CtrlK
BlogDocsLog inGet started
Tessl Logo

miloco-home-prune

home-dreaming 定时任务的 Prune 步骤,仅由该任务调用。

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

Quality

Content

80%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 executable commands and well-organized sections, but its destructive batch workflow lacks explicit validation checkpoints, which caps workflow clarity.

Suggestions

Add an explicit validation step before commit — e.g., re-list subjects and confirm no unresolved inconsistencies remain after reassign.

Include a feedback loop: if commit reports conflicts or insufficient-evidence removals, show how to inspect and re-run rather than silently proceeding.

Add a pre-commit verification command or checklist confirming reassign actually merged the intended subjects.

DimensionReasoningScore

Conciseness

The body is lean with concrete steps and two complete code blocks, assuming Claude's competence; only the naming-policy list and notes section have minor over-explanation that could be trimmed, fitting the 'efficient; minor instances of over-explanation' anchor.

4 / 5

Actionability

Fully executable copy-paste-ready commands (home-profile list, reassign with complete JSON mappings, commit) cover both the member-binding and name-consolidation common cases, matching the 'fully executable; specific examples cover common cases' anchor.

5 / 5

Workflow Clarity

A clear numbered sequence exists, but this destructive/batch operation (identity merging, expiry removal, archiving) lacks explicit validate→fix→retry checkpoints before commit, so per the feedback-loop cap workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

No bundle files exist; this short single-purpose skill is well-organized into clear sections with no nested references, so per the simple-skills note it scores 5 on structure alone.

5 / 5

Total

17

/

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 one internal cron pipeline but omits concrete actions and any explicit 'Use when...' trigger, relying on pipeline jargon rather than natural user terms.

Suggestions

Add the concrete actions the step performs (e.g., bind member aliases to a person_id, consolidate space/device names, commit with expiry cleanup).

Include an explicit 'Use when...' clause or equivalent trigger guidance stating when this skill activates.

Add natural-language synonyms alongside the cron jargon so the description reads as something a user would actually say.

DimensionReasoningScore

Specificity

The description names the domain ("Prune 步骤" of the home-dreaming cron) but states no concrete actions — no mention of subject binding, name consolidation, or commit — matching the 'names the domain but actions are minimal' anchor.

2 / 5

Completeness

A clear 'what' (the Prune step) is present, but 'when' is only a usage constraint ("仅由该任务调用") rather than an explicit 'Use when...' trigger, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Only technical pipeline jargon ("home-dreaming 定时任务", "Prune 步骤") appears, with no natural phrases or synonyms a user would actually say, fitting the 'one or two generic keywords; missing natural phrases' anchor.

2 / 5

Distinctiveness Conflict Risk

Scoped to a single named internal cron task ("仅由该任务调用"), giving a clear niche with minimal conflict risk, though the trigger phrasing is not user-natural so it sits just below the 5 anchor.

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.