CtrlK
BlogDocsLog inGet started
Tessl Logo

miloco-home-promote

home-dreaming 定时任务的 Promote 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-promote/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%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 lean, highly actionable, and well-structured, with concrete commands and a clear decision table. The only meaningful weakness is the absence of validation/verification for a destructive batch write, which caps workflow clarity.

Suggestions

Add an explicit validation checkpoint after profile-write (e.g., re-run `home-profile list --target both` to confirm the candidate was removed and the formal entry is correct), which would lift workflow_clarity above the 3 cap.

Provide full example ops JSON for `merge` and `replace` (not only `add`) so every branch of the decision table is copy-paste ready, removing the small inference gap.

Add a brief dry-run or guard for the batch case (e.g., review all ops in the `--ops` array before submitting) to match the batching note with a concrete verification step.

DimensionReasoningScore

Conciseness

The body is lean and table-driven — purpose line, a 3-step list, a compact decision table, one bash example, and short criteria/notes — with no padding and no explanation of concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

It provides executable commands (`miloco-cli home-profile list --target both`, `profile-write --ops '...'`), a copy-paste-ready JSON ops example, and a decision table mapping each relationship to a concrete op with required parameters, covering the common cases.

5 / 5

Workflow Clarity

The sequence (list ready_to_promote → analyze relationship → profile-write) is clear and the decision table is explicit, but profile-write is a destructive batch operation that auto-deletes candidates and can replace entries, and there is no validation/verification checkpoint; the rubric caps such skills at 3.

3 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and uses no external references, but is well-organized into clear section headers (执行步骤, 提升决策, 矛盾裁决参考, 注意), satisfying the simple-skill exception for a 5.

5 / 5

Total

18

/

20

Passed

Description

33%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 is concise and clearly scoped to an internal cron-driven niche, but it does not state concrete actions and contains no natural user trigger terms because it is explicitly not user-invoked. Distinctiveness is its strongest aspect.

Suggestions

Add one concrete action phrase to the description (e.g., 'Evaluates ready-to-promote candidates and writes them into the formal knowledge area via add/merge/replace ops') to lift specificity above 2.

State the 'what' more concretely so the purpose is clear without reading the body, since the current 'Promote 步骤' relies on domain familiarity.

Even for an internal-only skill, add a brief explicit trigger clause (e.g., 'Activated only within the home-dreaming cron Promote stage; not for standalone use') to make the 'when' an inclusion rule rather than only an exclusion.

DimensionReasoningScore

Specificity

The description names the domain ("Promote 步骤") and its parent context but lists no concrete actions, matching the 'names the domain but actions are minimal or generic' anchor; it is more specific than pure vagueness (score 1) yet well short of listing actions (score 3).

2 / 5

Completeness

It offers a vague 'what' (the Promote step) and an explicit but exclusion-only 'when' (only called by that cron task), with no 'Use when…' inclusion trigger; the missing explicit trigger guidance caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

The phrasing "仅由该任务调用" (only called by that task) marks it as internal-only, so it contains no natural user trigger terms — only technical jargon (home-dreaming, 定时任务, Promote), matching the 'no natural keywords; only technical jargon' anchor.

1 / 5

Distinctiveness Conflict Risk

It is scoped to a single named internal cron task (home-dreaming), giving it a clear niche with minimal conflict risk, but the trigger is an internal call rather than a clean natural-language trigger set, so it falls short of the 5 anchor.

4 / 5

Total

10

/

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.