CtrlK
BlogDocsLog inGet started
Tessl Logo

miloco-miot-admin

Miloco 系统运维:连通性 / 设备缓存 / 感知成本统计。

53

Quality

60%

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-miot-admin/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is well-structured and highly actionable with concrete commands, expected outputs, error paths, and explicit boundaries. The only weakness is mild redundancy around the unimplemented cost command and the duplicated home-info note.

Suggestions

Remove the redundant blockquote under 命令对照 that repeats the home-info table row.

Consolidate the "cost 未实现" note so it appears once (e.g. only in 异常处理 + the 关键规则 guard) rather than across four sections.

DimensionReasoningScore

Conciseness

The body is mostly token-efficient (tables, terse commands, no concepts Claude already knows), but the standalone blockquote restates the home-info table row and the "cost 未实现" note recurs in four sections, so it could be tightened.

2 / 3

Actionability

It gives fully executable commands (`miloco-cli admin status`, `admin home-info`, `admin cost --period {today|month}`) with concrete expected outputs and ready replies, plus an exception table — copy-paste ready.

3 / 3

Workflow Clarity

For a simple query skill, the flow is unambiguous: judge intent → run command → handle exceptions → reply; the cost guard ("永远先告知未实现,不要解析 stdout 里的数字") acts as an explicit checkpoint, and the simple-skill scoring note permits a 3.

3 / 3

Progressive Disclosure

No bundle files exist and none are needed; the body is well-organized into clearly labeled sections (何时激活, 命令对照, 异常处理, 关键规则, 示例, 边界), which satisfies the under-50-line no-references allowance for a 3.

3 / 3

Total

11

/

12

Passed

Description

35%

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 concise and names a clear niche, but it reads as a technical label rather than a trigger-rich, action-oriented summary. It lacks natural user keywords and any explicit "when to use" guidance.

Suggestions

Reword in third person with concrete verbs, e.g. "Checks MiOT connectivity, device-cache freshness, and perception cost statistics via miloco-cli admin."

Add a trigger clause: "Use when the user asks about system health, cache validity, or perception costs — not device control or environment sensing."

Include natural phrasings a user would say (e.g. "系统状态", "缓存是否有效", "今天花了多少") so the skill triggers on real utterances.

DimensionReasoningScore

Specificity

The description names a specific domain ("Miloco 系统运维") and three concrete capability areas ("连通性 / 设备缓存 / 感知成本统计"), but uses topic nouns rather than concrete action verbs, so it is not fully comprehensive on actions.

2 / 3

Completeness

It states "what" the skill covers but provides no "when" guidance — there is no "Use when…" clause or equivalent trigger, which caps completeness at 2 per the guidelines.

2 / 3

Trigger Term Quality

The phrasing ("连通性", "设备缓存", "感知成本统计") is technical system jargon; a user would not naturally say these, and there are no natural user-facing keywords of the kind found in the body (e.g. "状态怎么样", "今天花了多少").

1 / 3

Distinctiveness Conflict Risk

The Miloco admin niche with named subsystems is reasonably specific, but without explicit triggers the description alone could still overlap with sibling skills (miloco-devices, miloco-perception) referenced only in the body.

2 / 3

Total

7

/

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.