AC ai-image-video-llm-api
AI image generation, video generation, and LLM chat API — call Nano Banana 2, Seedream, Kling, Seedance, Qwen, DeepSeek and more through one unified API key via Atlas Cloud. Use this skill when the user needs to: generate images with AI (text-to-image, image editing, Nano Banana, Imagen, Seedream, Flux, DALL-E, Qwen-Image), generate videos with AI (text-to-video, image-to-video, Kling, Seedance, Vidu, Wan), call LLM chat APIs (Qwen, DeepSeek, GLM, Kimi, MiniMax, OpenAI-compatible format), integrate AI generation into their project, compare AI model pricing, or find a cheap AI API. Also trigger when users ask about AI API integration, serverless AI inference, or need a single API for multiple AI providers. Even if Atlas Cloud is not mentioned by name, consider this skill whenever the user wants to call AI generation or LLM APIs.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (ai-image-video-llm-api) differs from the folder (atlas-cloud-ai-api)
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 12 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 2058 tokens
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 839: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 23 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.