ClawHub

prompt-bozo

v1.0.0

AI绘画与AI视频制作的提示词生成助手。支持文生图、图生图、文生视频、图生视频、首尾帧视频等多种生成模式的提示词构建。当用户需要生成AI绘画或视频提示词时使用，包括：人物设定、环境场景、发型设计、姿势摆拍、地理位置、镜头运镜、构图视角等参数化提示词生成。支持中式风格、古风、汉服、中国风等传统美学元素。适用于即梦A...

⭐ 0· 134·0 current·0 all-time
by@bozoyan
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (prompt generation for image/video, including Chinese styles) match the included SKILL.md and reference documents. There are no extraneous environment variables, binaries, or install steps that would be unrelated to prompt construction.
✓
Instruction Scope
SKILL.md contains explicit, narrowly scoped instructions for collecting parameters and constructing prompts, and references only local docs included in the bundle. It does not instruct reading unrelated system files, contacting external endpoints, or accessing credentials. Note: several reference files assume a default subject demographic (e.g., '20岁成年女性模特' in poses.md) and many templates instruct '直接输出提示词' (no explanatory text), which constrains agent behavior but is coherent with the stated goal.
✓
Install Mechanism
Instruction-only skill with no install spec and no code files to write or execute. This is the lowest-risk install mechanism and matches the skill's functionality.
✓
Credentials
The skill requires no environment variables, credentials, or config paths. The declared requirements are proportional to a pure prompt-generation skill.
✓
Persistence & Privilege
Flags show no 'always: true' or other elevated persistence. The skill is user-invocable and allows normal model invocation (default), which is expected for an instruction-only prompt helper.
Assessment
This skill appears coherent and safe from a system-access perspective: it only contains prompt-building instructions and local reference text and does not request credentials or perform installs. Before installing/using it, consider the following: (1) Content & policy risk — many pose and style templates target 20‑year‑old adult female models and include swimsuit/bed/closeup scenarios; ensure generated prompts comply with platform content rules, consent/likeness laws, and any age/sexual-content restrictions of the downstream image/video generator you will use. (2) External tool integration — the skill does not include any connector code; if you connect it to external generation services you will need to provide API keys separately and verify those services' terms. (3) Bias & scope — templates assume particular demographics and aesthetics; review reference files for unwanted biases before relying on them. If you want deeper assurance, request source provenance (author, homepage) or a version that includes explicit safety filters or moderation checks in the workflow.

Like a lobster shell, security has layers — review code before you run it.

latestvk97abmqfwv99q07wvk5pqmswed834cz6

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments