BF deepsop-genvis
AI 图片与视频异步生成技能，调用 AI Artist API 根据文本提示词生成图片或视频，自动轮询直到任务完成。 ⚠️ 使用前必须设置环境变量 AI_ARTIST_TOKEN 为你自己的 API Key！ 需要 API Key 授权：已有账号请前往 https://ai.deepsop.com/login?source=2 登录获取；没有账号请前往 https://ai.deepsop.com/register?source=2 注册后获取。 支持图片模型：**3.1Nano2-Evo（默认）**、S5.0L、N2、W2.7、W2.7Pro、Nano2-Beta-Evo、**Image2（GPTimage-2）**。 支持视频模型：**V3.1FB（默认）**、S1.5Pro、V3.1PB、V3.1Fast、W2.6t / W2.6i / W2.6r、klingV3Omni、W2.7t / W2.7i / W2.7r、**S2.0 / S2.0Fast**（Seedance2.0 系列，支持多音频参考与联网搜索）、**HappyHorse**（高效短视频，支持文生/首帧/参考图/视频编辑模式）。 查看当前服务端激活的模型请运行：`python3 scripts/generate_image.py --list-models`。 触发场景： - 用户要求生成图片，如"生成一匹狼"、"画一只猫"、"风景画"、"帮我画"等。 - 用户要求生成视频，如"生成视频"、"文生视频"、"图生视频"、"生成一段...的视频"等。 - 用户指定模型：N2、S5.0L、W2.7、W2.7Pro、3.1Nano2-Evo、Nano2-Beta-Evo、Image2、GPTimage-2、gpt-image-2、S1.5Pro、V3.1FB、V3.1PB、V3.1Fast、W2.6t、W2.6i、W2.6r、klingV3Omni、W2.7t、W2.7i、W2.7r、S2.0、S2.0Fast、Seedance2.0、HappyHorse。 - 用户上传参考图/参考视频时，自动先调用文件上传 API 转换为可访问 URL。
AI 图片与视频异步生成技能，调用 AI Artist API 根据文本提示词生成图片或视频，自动轮询直到任务完成。 ⚠️ 使用前必须设置环境变量 AIARTISTTOKEN 为你自己的 API Key！ 需要 API Key 授权：已有账号请前往…
As a process F 29/100 · Will not run — References files that are not bundled: 图片URL, url
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Exfiltration
read-dotenvSKILL.md:578Reads a .env filecp .env.example .env
-
low Exfiltration
read-dotenvSKILL.md:589Reads a .env filesource .env
-
low Exfiltration
read-dotenvSKILL.md:592Reads a .env fileexport $(cat .env | xargs)
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5107 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: 图片URL - warning
missing-refreference to a missing file: url
Process rating: all ten parameters 29/100
- 0Tools and files. 2 referenced file(s) missing: 图片URL, url
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (deepsop-genvis) differs from the folder (deepsop-genvis-ai)
- 70Execution cost. Instruction body is 5107 tokens
- 100Steps. 104 steps
- 100Running it twice. No mutating operations
- low 13 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 920: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 38 headings
- +3Step-by-step instructions: 104 items
- +4Has examples (21 code blocks)
- +4Reference files are cited in the instructions (1 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.