CtrlK
BlogDocsLog inGet started
Tessl Logo

miloco-devices

查询与控制米家智能家居设备。查询能力包括设备开关状态、运行状态、电量、设定温度、当前温湿度、PM2.5 等环境与设备数据;控制能力包括开关灯、调节空调温度/模式/风速、控制窗帘开合、启动或停止扫地机器人、开关摄像头等设备操作;场景能力包括触发已有米家场景,如回家、离家、睡眠等智能场景;以及刷新设备列表缓存。

66

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/skills/miloco-devices/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

The body is an exceptionally actionable, concise, well-sequenced workflow with strong safety/validation checkpoints for batch and risky device operations. Its only notable weakness is progressive disclosure: it is a dense single file that keeps device-specific guidance and exception handling inline rather than splitting them into one-level-deep reference files.

Suggestions

Consider moving the 设备控制指导 (device-specific guidance for smart speakers, kitchen appliances) and 异常处理 tables into a separate reference file (e.g. references/device-guidance.md) and linking from the body, keeping the core workflow lean.

If the skill grows further, split the command/parameter reference (access columns, on-supplement rules) into a one-level-deep reference so the main file stays a navigable overview.

Ensure any future references are clearly signaled as links at one level of depth rather than nested.

DimensionReasoningScore

Conciseness

The body is lean and table-driven, assumes Claude's competence (no padding about what smart-home devices or CLIs are), and every section earns its place with decision rules, command tables, and minimal prose. It matches 'lean and efficient; every token earns its place' and is not merely mostly-efficient (a 2).

3 / 3

Actionability

Commands are fully executable and copy-paste ready — e.g. `miloco-cli device control 4962 --set target-temperature 26 --set on@空调 true` and `device action 4981 start-charge` — paired with concrete ✅/❌ example tables and exact grep forms. This matches 'fully executable code/commands; specific examples; copy-paste ready' rather than pseudocode (a 2).

3 / 3

Workflow Clarity

A clearly sequenced 6-step core workflow (命令拆分 → 确定设备列表 → 确定 spec → 生成指令 → 安全分流 → 下发和回复) with explicit validation checkpoints (二次确认 for safety devices, 异常处理 recovery table, range/enum validation before dispatch). This matches the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor and exceeds the 2-anchor's implicit-checkpoint bar.

3 / 3

Progressive Disclosure

No bundle files exist, so this is a single self-contained SKILL.md. It is well-sectioned, but at ~210 lines it is monolithic — device-control guidance, exception handling, and examples that could plausibly live in separate reference files are all inline. This matches 'some structure but content that should be separate is inline' rather than the well-split 3-anchor.

2 / 3

Total

11

/

12

Passed

Description

67%

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 strong on specificity and distinctiveness, clearly scoping a Mi Home IoT skill with concrete query/control/scene capabilities. Its main weakness is the absence of an explicit 'when to use' trigger clause, which caps completeness, and its trigger phrasing is more a capability list than natural user speech.

Suggestions

Append an explicit 'Use when...' / '当用户...' trigger clause naming the situations that should activate this skill, e.g. 米家设备控制、查询设备状态、触发米家场景、刷新设备列表.

Surface natural user phrasings as triggers (e.g. '把空调调到26度', '灯开着吗', '执行回家模式') rather than only enumerating capability categories, to broaden trigger-term coverage.

Trim the long capability inventory slightly so the description stays scannable while keeping the concrete actions.

DimensionReasoningScore

Specificity

Lists many concrete actions across query, control, scene, and refresh capabilities — '设备开关状态、运行状态、电量、设定温度、当前温湿度、PM2.5', '开关灯、调节空调温度/模式/风速、控制窗帘开合、启动或停止扫地机器人、开关摄像头', '触发已有米家场景'. This matches the 'Lists multiple specific concrete actions' anchor and is not merely naming the domain.

3 / 3

Completeness

It thoroughly answers 'what' (detailed device query/control/scene/refresh capabilities), but there is no explicit 'when'/'Use when' trigger clause, so 'when' is only implied. Per the rubric guideline, a missing 'Use when...' clause caps completeness at 2, so it is not a 3.

2 / 3

Trigger Term Quality

It includes some natural user terms ('打开灯', '调到26度', '扫地', '回家'), but these are embedded in a capability enumeration rather than surfaced as natural trigger phrases a user would say; it misses common variations and reads as a feature list. It does not reach the broad natural-term coverage of a 3.

2 / 3

Distinctiveness Conflict Risk

It targets a clear niche — 米家 (Mi Home) IoT device interaction — with distinctive device-category and scene triggers unlikely to fire for unrelated skills. This matches the 'clear niche with distinct triggers; unlikely to conflict' anchor.

3 / 3

Total

10

/

12

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.