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".
52
56%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/27-video-integration-specialist/SKILL.mdQuality
Discovery
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. Its main weakness is that the capability description leans more toward listing video workflow types rather than specific concrete actions the skill performs. The explicit trigger list with product names and workflow terms makes it highly distinctive and easy for Claude to match.
Suggestions
Add more specific concrete actions beyond 'integrar geracao e manipulacao' — e.g., 'generates video from text prompts, converts static images to animated video, creates avatar-based talking head videos, exports clips in multiple formats'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description 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 actions beyond 'integrar geracao e manipulacao' — it lists use cases rather than specific operations like 'render', 'export', 'edit timeline', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (integrating video generation and manipulation in applications, covering text-to-video, image-to-video, promotional clips, avatar video, motion explainers) and 'when' (explicit 'Use quando' clause plus a dedicated 'Trigger em' list with specific keywords). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including both Portuguese and English variations, specific product names (Sora, Veo, Runway), workflow types (text-to-video, image-to-video), and general terms (video AI, gerar video, fal video). These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The skill occupies a clear niche around generative video specifically, with distinct triggers like product names (Sora, Veo, Runway) and specific workflow types (text-to-video, avatar video, motion explainer) that are unlikely to conflict with other skills like general video editing or image generation. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a metadata template or routing document rather than an actionable skill. It defines when to use the skill, what inputs/outputs to expect, and what files to consult, but provides zero concrete guidance on how to actually integrate video generation — no code examples, no API patterns, no workflow steps, no provider-specific instructions. The content delegates everything to referenced files that aren't provided in the bundle.
Suggestions
Add a concrete workflow with numbered steps for integrating a video generation provider (e.g., fal.ai or Runway), including API call examples, webhook/polling patterns for async processing, and validation checkpoints.
Include at least one executable code example showing an adapter pattern or API integration snippet for a common provider like fal.ai text-to-video.
Add a quick-start section with a minimal end-to-end integration example (API call → status polling → video delivery) that Claude can immediately adapt.
Replace the abstract 'Saidas Esperadas' list with a concrete output template or schema showing what the integration plan should look like.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is moderately efficient but includes several sections that are somewhat formulaic and don't add much value (e.g., 'Quando Nao Usar' with vague negatives, 'Entradas Esperadas' listing obvious inputs). Some sections like 'Governanca Global' just list policy files without actionable context. | 2 / 3 |
Actionability | The skill provides no concrete code, commands, API examples, or executable guidance. It describes what should happen at a high level ('adapter, hook e fluxo de processamento recomendados') but never shows how. There are no code snippets, no API call examples, no configuration samples — everything is abstract direction. | 1 / 3 |
Workflow Clarity | There is no sequenced workflow, no numbered steps for integration, no validation checkpoints. The skill lists inputs, outputs, and references but never describes the actual process of integrating video generation into an app. For a multi-step integration task, this is critically insufficient. | 1 / 3 |
Progressive Disclosure | The skill references multiple external files (patterns/ai-integration/video-generation.md, policies/handoffs.md, etc.) which suggests an attempt at progressive disclosure. However, no bundle files are provided to verify these exist, the references are not clearly signaled with descriptions of what each contains, and the main file itself lacks substantive content to serve as a useful overview. | 2 / 3 |
Total | 6 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
7577622
Table of Contents
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.