Name: xiaoyue-companion
Rating: 58.4 (1 reviews)
Author: anbeime

Blog Docs Log in Get started

xiaoyue-companion

专为软件开发工程师与综合办公文员打造。当你在等待任务执行、工作疲惫或需要鼓励时，使用此技能通过智谱AI自动生成温暖对话回应与场景配图，一键获取专属情绪价值与虚拟陪伴，让AI助手更懂你。

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./projects/companion-simple/SKILL.md

The canonical home for this skill is xiaoyue-companion in anbeime/skill

Quality

Content

63%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 executable scripts and a clear workflow, but it wastes tokens by duplicating full script contents that already live in the scripts/ bundle and references images absent from assets/. Restructuring around the bundle files would improve both conciseness and progressive disclosure.

Suggestions

Replace the inlined full Node.js and bash scripts with brief snippets plus 'See scripts/xiaoyue-chat.js and scripts/xiaoyue-companion.sh' to remove the duplication and lift conciseness and progressive_disclosure.

Either add the referenced images to assets/ (tired-rest.jpg, celebration.jpg, etc.) or note they are optional/user-supplied so the image-sending examples are not misleading.

Add an explicit validation checkpoint before sending to an external channel (e.g. verify the generated response is non-empty and the gateway is running) to lift workflow_clarity toward 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with useful code, but it inlines the full Node.js implementation and a full bash script that already exist verbatim as bundle files in scripts/, which is redundant padding. Not a 2 because it does not over-explain concepts Claude already knows; not a 4 because the duplicated full scripts are a clear tightening opportunity.	3 / 5
Actionability	Provides copy-paste-ready, executable commands and complete scripts with concrete examples covering common scenes. Not a 5 because the image-sending examples reference assets/ files (tired-rest.jpg, celebration.jpg) that do not exist in the bundle, a real execution gap.	4 / 5
Workflow Clarity	A clear four-step sequence (receive -> generate -> optional image -> send) plus a full script with environment-variable and API-error checks. Not a 5 because there are no explicit validation checkpoints or a validate-fix-retry feedback loop before sending to external channels.	4 / 5
Progressive Disclosure	Good section headers and real bundle references (scripts/xiaoyue-chat.js), but the full content of bundle scripts is duplicated inline rather than signaled as one-level-deep references, so content that should stay separate is inlined. Not a 4 because the inline duplication defeats the file separation.	3 / 5
	Total	14 / 20 Passed

Description

70%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 covers both what the skill does and when to use it with concrete trigger phrases and a clear niche. It loses points for buzzword padding ('情绪价值', '更懂你') and second-person voice rather than a crisp third-person 'Use when...' clause.

Suggestions

Rewrite in third person and lead with a 'Use when...' clause, e.g. 'Use when the user says they are tired, needs encouragement, or is waiting on a task.'

Replace buzzword padding ('情绪价值', '虚拟陪伴', '让AI助手更懂你') with one or two more concrete capabilities to lift specificity from 3 to 4.

Add natural synonyms and the trigger phrases already in the body ('有点累', '在吗', '发张照片') so trigger coverage reaches 5.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('自动生成温暖对话回应与场景配图'), but coverage is limited and padded with buzzwords like '情绪价值' and '让AI助手更懂你'. Not a 4 because it does not list several specific actions with only minor gaps.	3 / 5
Completeness	Answers both what ('通过智谱AI自动生成温暖对话回应与场景配图') and when ('当你在等待任务执行、工作疲惫或需要鼓励时') with explicit triggers. Not a 5 because the 'what' is buzzword-padded and the 'when' clause is second-person rather than a crisp 'Use when...' formulation.	4 / 5
Trigger Term Quality	Contains several natural trigger phrases users would say ('工作疲惫', '需要鼓励', '等待任务执行'), giving good keyword coverage. Not a 5 because common synonyms and variations are missing, and the voice is second-person rather than a clean trigger list.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (emotional companion for software engineers and office workers via ZhipuAI) with distinct triggers, so overlap risk is low. Not a 5 because the trigger phrasing is somewhat broad and could marginally overlap with general chat/companion skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anbeime/skill
Path: projects/companion-simple/SKILL.md
Commit: d9e888d

Reviewed: 2 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.