CtrlK
BlogDocsLog inGet started
Tessl Logo

agentkit-multimedia-shopping

基于ByteDance agentkit-samples多媒体用例的小省导购员数字人带货视频生成技能,整合多模态内容生成能力(图像、视频、音频),支持AI绘画、语音合成、视频生成,与小省导购员人设融合,9:16竖屏适配,直接对接带货视频生成流程

54

Quality

62%

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 ./skills/agentkit-multimedia-shopping/agentkit-multimedia-shopping/SKILL.md
SKILL.md
Quality
Evals
Security

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 content is well-organized with a clear workflow and excellent progressive disclosure through real, well-signaled bundle files. Its weaknesses are redundancy across sections, the absence of executable code/commands, and missing validation checkpoints in the batch generation workflow.

Suggestions

Add concrete, executable examples (e.g., 'python scripts/generate_character.py --profile references/character-profile.md') so guidance is copy-paste ready.

Insert validation checkpoints after each generation step (e.g., verify output image is 1080×1920, audio is 16kHz mono wav) before proceeding.

Remove redundancy between 操作步骤, 使用示例, and 工作流总结 by having the latter two reference the main steps rather than restate them.

DimensionReasoningScore

Conciseness

The body is structured and mostly efficient without concept over-explanation, but the 使用示例, 工作流总结, and 与InfiniteTalk的协同 sections repeat content already covered in 操作步骤, so it could be tightened.

2 / 3

Actionability

Names specific scripts and concrete input/output specs (9:16, 1080×1920, 16kHz mono wav) but shows no executable code or command-line invocations, so guidance is concrete yet incomplete.

2 / 3

Workflow Clarity

The 5-step sequence and ordering are clear with optional branches, but there are no validation checkpoints for the batch asset-generation and assembly workflow, which caps workflow clarity at 2.

2 / 3

Progressive Disclosure

A clear overview with a 资源索引 section signals one-level-deep references with explicit '何时读取' guidance, and all referenced bundle files (references/, scripts/, assets/) are real and appropriately split.

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, naming concrete multimodal generation actions tied to a clear persona/pipeline niche. Its main weakness is the absence of an explicit trigger clause and the reliance on internal jargon over natural user terms.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when the user wants to generate a Xiao Sheng shopping-guide digital-human livestream-commerce video').

Replace or supplement internal jargon like 'agentkit-samples多媒体用例' with natural terms a user would actually say.

Add common trigger variations such as '带货视频', '数字人视频', 'AI口播' to broaden natural-term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'AI绘画生成', '语音合成', '视频生成' — plus persona fusion and 9:16 adaptation, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly states what the skill does but provides no explicit 'when to use' trigger; per the guideline a missing 'Use when...' clause caps completeness at 2.

2 / 3

Trigger Term Quality

Contains relevant keywords ('带货视频', '数字人', 'AI绘画', '语音合成') but also internal jargon ('agentkit-samples多媒体用例') users would not naturally say, and lacks natural 'Use when...' phrasing, so coverage of common terms is partial.

2 / 3

Distinctiveness Conflict Risk

Targets a specific niche (Xiao Sheng shopping-guide digital-human livestream-commerce video) tied to a fixed persona and pipeline, making it clearly distinguishable and unlikely to trigger for unrelated skills.

3 / 3

Total

10

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 2 deeper-than-1-level

Warning

Total

13

/

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.