BF aqara-agent
aqara-agent is an official Aqara Home AI Agent skill. It supports natural-language home and space management, device inquiry, device control, ambience_create (氛围创建: apply or compose a named mood in a room or whole home via scene match then lights + optional music), ambience / mood orchestration reference, lighting effect inquiry and control (named lighting presets), device configuration (firmware/OTA upgrade only - not supported: rename devices, move devices between rooms or positions, or other device record edits outside firmware), device logs, scene management (query, execute, create, snapshot, and logs), automation management (create, query, detail, toggle, and logs), and energy / electricity-cost statistics (by device, room, or home). Examples: "How many lights are at home?", "Switch to my other home.", "Turn off the living room AC.", "What are the temperature and humidity in the bedroom?", "氛围创建", "卧室营造温馨居家氛围.", "Whole home sunset vibe.", "What lighting effects or scene modes are available at home?", "Set the bedroom lights to the reading lighting effect.", "Upgrade the bedroom camera firmware.", "Upgrade firmware for the hub.", "Show device logs for this device.", "Run the Movie scene.", "Recommend a bedtime setup for the bedroom.", "Create a good-night scene in the bedroom.", "Capture a scene snapshot of how things are now.", "Which scenes use the kitchen lights?", "When it is sunset in Haidian District, Beijing, turn off the security alarm.", "Create an automation to turn off the bedroom lights every day at 10:30pm.", "Five minutes after the living room motion sensor detects someone, turn on the hallway lights.", "At 7am on weekdays, run the Good Morning scene.", "If outdoor temperature drops below 5 degrees C, send me a notification.", "What automations do I have?", "Turn off the morning routine automation.", "What triggers the Leave Home automation?", "What was last month's electricity bill at home?", "How much power did the bedroom use this week?", "Check
As a process F 46/100 · Will not run — References files that are not bundled: references/*.md, references/scene-workflow/*.md, references/automation-workflow/*.md
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 39. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 2109 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5114 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/*.md - warning
missing-refreference to a missing file: references/scene-workflow/*.md - warning
missing-refreference to a missing file: references/automation-workflow/*.md - warning
missing-refreference to a missing file: references/automation-create-workflow/* - warning
missing-refreference to a missing file: scripts/*.py - note
description-budgetdescription takes 2109 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 46/100
- 0Tools and files. 5 referenced file(s) missing: references/*.md, references/scene-workflow/*.md, references/automation-workflow/*.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 42 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 5114 tokens
- 100Steps. 34 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 2109: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 27 example trigger phrases
- +4Structure: 15 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (11 of 11)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 43.