by Moeblack · Agent Tool · ★ 87
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 87 |
| Forks | 3 |
| Category | Agent Tool |
| Quality Score | 52/100 |
| Last Updated | 2026-10-21 |
| Created | 2026-10-17 |
| Est. Tokens | ~17k |
moss-image-prompt-skill 给 （OpenMOSS，Qwen3.5-9B 文本编码器 + 5B 单流 DiT）编写图像提示词的规则集：写实、二次元、跨次元三种模式，含多分镜漫画与 JSON 版式。 📌 更新记录 🎬 影视剧照复刻 上行 是原作截图，下行 是按本 复刻出来的结果。 12 组对照覆盖 90 年代港片、Dune、Joker、Inception、Titanic 等不同年代与调色风格。 复刻时不写片名、不写演员名，只按 §3.2 的写法组织描述：开头放光学与显影参数（胶片型号、镜头、色片），正文写机位与
These tools work well together with moss-image-prompt-skill for enhanced workflows:
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: