runware
Generate images and videos via Runware API. Access to FLUX, Stable Diffusion, Kling AI, and other top models. Supports text-to-image, image-to-image, upscaling, text-to-video, and image-to-video. Use when generating images, creating videos from prompts or images, upscaling images, or doing AI image transformation.
73
89%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
100%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 an excellent skill description that clearly communicates capabilities, names specific tools and models, and includes an explicit 'Use when...' clause with natural trigger terms. It covers both image and video generation workflows comprehensively while remaining concise and distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: text-to-image, image-to-image, upscaling, text-to-video, image-to-video. Also names specific models (FLUX, Stable Diffusion, Kling AI) and the API (Runware). | 3 / 3 |
Completeness | Clearly answers both 'what' (generate images/videos via Runware API with specific models and capabilities) and 'when' (explicit 'Use when...' clause covering generating images, creating videos, upscaling, and AI image transformation). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'generating images', 'creating videos', 'upscaling images', 'AI image transformation', plus model names like 'FLUX', 'Stable Diffusion', 'Kling AI' that users would reference. Good coverage of common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to naming the specific API (Runware), specific models (FLUX, Stable Diffusion, Kling AI), and specific operations (text-to-image, image-to-video, etc.). Unlikely to conflict with other skills unless another skill also targets the same API. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%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-crafted skill that excels at actionability and conciseness — every feature is demonstrated with executable commands and sensible defaults. The main weakness is the lack of validation/error-handling guidance, particularly for async video generation and paid API calls. The structure is clean but could benefit from separating reference material (model tables, full option lists) into supporting files.
Suggestions
Add error handling guidance for common failure modes: API key issues, timeout on video polling, invalid model IDs, and how to verify generated outputs exist and are valid.
Add a brief validation step after video generation (e.g., check file size, verify video is playable) since these are async operations that can silently fail.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what APIs, models, or image generation are. Every section delivers concrete commands and options without padding. The model tables and notes are brief and informative. | 3 / 3 |
Actionability | Every feature has a complete, copy-paste-ready bash command with realistic example arguments. Options are listed concisely with defaults. The commands cover all advertised capabilities (text-to-image, img2img, upscale, text-to-video, img2vid). | 3 / 3 |
Workflow Clarity | Each command is clear as a standalone operation, but there are no validation checkpoints or error handling guidance. For operations that cost money (API calls) and involve async polling (video generation), there's no guidance on what to do if things fail, how to verify outputs, or how to handle timeouts beyond the --max-wait flag. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but everything is inline in a single file. The model tables and detailed options could be split into reference files. However, no bundle files are provided, so there's no external structure to leverage. For a skill of this size (~100 lines), the inline approach is borderline acceptable but the options lists add bulk. | 2 / 3 |
Total | 10 / 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.
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
f45fcb5
- 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.