media-generation
Generate images and videos using x402-protected AI models at StableStudio. USE FOR: - Generating images from text prompts - Generating videos from text or images - Editing images with AI - Creating visual content TRIGGERS: - "generate image", "create image", "make a picture" - "generate video", "create video", "make a video" - "edit image", "modify image" - "stablestudio", "nano-banana", "sora", "veo" ALWAYS use `npx agentcash fetch` or `npx agentcash fetch-auth` for stablestudio.dev endpoints.
Install with Tessl CLI
npx tessl i github:Merit-Systems/agentcash-skills --skill media-generation95
Does it follow best practices?
Validation for skill structure
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 a well-crafted skill description that excels across all dimensions. It clearly specifies capabilities, provides comprehensive trigger terms that match natural user language, explicitly separates 'USE FOR' and 'TRIGGERS' sections to answer both what and when, and includes distinctive identifiers (StableStudio, specific model names, agentcash commands) that minimize conflict risk with other image/video generation skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generating images from text prompts', 'Generating videos from text or images', 'Editing images with AI', 'Creating visual content'. Uses third person voice appropriately. | 3 / 3 |
Completeness | Clearly answers both what (generate images/videos, edit images using x402-protected AI models) and when (explicit TRIGGERS section with natural language phrases users would say). Also includes implementation guidance with the npx command. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'generate image', 'create image', 'make a picture', 'generate video', 'create video', 'make a video', 'edit image', plus specific model names like 'stablestudio', 'sora', 'veo'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche with distinct triggers: specifically targets StableStudio and x402-protected models, mentions specific model names (nano-banana, sora, veo), and includes the unique technical requirement of using agentcash fetch commands. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%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 with excellent conciseness and actionability. The quick reference table, executable examples, and clear model comparison make it immediately useful. The main weakness is the job polling workflow which could benefit from explicit error handling and retry logic for failed generations.
Suggestions
Add explicit error handling for job polling (e.g., what to do if job fails, timeout after N attempts, retry logic)
Include example response structure for successful job completion to clarify what 'complete' looks like
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables for quick reference and avoiding unnecessary explanations. Every section serves a purpose with no padding or concepts Claude already knows. | 3 / 3 |
Actionability | Provides fully executable bash commands with complete JSON payloads that are copy-paste ready. Options are clearly listed with valid values, and endpoints are specific. | 3 / 3 |
Workflow Clarity | Job polling workflow is mentioned but lacks explicit validation/error handling steps. The sequence of generate -> poll -> get result is present but missing feedback loops for failed jobs or timeout handling. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, appropriate references to external files (getting-started.md, uploads.md) that are one level deep, and tables for quick scanning. Content is appropriately split between overview and detailed guidance. | 3 / 3 |
Total | 11 / 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.
- 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.