AB alibabacloud-video-prompt-architect
Generates structured, high-quality prompts for AI video and image generation models. Transforms natural language descriptions into optimized prompts adapted for 18 models including Happy Horse, Seedance, Kling, Pika, Midjourney, Recraft, FLUX, and more. Use when creating video prompts, image prompts, product images, posters, or adapting prompts across different AI generation models. Triggers: "生成视频提示词", "视频prompt", "文生视频", "图生视频", "文生图", "商品图", "海报生成", "AI生成提示词", "prompt architect", "media prompt"
Generates structured, high-quality prompts for AI video and image generation models.
As a process B 73/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6425 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 70Execution cost. Instruction body is 6425 tokens
- 85Steps. 89 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 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
- +4Description does not say when NOT to use the skill (false activations)
- -216 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 502: enough signal without eating the budget
- +4Structure: 40 headings
- +3Step-by-step instructions: 89 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.