ai-video-gen

Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance, MiniMax, Gemini Omni). Supports gateways: HeyGen API, fal.ai API, and the Gemini API (Gemini Omni Flash).

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/ai-video-gen/SKILL.md

Quality

Content

71%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.

Highly actionable and executable content with a clear multi-step generation/polling workflow, but it is held back by repeated endpoint examples and a large monolithic API reference that belongs in separate files. Dangling references to non-existent Layer 3 guides weaken navigation.

Suggestions

Move the bulk API reference (request-field table, providers table, full curl/TypeScript/Python snippets, response formats) into a reference file and keep only a quick-start example in SKILL.md.

Remove the duplicated HeyGen curl example that appears in both 'Authentication' and 'Execute Video Generation', or consolidate the repeated usage examples.

Either add the referenced 'gemini-omni' and 'seedance-2-0' Layer 3 files to the bundle or replace the dangling 'See Layer 3' pointers with inline one-line guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concepts Claude already knows, but the same HeyGen endpoint/workflow curl is repeated across 'Default Workflow', 'Execute', and 'Usage Examples', and a large inlined API reference (request fields, providers table, curl/TS/Python, response formats) could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready guidance: concrete endpoints, a request-field table, complete curl/TypeScript/Python snippets, response formats, and named provider values covering the common cases.	5 / 5
Workflow Clarity	The numbered 'Default Workflow' (submit -> execution_id -> poll every 10s -> use video_url) plus polling code with failed/not_found/timeout handling gives a clear sequence with most checkpoints present; only minor error-recovery validation gaps remain.	4 / 5
Progressive Disclosure	Clear section headers give some structure, but ~300 lines of API reference are inlined in SKILL.md rather than split into reference files, and the body points to 'Layer 3 gemini-omni' and 'Layer 3 seedance-2-0' guides that do not exist in any bundle.	3 / 5
	Total	15 / 20 Passed

Description

83%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.

A well-constructed description that clearly states capabilities, enumerates explicit use-when triggers, and lists concrete provider names for distinctiveness. Verbosity is controlled and it avoids fluff.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions ('Generate AI videos from text prompts', 'Image-to-video generation with a reference image', 'Choosing between video generation providers') with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' ('Generate AI videos from text prompts using multiple provider gateways') and 'when' with a concrete numbered 'Use when: (1)...(4)' trigger list.	5 / 5
Trigger Term Quality	Strong natural phrases users would say ('Generate AI videos from text prompts', 'video clips', 'image-to-video') plus named providers (VEO, Kling, Sora); a few synonyms/extensions missing keeps it just below 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (AI video generation via specific named gateways) with distinct triggers; minor overlap risk with a generic video-editing skill keeps it just below 5.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: calesthio/OpenMontage
Path: .claude/skills/ai-video-gen/SKILL.md
Commit: 1bab711

Reviewed: about 20 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.