video-generation

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

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

72%

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

The content is highly actionable with concrete commands and a complete worked example, and its single bundle file is cleanly signaled. Its weaknesses are workflow sequencing (a duplicated Step 3 and absent validation checkpoints) and minor verbosity.

Suggestions

Fix the duplicate 'Step 3' heading so the workflow is correctly numbered (Step 1-4) and unambiguous.

Add a validation/error-recovery checkpoint for generation failures, especially the MiniMax async poll/download, to raise workflow clarity.

Trim redundant Notes ('JSON format ensures structured, parsable prompts', 'Iterative refinement is normal') and avoid repeating the bash block in the example section.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational and avoids explaining basic concepts, but a duplicated 'Step 3' heading, a repeated bash command block, and padded Notes ('JSON format ensures structured, parsable prompts', 'Iterative refinement is normal') could be tightened, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Provides a copy-paste-ready bash invocation with every flag documented, a complete JSON prompt example with real paths, and concrete output handling via the present_files tool, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Steps are listed but two separate 'Step 3' headings break the sequence and there are no validation or error-recovery checkpoints (e.g., handling a failed MiniMax async poll), fitting the 'steps listed but validation gaps; checkpoints missing or implicit' anchor rather than 3.	2 / 3
Progressive Disclosure	Well-organized sections plus a single one-level-deep bundle (scripts/generate.py) clearly signaled by absolute path and inline parameter documentation; no nested reference chain, matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	10 / 12 Passed

Description

75%

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, distinct video-generation niche. Its main weakness is trigger-term breadth and action specificity, where verbs overlap and common phrasings are missing.

Suggestions

Add concrete, distinct actions rather than synonyms (e.g., 'generate videos from text prompts, use a reference image as the first/last frame, control aspect ratio').

Broaden trigger terms with natural variations users say, such as 'make a video', 'video clip', or 'animate'.

Dimension	Reasoning	Score
Specificity	Names the video domain and some actions ("generate, create, or imagine videos"; "structured prompts and reference image") but the verbs are near-synonymous rather than multiple distinct concrete capabilities, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	Explicitly answers when ("Use this skill when the user requests to generate, create, or imagine videos") and what (structured prompts and reference image for guided video generation), satisfying both halves with an explicit trigger clause; not below because the 'Use when...' clause is present and not above due to the scale ceiling.	3 / 3
Trigger Term Quality	"generate, create, or imagine videos" are natural trigger phrases, but coverage misses common variations a user might say ("make a video", "video clip", "animate"), fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	Video generation is a clear niche with distinct, video-specific triggers unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: bytedance/deer-flow
Path: skills/public/video-generation/SKILL.md
Commit: cd9432b

Reviewed: about 14 hours 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.