No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Miint-Sunny · Agent Tool · ★ 68
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is nai5-prompting safe to install? View the security audit →
NovelAI V5 完整构思与写法 · v1.2a-nightly 这是 的完整方法包，以本项目 v1.1 通用写法为基准，整合普通插画、漫画与四格、OC 服装设计和提示词转换。本版为 nightly 预发布；v1.1 继续作为正式版。 使用 将 NAI5AllPrompting.md 全文交给聊天助手作为参考，再提出本次任务。支持技能目录的环境可通过 SKILL.md 入口使用同一完整稿；当前方法不依赖其他安装包。角色设定由用户按需提供或明确启用，包内不包含私人 OC 库。 先看正文开头的任务与共同契约，再读对应章节： 普通完整插画：主串组织动作、镜头和场景，角色栏承载人物外貌与服装。 漫画与四格：包括导演、分镜、布局、文字归属和跨格连续性；新漫画默认先交完整文字分镜，已确认或明确要求直接转换时再按逐格框导出。 服装设计与衣物片段：可以只做设计、只交衣物串或只改指定部件；明确要完整画面时接回对应领域的字段规则。 用户已给定的剧情、服装、文字和逐字原串按其范围保留。完整导出按实际质量与 UC 预设去重和处理冲突；只复制文本不代表已经修改界面开关，也不会自动开始生图。 版本范围 本版已完成完整文字复核、混合任务应用回归与离线装配核验；本次没有新增 NovelAI 实图验证。既有示例、实图反馈及教程的证据边界在正文保留，不将有限应用当作生成成功率。 当前先提供完整整合稿，后续再据定稿拆分为单文件、通用构思＋写法和具体技能小包。此前的分包边界不作为本版新整合内容的固定边界。 公开仓保留的 两份文件是 v1.1 兼容目录，不包含本 nightly 的漫画和服装整合内容，也不参与本入口的当前输出规则；旧版内容可查 v1.1 参考目录。本次下载包只包含完整稿、SKILL、README、LICENSE 和 NOTICE，不附该旧目录。 许可与来源 Copyright (C) 2026 Miint-Sunny。本项目的原创贡献、编排与修改采用 GNU GPL version 3（），完整文本见 LICENSE，权利范围、第三方材料与无担保说明见 NOTICE。既有来源及第三方权利继续保留。 项目与公开来源：Miint-Sunny/nai5-prompting。
| Stars | 68 |
| Forks | 3 |
| Category | Agent Tool |
| License | GPL-3.0 |
| Quality Score | 47.4873164584639/100 |
| Last Updated | 2026-09-19 |
| Created | 2026-08-26 |
| Est. Tokens | ~16k |
Looking for a nai5-prompting alternative? If you're comparing nai5-prompting with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture.
A collection of AI agent skills for Clawdbot, Claude Code, Codex
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca
A CLI tool for logging and analyzing Claude Code and Cursor ai-driven coding session.
A minimal yet powerful framework for creating AI agents with full control over tools, providers, and execution
Explore other popular agent tool tools:
nai5-prompting is 教 AI 写 NovelAI Diffusion V5 提示词的方法 skill：构思＋写法两件套，基于 2226 张实测图库 / 962 条真实提示词。Agent Skills 标准封装。. It is categorized as a Agent Tool with 68 GitHub stars.
You can find installation instructions and usage details in the nai5-prompting GitHub repository at github.com/Miint-Sunny/nai5-prompting. The project has 68 stars and 3 forks, indicating an active community.
nai5-prompting is released under the GPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to nai5-prompting on Agent Skills Hub include claude-skills, agent-skills, claudepro-directory. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: