pet-commerce-creator

萌宠带货短视频全流程创作技能，基于COZE视频大模型API，支持萌宠剧情/好物测评/品种科普/宠品带货等全类型创作，覆盖爆款解析反推、知识库联动、互动优化、素材批量下载、全素材整合，实现从创意到带货引流型成品视频的自动化生成，适配15-30秒竖屏9:16主流平台规格。

Quality

62%

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 ./skills/pet-commerce-creator/pet-commerce-creator/SKILL.md

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured with excellent progressive disclosure and real executable commands, but it suffers from redundancy between steps and examples and lacks explicit validate-retry checkpoints for its batch/synthesis operations.

Suggestions

Deduplicate the video-download metadata steps that appear in both '操作步骤' and '示例0', keeping the worked example and trimming the repeated prose.

Add an explicit validation/retry checkpoint (e.g., after synthesis run 品控巡检 → if API适配校验 fails, fix and re-synthesize) so the batch/synthesis workflow has a clear feedback loop.

Make the multi-agent orchestration steps more executable by naming the concrete reference file and expected output per agent instead of describing the collaboration abstractly.

Dimension	Reasoning	Score
Conciseness	The body is mostly instructional and avoids explaining concepts Claude already knows, but it repeats content between '操作步骤' and '使用示例' (e.g., video-download metadata extraction appears in both), so it 'could be tightened' rather than earning the lean/every-token-earns-place anchor at 3.	2 / 3
Actionability	It provides concrete executable commands ('python scripts/video_downloader.py download "<URL>"','scripts/coze_video_api.py') and worked examples, but the multi-agent orchestration steps remain partly descriptive ('基于知识库参考文档执行多智能体协同创作') with execution detail deferred to references, fitting 'some concrete guidance but incomplete' rather than copy-paste-ready at 3.	2 / 3
Workflow Clarity	The multi-step process is clearly sequenced (numbered standard flow, download steps, 11-agent order) and has a hard-stop rule, but for batch-download and full-synthesis operations there is no explicit validate→fix→retry checkpoint loop; per the rubric, missing validation checkpoints for batch/destructive operations caps workflow clarity at 2.	2 / 3
Progressive Disclosure	SKILL.md is a clear overview whose '资源索引' points to one-level-deep references and scripts, each annotated with '何时读取' signals, and all referenced files (verified on disk) exist; this matches 'clear overview with well-signaled one-level-deep references; easy navigation' rather than the implicit/inline-content anchor at 2.	3 / 3
	Total	9 / 12 Passed

Description

67%

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 specific and distinctive with a clearly defined niche, but it lacks an explicit trigger/usage clause, which caps completeness, and its keywords lean on jargon over plain user phrasing.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user wants to create pet-commerce short videos, or needs to analyze/reverse-engineer a viral pet video link') to lift completeness to 3.

Include plainer natural-language trigger terms a user would actually say (e.g., '做宠物带货视频','猫狗短视频','萌宠好物推荐') alongside the current product terminology.

Trim internal jargon like '爆款解析反推' and '带货引流型' in favor of clearer action verbs to improve trigger term quality.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions ('爆款解析反推、知识库联动、互动优化、素材批量下载、全素材整合') plus a concrete spec constraint ('15-30秒竖屏9:16'), matching the 'lists multiple specific concrete actions' anchor rather than the partial-coverage anchor at 2.	3 / 3
Completeness	Clearly states what the skill does, but the description lacks any explicit 'Use when...' or equivalent trigger clause; per the guidelines a missing explicit trigger caps completeness at 2 ('has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	Contains relevant domain terms ('萌宠带货短视频','萌宠剧情/好物测评/品种科普/宠品带货') but leans on product jargon ('爆款解析反推','带货引流型') and omits plain variations a user might actually say (e.g. '做宠物视频'), fitting 'some relevant keywords but missing common variations' rather than broad coverage at 3.	2 / 3
Distinctiveness Conflict Risk	The niche is sharply defined (pet-commerce short video via COZE API, vertical 9:16, 15-30s), making it unlikely to trigger for unrelated skills; this matches 'clear niche with distinct triggers' rather than the overlap-prone anchor at 2.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anbeime/skill
Path: skills/pet-commerce-creator/pet-commerce-creator/SKILL.md
Commit: f595e96

Reviewed: about 12 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.