miloco-create-task

创建/管理"持续运转的家庭任务"—— 由 rule（条件触发自动化）/ schedule（定时提醒）/ record（行为累积统计）/ lifecycle（长期/限时）组合装配；也是 [感知引擎] 语音指令类系统消息的统一入口。覆盖：定时/累积提醒、"X 时 Y" 自动化、行为统计、持续状态阈值等。

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/skills/miloco-create-task/SKILL.md

Quality

Content

81%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 concrete, executable CLI guidance, strong sequencing, and explicit validation/rollback feedback loops for destructive operations. Its main weakness is length — repeated reload banners and dense phrasing leave room for tightening despite the otherwise efficient structure.

Suggestions

Consolidate the repeated '[输出协议 reload]' banners into a single stated-once rule to trim conciseness overhead.

Consider moving the 10 worked examples (or the recommendation tables) into a separate references/examples.md to let the main SKILL.md serve as a leaner overview.

Promote the 装配后自检 checklist to a more prominent top-level step so the feedback loop is visible before the assembly mapping.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly efficient, but at ~860 lines it carries repeated '输出协议 reload' banners and some padded phrasing that could be tightened, fitting the 'mostly efficient but includes some unnecessary explanation or could be tightened' anchor rather than the lean 4.	3 / 5
Actionability	Provides concrete CLI commands, full flag-mapping tables, Record content JSON templates, and 10 fully executable copy-paste bash examples covering the common cases — matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	Sequences work across three explicit layers (前置检查 → 维度判定 → 装配映射) with an Y/N 装配后自检 checklist as a validation feedback loop and a 装配失败回滚 procedure for the destructive/batch CLI operations, matching the 'explicit validation steps; feedback loops; checklists' anchor.	5 / 5
Progressive Disclosure	CRUD operations are split into the real, clearly-signaled references/crud-ops.md (one level deep, linked from the routing table) while the main SKILL.md concentrates on the create path, giving good structure with only minor organization gaps rather than the ideal one-level split.	4 / 5
	Total	17 / 20 Passed

Description

58%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 clearly conveys what the skill does and names concrete composing primitives, but it lacks an explicit 'when to use' trigger clause and leans on technical vocabulary over the natural phrases a user would say. It is distinct within its ecosystem yet slightly over-technical for trigger discovery.

Suggestions

Add an explicit 'Use when...' clause with natural user trigger phrases (e.g., '每天喝 8 杯水'、'房间没人提醒我'、'明天 X 提醒') so completeness can reach 4-5.

Replace or supplement technical terms (rule/schedule/record/lifecycle) with the plain-language equivalents users actually say to raise trigger_term_quality.

Tighten the 覆盖 list into concrete, copy-pasteable trigger examples to reduce jargon density.

Dimension	Reasoning	Score
Specificity	Names the domain (持续运转的家庭任务) and lists several concrete composing primitives (rule/schedule/record/lifecycle) plus concrete coverage categories (定时/累积提醒、'X 时 Y' 自动化、行为统计、持续状态阈值), giving multiple specific actions with only minor coverage gaps — matches the 'lists several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	There is a clear 'what' (创建/管理持续运转的家庭任务，组合装配) but 'when' is only weakly implied through the 覆盖 list and '语音指令类系统消息的统一入口' with no explicit 'Use when...' trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Contains some natural user terms (定时提醒、行为统计) but the description leans technical (rule/schedule/record/lifecycle、感知引擎、语音指令) and is missing common natural variations a user would actually say, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The niche (持续运转的家庭任务 via rule/schedule/record/lifecycle, 感知引擎语音指令入口) is mostly distinct with only minor overlap risk against sibling miloco-* skills, matching the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	14 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (874 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: XiaoMi/xiaomi-miloco
Path: plugins/skills/miloco-create-task/SKILL.md
Commit: 095782d

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.