CtrlK
BlogDocsLog inGet started
Tessl Logo

miloco-miot-scope

感知范围控制 — 管理 miloco 感知哪些家庭、哪些摄像头,每台摄像头的声音(是否参与感知),以及每台摄像头的「感知须知」(专属 prompt,补机位环境 / 关注 / 忽略以提升感知准确性)。用户说「只用/不用某家庭」「让 miloco 感知/别感知 某家庭或摄像头」「屏蔽某摄像头/把某摄像头从感知里去掉」「把某摄像头声音关了/打开」「XX 老误报(声音类)」「哪些家庭在用」时激活;也在用户吐槽**画面/视觉类固定误识**时激活——「门口摄像头老把电梯门当成我家门」「XX 老把 Y 认成 Z」「这台摄像头总把走廊的人当成家里人」「能不能告诉它忽略窗外的马路」等,用「感知须知」给该机位补指导。注意区分:开关摄像头设备本身(开机/关机/电源/录制)走 miloco-devices;感知引擎自身的开关/参数走 miloco-perception。

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

80%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with real command examples and a strong, sequenced prompt-writing workflow, and is well structured. Its main weakness is repetition: the four-way routing distinction is restated several times, inflating the token budget without adding new information.

Suggestions

Consolidate the device-vs-perception-vs-mic-vs-prompt disambiguation into a single canonical section (e.g. the existing 「何时激活 vs 走别的 skill」/「四路分流」) and cross-reference it from elsewhere instead of restating the rules in 4 places.

Add an explicit post-operation verification step (e.g. re-run scope camera list after mic/disable/prompt changes to confirm the expected in_use/voice_in_use/perception_prompt state) to strengthen feedback loops on batch operations.

Tighten the 「工作方式」 section by removing the rationale paragraphs that re-explain opt-in reasoning and SNR positioning already covered in the example commentary.

DimensionReasoningScore

Conciseness

Mostly efficient and only covers proprietary CLI behavior Claude would not know, but the four-way device-vs-perception-vs-mic-vs-prompt disambiguation is restated across at least four overlapping sections, adding repeated tokens.

3 / 5

Actionability

Fully executable: concrete miloco-cli commands with flags, batch did semantics, and copy-paste-ready examples with realistic JSON envelope responses covering common cases (home switch, camera disable/enable, mic-on/off, prompt-set/clear).

5 / 5

Workflow Clarity

The prompt-writing flow is clearly sequenced with a confirm-before-write checkpoint, append-not-overwrite handling, and a retry/adjust loop; the 校验行为 table enumerates validation rules, but no explicit post-operation verification step is required beyond backend rejection.

4 / 5

Progressive Disclosure

Well-organized into logical sections with clear headers and no external bundle files needed at this size; minor gaps are the inlined repetition of the disambiguation guidance that could be consolidated, but overall navigation is easy.

4 / 5

Total

16

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is precise, comprehensive, and exemplary in distinguishing this skill from its closest siblings. Both the what and when are answered with concrete trigger phrases users would actually say.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 控制家庭、摄像头视频感知 enable/disable、声音 mic-on/mic-off、专属「感知须知」prompt-set — covering the full scope comprehensively rather than abstractly.

5 / 5

Completeness

Explicitly answers both what (感知范围/声音/须知管理) and when (用户说某家庭、感知某摄像头、屏蔽某摄像头、关声音、误识吐槽时激活) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural user phrases including synonyms and paraphrases — 「只用/不用某家庭」「让 miloco 感知/别感知」「屏蔽某摄像头」「把声音关了」「哪些家庭在用」「老把 X 当 Y」.

5 / 5

Distinctiveness Conflict Risk

Has a clear niche (感知范围控制) and actively disambiguates from sibling skills — explicitly routes 设备开关 to miloco-devices and 引擎参数 to miloco-perception, minimizing wrong-skill triggers.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
XiaoMi/xiaomi-miloco
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.