CtrlK
BlogDocsLog inGet started
Tessl Logo

miloco-home-observe

home-dreaming 定时任务的 Observe 步骤,仅由该任务调用。

48

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/skills/miloco-home-observe/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 content is a well-structured, highly actionable workflow with executable commands, explicit validation prerequisites, and thorough dedup guardrails for a batch-write operation. Its only weakness is moderate redundancy in restating the dedup rule.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence without teaching basic concepts, but the dedup rule is restated across the red-lines, execution steps, and section ③, which pads the text beyond lean — matching the score-2 anchor of mostly efficient with some unnecessary repetition rather than the score-3 'every token earns its place' anchor.

2 / 3

Actionability

It provides fully executable miloco-cli commands with complete JSON op examples (add/merge), explicit required fields (op, date, entry, evidence_log), and realistic merge syntax, matching the score-3 anchor of copy-paste-ready executable commands.

3 / 3

Workflow Clarity

A clear numbered execution sequence is paired with an explicit validation prerequisite ('写入前的强制前置步骤,不 list 不写'), a decision chain (①②③), and pre-submit dedup/evidence-dedup checklists for this batch-write operation, matching the score-3 anchor of explicit validation checkpoints and feedback loops.

3 / 3

Progressive Disclosure

No bundle files exist and none are warranted; the self-contained body is organized into clear sections (red-lines, decision chain, taxonomy tables, command format), which per the simple-skills scoring note can score 3 with well-organized sections and no needed external references.

3 / 3

Total

11

/

12

Passed

Description

17%

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 identifies an internal cron-coupled step but provides no concrete actions, no user-facing trigger terms, and no explicit 'use when' guidance. It is narrowly scoped enough to avoid conflicts yet too thin on what/when to score well.

Suggestions

Add concrete actions to the description, e.g. 'Extracts family-member habits, preferences, and home-environment knowledge from perception/interaction memory and writes it to the home profile via miloco-cli.'

Include an explicit trigger clause such as 'Use during the miloco-home-dreaming Observe step when consolidating household knowledge from daily memory.'

Replace the internal-only framing with user-relevant keywords (home profile, household habits, member preferences) so the skill is discoverable by intent.

DimensionReasoningScore

Specificity

Names a specific domain ('home-dreaming 定时任务的 Observe 步骤') but lists no concrete actions (what it extracts or writes), matching the score-2 anchor of naming a domain without comprehensive actions rather than the score-3 anchor of multiple concrete actions.

2 / 3

Completeness

It gives a vague 'what' (an Observe step) and no positive 'when to use' trigger — in fact it states it is only called by one cron task, so the 'when' is missing/implied, matching the score-1 anchor rather than score-2 (which requires a clear 'what').

1 / 3

Trigger Term Quality

It contains only an internal pipeline identifier ('home-dreaming 定时任务') and no natural keywords a user would say; this matches the score-1 anchor of technical jargon with no natural trigger terms, not score-2 which expects some relevant keywords.

1 / 3

Distinctiveness Conflict Risk

Coupling to the specific 'home-dreaming' pipeline makes it unlikely to conflict with unrelated skills, but the distinction is an internal cron coupling rather than a clean user-facing niche, fitting score-2 rather than the score-3 clear-niche anchor.

2 / 3

Total

6

/

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.