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。

57

Quality

66%

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-home-observe/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 content is highly actionable with concrete CLI commands and a well-sequenced, validated batch workflow supported by clear classification tables and red-line rules. Its only weakness is minor repetition of the dedup guidance across several sections.

Suggestions

Consolidate the dedup rules stated in the red-line box, step 5, and section ③ into a single authoritative location to remove repetition.

DimensionReasoningScore

Conciseness

The body is dense and task-specific (classification tables, subject rules, red lines) rather than explaining concepts Claude already knows, with only minor repetition of the dedup rules across the red-line box, step 5, and section ③ that could be tightened.

4 / 5

Actionability

Provides copy-paste-ready commands with a complete JSON example for `candidate-write --ops` plus concrete `merge` variants for both candidate and profile regions, covering the common add/merge cases with exact field shapes.

5 / 5

Workflow Clarity

Sequences a 6-step execution flow with a mandatory pre-write `list` checkpoint ("不 list 不写"), explicit self-dedup validation before writing, evidence-dedup checks, and fallback handling for missing memory files — validation is present for this batch operation, so it is not capped at 3.

5 / 5

Progressive Disclosure

No bundle files are needed and none are referenced; the body is organized into clear, well-signaled sections (执行步骤, ①②③, 命令格式) with no nested references, which earns a 5 for a self-contained skill.

5 / 5

Total

19

/

20

Passed

Description

41%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 scopes the skill to a single internal cron-driven step but is thin on concrete actions and lacks any user-facing trigger guidance. It is distinguishable yet not actionable from the description alone.

Suggestions

Add a concrete action clause stating what the Observe step actually does (e.g., extracts family/home knowledge from perception and interaction memory into the home profile).

Add an explicit 'Use when...' trigger guidance, even if it references the cron context, to lift completeness above 3.

Include natural trigger synonyms so the description reads as something a caller would naturally reference.

DimensionReasoningScore

Specificity

Names the domain ("home-dreaming 定时任务的 Observe 步骤") but describes no concrete actions — it only identifies what step this is, not what it does.

2 / 5

Completeness

Gives a clear 'what' (the Observe step of the home-dreaming cron task) but the 'when' is only weakly implied via "仅由该任务调用", with no explicit 'Use when...' trigger guidance, capping it at 3.

3 / 5

Trigger Term Quality

Contains one or two specific keywords ("home-dreaming 定时任务", "Observe 步骤") but these are internal/system jargon rather than natural phrases a user would say; no synonyms or user-facing trigger terms.

2 / 5

Distinctiveness Conflict Risk

The explicit scoping "仅由该任务调用" pins it to a single cron task, giving it a clear niche with minimal overlap risk, though it lacks explicit distinct trigger phrases.

4 / 5

Total

11

/

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.