CtrlK
BlogDocsLog inGet started
Tessl Logo

video-understand

Implement specialized video understanding capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze video content, understand motion and temporal sequences, extract information from video frames, describe video scenes, or perform video-based AI analysis. Optimized for MP4, AVI, MOV, and other common video formats.

57

Quality

66%

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/video-understand/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%

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

The skill provides highly actionable, executable code examples but is severely bloated with repetitive patterns — the same API call structure is repeated 15+ times with only prompt text varying. A single parameterized example with a prompt table would convey the same information in 1/5 the tokens. The monolithic structure with no progressive disclosure makes this inefficient for context window usage despite its technical correctness.

Suggestions

Consolidate the 15+ nearly identical code examples into one parameterized function with a table of example prompts for different use cases (sports, education, moderation, etc.)

Move advanced use cases (Express.js integration, Next.js API route, batch processing, multi-turn conversation) into separate referenced files to reduce the main skill to an overview

Remove explanations of concepts Claude already knows: video format descriptions, what content moderation is, what educational summarization means, the 'Common Use Cases' list

Add validation/verification steps for batch processing: verify output quality, implement retry logic for failed analyses, and add a checkpoint to confirm results before proceeding

DimensionReasoningScore

Conciseness

Extremely verbose at 500+ lines with massive repetition. Every code example follows the same pattern (create ZAI instance, call createVision with messages array) repeated 15+ times with only the prompt string changing. The overview lists capabilities Claude already understands, and sections like 'Common Use Cases' are pure filler. The supported video formats list with descriptions (e.g., 'AVI (.avi) - Audio Video Interleave') explains things Claude knows.

1 / 3

Actionability

The code examples are fully executable, copy-paste ready JavaScript/TypeScript with proper imports, async/await patterns, error handling, and realistic usage examples. CLI commands are concrete with actual flags and parameters. The Express.js and Next.js integration examples are complete and functional.

3 / 3

Workflow Clarity

The skill presents clear individual operations but lacks validation checkpoints for batch processing (no verification that videos were correctly analyzed, no retry logic beyond basic try/catch). The batch processor has basic error handling but no feedback loop for failed videos. The 'Recommended Approach' section hints at a workflow but doesn't provide explicit validation steps.

2 / 3

Progressive Disclosure

This is a monolithic wall of text with no references to external files despite mentioning a scripts directory. All content is inline — the 10+ use-case variations (sports analysis, educational summarization, content moderation, quality assessment, etc.) should be in separate reference files. The skill references '{Skill Location}/scripts/video-understand.ts' but no bundle files are provided, and the content doesn't effectively split between overview and detailed materials.

1 / 3

Total

7

/

12

Passed

Description

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid skill description that clearly communicates its purpose and when to use it. It has strong trigger terms covering video formats and analysis scenarios, and the explicit 'Use this skill when...' clause ensures completeness. The main weakness is that the listed capabilities are somewhat generic and overlapping rather than enumerating truly distinct concrete actions.

Suggestions

Replace overlapping capability phrases with more specific concrete actions, e.g., 'detect objects across frames, track motion trajectories, generate scene-by-scene summaries, transcribe on-screen text from video' instead of the current generic phrasing.

DimensionReasoningScore

Specificity

It names the domain (video understanding) and mentions some actions like 'analyze video content', 'extract information from video frames', 'describe video scenes', but these are somewhat generic and overlapping rather than listing distinct concrete operations like a score-3 description would.

2 / 3

Completeness

Clearly answers both 'what' (video understanding, analyzing content, extracting information from frames, describing scenes) and 'when' with an explicit 'Use this skill when...' clause listing specific trigger scenarios.

3 / 3

Trigger Term Quality

Good coverage of natural terms users would say: 'video', 'analyze video', 'video frames', 'video scenes', 'motion', 'MP4', 'AVI', 'MOV'. These are terms users would naturally use when requesting video analysis capabilities.

3 / 3

Distinctiveness Conflict Risk

The combination of video-specific triggers, the named SDK (z-ai-web-dev-sdk), and specific video format mentions (MP4, AVI, MOV) create a clear niche that is unlikely to conflict with other skills like image analysis or general media processing.

3 / 3

Total

11

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (917 lines); consider splitting into references/ and linking

Warning

Total

10

/

11

Passed

Repository
jjyaoao/HelloAgents
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.