video-integration-specialist

Skill para integrar geracao e manipulacao de video em aplicacoes. Use quando o app precisar de text-to-video, image-to-video, clips promocionais, avatar video, motion explainers ou outros fluxos de video generativo. Trigger em: "text-to-video", "image-to-video", "video generativo", "avatar video", "motion explainer", "clip promocional", "gerar video", "fal video", "Sora", "Veo", "Runway video", "video AI".

Quality

76%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/27-video-integration-specialist/SKILL.md

Quality

Content

62%

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

This is a well-structured skill that clearly communicates the fundamental differences between video and image generation, provides a solid async workflow pattern, and covers important operational concerns (cost, idempotency, moderation). Its main weaknesses are the lack of executable code examples (no actual API integration code for any provider) and moderate verbosity in sections that could be tighter or offloaded to referenced files.

Suggestions

Add at least one executable code example showing a real API call to FAL.ai (the recommended default gateway), including submit, poll/webhook handling, and storage move — this would significantly boost actionability.

Consider moving the provider comparison table and detailed prompt cinematographic guidance to referenced files (e.g., patterns/ai-integration/video-providers.md and prompt-patterns.md) to improve progressive disclosure and reduce inline length.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient with good use of tables and structured sections, but includes some unnecessary framing ('Video generativo nao e imagem que se move'), governance boilerplate, and the 'Quando Nao Usar' section adds moderate bloat. The comparison table with image generation is useful but slightly verbose.	2 / 3
Actionability	The skill provides a clear async flow pattern, prompt structure with a concrete example, and anti-patterns, but lacks executable code. The numbered workflow uses pseudocode-level descriptions (e.g., 'provider.submit()') rather than actual API calls or code snippets for any provider. No copy-paste ready integration code is provided.	2 / 3
Workflow Clarity	The async workflow is clearly sequenced (7 steps) with explicit decision points (webhook vs poll, cost confirmation threshold, idempotency, timeout/dead-job handling). Validation checkpoints are present: cost estimation before submit, deduplication on webhook, TTL for failed jobs, and moving assets to own storage. The feedback loop for error recovery is implicit but the anti-patterns section reinforces what not to skip.	3 / 3
Progressive Disclosure	The skill references multiple external files (patterns/ai-integration/video-generation.md, prompt-patterns.md, cost-efficiency.md, security.md, policies/, templates/) which is good structure, but no bundle files are provided to verify these exist. The SKILL.md itself is moderately long and could offload the provider comparison table or prompt cinematographic details to referenced files rather than inlining everything.	2 / 3
	Total	9 / 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 well-structured skill description with strong trigger term coverage and clear 'what/when' guidance. The explicit trigger list with product names and workflow types makes it highly distinctive. The main weakness is that the capability description could be more specific about concrete actions performed (e.g., 'generates video from text prompts, converts static images to animated video, creates avatar-based talking head videos') rather than just listing video types.

Suggestions

Expand the capability description with more concrete actions: instead of just listing video types, describe what the skill does with them (e.g., 'Generates videos from text prompts, animates static images into video clips, creates talking-head avatar videos').

Dimension	Reasoning	Score
Specificity	Names the domain (video generation/manipulation) and lists several types of video workflows (text-to-video, image-to-video, promotional clips, avatar video, motion explainers), but doesn't describe concrete technical actions like 'generate', 'edit', 'render', 'export' in detail — it's more of a list of video types than specific actions performed.	2 / 3
Completeness	Clearly answers both 'what' (integrating video generation and manipulation into applications) and 'when' (explicit 'Use quando' clause plus a dedicated 'Trigger em' list with specific keywords). Both dimensions are well-covered.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms including both generic terms ('gerar video', 'video AI', 'video generativo') and specific product/tool names ('Sora', 'Veo', 'Runway video', 'fal video'), as well as workflow-specific terms ('text-to-video', 'image-to-video', 'avatar video', 'clip promocional'). These are terms users would naturally use.	3 / 3
Distinctiveness Conflict Risk	The description carves out a clear niche around generative video specifically, with distinct triggers like 'text-to-video', 'avatar video', 'Sora', 'Veo', and 'Runway video' that are unlikely to conflict with other skills such as general video editing or image generation skills.	3 / 3
	Total	11 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: felvieira/claude-skills-fv
Commit: 9e5d744

Reviewed: 12 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.