CtrlK
BlogDocsLog inGet started
Tessl Logo

pet-commerce-creator

自媒体创作者与电商运营在需要批量制作萌宠带货短视频时,使用此技能可自动完成爆款解析、多智能体协同创作脚本分镜,并调用API一键合成15-30秒9:16竖屏成品视频,全流程自动化助力高效涨粉与商品转化。

59

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

60%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.

A well-structured orchestration skill with a clear section layout, verified bundle files, well-signaled one-level references, and explicit QA/termination checkpoints in the workflow. The main weaknesses are redundancy (the download flow appears twice) and thin executability on the primary path — the COZE synthesis script is referenced and described but never shown being invoked.

Suggestions

Consolidate the duplicated video-download instructions: keep the concrete command in one place (either 操作步骤 or 示例0) and reference it from the other.

Add an executable example invocation of scripts/coze_video_api.py (e.g., material upload → synthesis → status-poll commands) so the primary synthesis path is copy-paste ready.

Specify error-recovery handling for the COZE API workflow (poll timeout, synthesis failure, retry behavior) to strengthen the workflow's feedback loops.

DimensionReasoningScore

Conciseness

The body is mostly operational and avoids explaining known concepts, but the video-download flow is stated twice in full (「视频下载步骤」 in 操作步骤 and again in 示例0), and the 11-agent roster appears both inline and in references/agents-prompts.md — unnecessary repetition that should be consolidated, matching the "mostly efficient but could be tightened" anchor.

3 / 5

Actionability

There is one concrete executable command (python scripts/video_downloader.py download "URL"), but the primary COZE synthesis path is only described ("处理素材上传、视频合成、状态轮询") with no example invocation of scripts/coze_video_api.py, and the multi-agent steps are narrative descriptions of what each agent outputs rather than executable steps — concrete guidance present but incomplete.

3 / 5

Workflow Clarity

Sequences are clearly numbered (标准流程 1-6, agent chain 1-11, per-example flows) and validation checkpoints exist (品控巡检宠管家 full-pipeline QA plus the forced termination rule "出现本地包调用行为立即终止流程"), satisfying the batch-operation validation requirement; what keeps it below a 5 is the absence of error-recovery handling for API failures (e.g., what to do when 状态轮询 times out or synthesis errors).

4 / 5

Progressive Disclosure

Bundle structure is good: all five references/*.md files and both scripts/*.py files referenced in the body exist, references are one level deep, and each is annotated with a when-to-read condition ("何时读取"); minor gaps are the long inline 使用示例 section and the duplicated download instructions that could be consolidated or externalized.

4 / 5

Total

14

/

20

Passed

Description

78%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.

A strong, niche-specific description that names its audience, an explicit trigger scenario, and three concrete capabilities with concrete output specs (15-30s, 9:16, vertical). Weaknesses are minor: a buzzwordy closing benefit claim and a trigger clause that covers only the batch-creation scenario rather than all supported entry points.

Suggestions

Trim the trailing benefit buzzword ("全流程自动化助力高效涨粉与商品转化") or replace it with a concrete capability such as batch material download.

Broaden the when-clause to cover the other supported entry points, e.g., "使用此技能当用户需要萌宠带货短视频创作、爆款视频链接解析反推、或知识库调取时".

Add platform synonyms users naturally mention (抖音/B站/YouTube) to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions with hard parameters ("爆款解析"、"多智能体协同创作脚本分镜"、"调用API一键合成15-30秒9:16竖屏成品视频"), but the closing benefit claim "全流程自动化助力高效涨粉与商品转化" is buzzwordy padding, so coverage is not fully comprehensive as the score-5 anchor requires.

4 / 5

Completeness

Both what (解析/创作/合成 concrete pipeline) and when ("在需要批量制作萌宠带货短视频时" — explicit trigger guidance, so above the cap of 3) are present; the when-clause covers only one scenario and could be more specific about link-parsing and knowledge-base triggers, keeping it below the score-5 anchor.

4 / 5

Trigger Term Quality

Natural phrases a user would say are present ("萌宠带货短视频"、"爆款解析"、"涨粉"、"商品转化"), giving good keyword coverage; a few natural synonyms are missing (e.g., platform names like 抖音/TikTok, and the video-link-parsing trigger the body supports).

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche (pet-commerce short-video creation via multi-agent collaboration and COZE API synthesis of 15-30s 9:16 vertical videos) with distinct triggers, so conflict risk with other skills is minimal.

5 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anbeime/skill
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.