CtrlK
BlogDocsLog inGet started
Tessl Logo

video-generation

Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.

59

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/public/video-generation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 executable commands and a concrete worked example, but suffers from a numbering defect (duplicate Step 3), no validation checkpoint, and inlined detail that would benefit from separate references.

Suggestions

Fix the duplicate 'Step 3' numbering in the Workflow section so steps are unambiguously sequenced.

Add an explicit validation/checkpoint step (e.g., confirm the prompt JSON parses and required arguments are set) before invoking generate.py.

Move the large worked JSON example and the detailed provider/env-var configuration into reference files linked from SKILL.md to reduce repetition and improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient with executable commands, but the 'Video Generation Example' section re-states much of the Workflow and the Notes section repeats obvious points, so it could be tightened.

3 / 5

Actionability

Provides a fully executable copy-paste python command, a complete documented parameter list, a full JSON prompt example, and concrete provider env-var configuration covering the common cases.

5 / 5

Workflow Clarity

Steps are listed but there is no validation/verification checkpoint before the irreversible generation call, and two sections are both labeled 'Step 3', which caps clarity at 3.

3 / 5

Progressive Disclosure

There is reasonable section structure and a real scripts/generate.py bundle, but the large JSON example and full parameter/provider details are inlined in SKILL.md rather than split into reference files.

3 / 5

Total

14

/

20

Passed

Description

70%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 well-formed with an explicit trigger clause and a clear, third-person statement of capability. It is solid but not exceptional because its action list and synonym/extension coverage are incomplete.

DimensionReasoningScore

Specificity

Names the video domain and a couple of concrete capabilities (structured prompts, reference-image guidance), but does not enumerate a comprehensive list of specific actions.

3 / 5

Completeness

Both a clear 'what' (video generation with structured prompts and reference images) and an explicit 'Use this skill when...' trigger are present, but the 'what' could be more explicit/comprehensive.

4 / 5

Trigger Term Quality

Natural trigger verbs ('generate, create, or imagine videos') map well to what users say, though common synonyms and the .mp4 extension are missing.

4 / 5

Distinctiveness Conflict Risk

Video generation is a clear niche with distinct triggers, with only minor overlap risk against the closely related image-generation skill on shared verbs.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bytedance/deer-flow
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.