm install` in the skill directory before launching.

Entry script: `scripts/run-benchmark.cjs`

### Verification

```bash
node scripts/run-benchmark.cjs --help