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.

Quality

76%

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/video-understand/SKILL.md

Quality

Content

63%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.

The body is highly actionable with abundant executable examples and a clear core pattern, but it is markedly verbose due to repetitive near-identical recipes and inlines content that should be split into reference files rather than loaded unconditionally.

Suggestions

Collapse the 10+ near-identical recipe code blocks into one canonical example plus a table of prompt variations, moving domain-specific recipes (sports, educational, moderation, quality) into separate reference files.

Move the Express.js and Next.js integration examples and the troubleshooting list into references/ files, leaving SKILL.md a lean overview with one-level-deep links.

Trim redundant restatements of the backend-only warning and the awkward "this skill is located at above path" filler to tighten token usage.

Dimension	Reasoning	Score
Conciseness	The ~900-line body repeats near-identical code blocks across 10+ recipes (each is import → create → createVision → return choices[0].message.content) and re-states the backend-only warning, so it is noticeably verbose with several padded sections that could be tightened.	2 / 5
Actionability	Provides fully executable, copy-paste-ready code and CLI commands covering the common cases (single analysis, scene understanding, batch processing, Express/Next.js integration, error handling).	5 / 5
Workflow Clarity	The core single-action pattern (create ZAI, build messages with video_url, call createVision) is unambiguous and shown repeatedly, and the batch and error-handling sections include try/catch feedback; minor validation gaps keep it just below a 5.	4 / 5
Progressive Disclosure	Section structure exists and one scripts/ file is signaled ("See {Skill Location}/scripts/video-understand.ts"), but large amounts of content that belong in separate reference files (integration examples, variant recipes, troubleshooting) are inlined in SKILL.md with no references/ or assets/ split.	3 / 5
	Total	14 / 20 Passed

Description

88%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.

The description is strong: it states concrete capabilities, provides an explicit "Use when" trigger clause with natural terms and file extensions, and occupies a distinct video-understanding niche. The only gaps are a few missing synonyms (e.g. video summarization) and minor overlap with general vision skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "analyze video content, understand motion and temporal sequences, extract information from video frames, describe video scenes, or perform video-based AI analysis" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both "what" ("Implement specialized video understanding capabilities using the z-ai-web-dev-sdk") and "when" via a concrete "Use this skill when the user needs to..." clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage including natural phrases ("analyze video content", "describe video scenes") and file extensions (MP4, AVI, MOV), though common variations like "summarize video" are absent.	4 / 5
Distinctiveness Conflict Risk	Carves a clear video-understanding niche tied to a specific SDK with distinct video triggers, but the underlying vision API overlaps conceptually with image/vision skills, leaving minor conflict risk.	4 / 5
	Total	18 / 20 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
skill_md_line_count	SKILL.md is long (917 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: jjyaoao/HelloAgents
Path: skills/video-understand/SKILL.md
Commit: 93e77ea

Reviewed: 5 days 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.