CC yeelight-smart-home
Control, organize, diagnose, design, personalize, and answer product knowledge questions for a Yeelight smart home. Use for Yeelight homes, rooms, areas, gateways, devices, groups, scenes, automations, lighting moods, preferences, local memory, recommendations, product manuals, FAQ, SKU lookup, and product pedia consultation. Requires the locally installed yeelight-home CLI runtime and must use only yeelight-home invoke --stdin.
Control, organize, diagnose, design, personalize, and answer product knowledge questions for a Yeelight smart home.
As a process C 64/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 2
-
high Concealment
en-hide-from-userreferences/runtime-status-and-errors.md:39Instruction to hide actions from the user- Do not tell the user that the payload shape is unknown when Runtime has returned `payloadShape` or `editablePayload`.
Medium and low: 1
-
low Concealment
en-hide-from-userreferences/memory-and-personalization.md:129Instruction to hide actions from the user (negated — the text forbids it)- Review stale or conflicting memories conversationally. If the user says "我现在不喜欢浪漫风了", save the new explicit preference or recommendation suppression; do not silently delete old records unless the us
negated
Files scanned: 39. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 64/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 66 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3609 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (5 tags): a typed call is more reliable
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 432: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 66 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (26 of 26)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.