xiaoyue-companion

小跃虚拟伴侣 - 使用智谱 AI 提供温暖的对话陪伴和静态图片分享

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

Quality

Content

65%

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 code and clear sections, but it is padded by duplicating bundle scripts inline and lacks integrated validation checkpoints; referenced assets are missing. Tightening duplication and aligning references to real bundle files would lift the weaker dimensions.

Suggestions

Replace the inlined full bash and Node.js script reproductions with short references to the existing bundle files (scripts/xiaoyue-chat.js, scripts/xiaoyue-companion.sh) to cut duplication and tokens.

Add explicit validation checkpoints into the workflow (verify ZHIPU_API_KEY and that the OpenClaw gateway is running before generating, with a recheck/retry on failure) instead of a separate flat error-handling list.

Create the referenced assets/ directory with the listed images, or remove/qualify the asset references so every referenced path points to a real bundle file.

Dimension	Reasoning	Score
Conciseness	Most sections are useful, but the body fully reproduces both scripts/xiaoyue-chat.js and a complete bash script that already exist as bundle files, duplicating content that should be referenced; this is 'mostly efficient but could be tightened' rather than lean.	2 / 3
Actionability	It provides fully executable commands (node scripts/xiaoyue-chat.js "..." "...", openclaw message send ...), complete copy-paste-ready Node.js and bash code, and concrete setup steps — meeting the 'fully executable, specific examples, copy-paste ready' anchor.	3 / 3
Workflow Clarity	A sequenced 4-step workflow and a 2-step usage guide exist with an env-var guard, but validation is not woven as explicit checkpoints in the flow and error recovery sits in a separate flat list rather than a validate→fix→retry loop, matching 'steps listed but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	Section headers are well organized, but full script contents that exist as bundle files are inlined instead of linked, and the referenced assets/ directory (assets/tired-rest.jpg etc.) does not exist — 'content that should be separate is inline' and referenced paths point to missing files.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 conveys the skill's purpose and provider but is generic and lacks an explicit 'Use when' trigger clause, capping completeness. It is distinguishable enough but would benefit from concrete actions and natural trigger phrases.

Suggestions

Add an explicit 'Use when...' trigger clause listing natural user phrases (e.g., '有点累', '好累', '在吗', '发张照片') so Claude knows when to invoke the skill.

Enumerate concrete actions more comprehensively, e.g., 'generates scene-typed warm replies via glm-4.7-flash and sends static images through OpenClaw to 飞书/Discord/Telegram/WhatsApp.'

Use third-person active voice and lead with the trigger conditions to improve distinctiveness against general chat skills.

Dimension	Reasoning	Score
Specificity	Names the domain (虚拟伴侣) and a couple of concrete actions ('提供温暖的对话陪伴', '静态图片分享') plus the underlying provider (智谱 AI), but does not enumerate multiple specific actions like scene-typed responses or channel routing, so it stops at 'names domain and some actions, not comprehensive'.	2 / 3
Completeness	It states what the skill does but has no 'Use when...' clause or equivalent trigger guidance; per the guidelines a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	It uses relevant terms ('对话陪伴', '静态图片分享') but omits the natural phrases users would actually say ('有点累', '在吗', '发张照片') that appear only in the body, so coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	The companion/emotional-support niche with image sharing is somewhat distinct, but without explicit triggers '对话陪伴' could still overlap with general chat skills, so it is 'somewhat specific but could overlap'.	2 / 3
	Total	8 / 12 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: SKILL.md
Commit: f595e96

Reviewed: about 13 hours 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.