📦 Wanxiang — 万象
v1.0.0Scroll Creation 万象绘卷创作引擎分卷 – 含内容生成引擎、网文创作全流程、质量控制
0· 21·0 当前·0 累计
by 下载技能包
最后更新
2026/4/19
安全扫描
OpenClaw
安全
high confidenceThis is an instruction-only writing/quality-control guide for web-novel creation that does not request credentials, install code, or access system resources — it appears to do what its name and description claim.
评估建议
This skill is an instruction-only writing engine and appears internally consistent with its purpose: it provides templates, generation prompts, and quality-control rules for producing Chinese web fiction. It does not request credentials, install code, or access system files. Things to consider before installing: (1) The package contains explicit '去AI化' / AI-trace-removal techniques — useful for humanizing text but potentially used to evade platforms' AI-disclosure rules; decide whether you are c...详细分析 ▾
✓ 用途与能力
The skill's name/description (网文创作、内容生成、质量控制) match the provided files: all files are writing guidelines, templates, and quality-control checklists. The required resources list is empty, which is proportionate to an instruction-only documentation skill.
✓ 指令范围
SKILL.md and the reference files are purely authoring guidelines and prompt/instruction templates. They do not instruct the agent to read arbitrary host files, access credentials, call external endpoints, or perform system operations. The only runtime-like instruction is to pair with a main skill ('wanxiang-scroll') via 'clawhub install', which is an installation suggestion rather than an action that exposes sensitive data.
✓ 安装机制
No install spec and no code files are present; this is instruction-only documentation. No downloads, package installs, or binaries are required by the skill itself.
✓ 凭证需求
The skill declares no required environment variables, no credentials, and no config paths. That is proportionate to the stated purpose (writing/quality-control). Note: the content explicitly includes '去AI化/AI痕迹移除' techniques (instructions for making AI-generated text appear more human), which is a content-risk (possible misuse) but not an environment/credential incoherence.
✓ 持久化与权限
Flags are default (always: false; user-invocable: true; disable-model-invocation: false). The skill does not request permanent presence or elevated privileges and does not modify other skills or system settings.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/4/19
Initial release of wanxiang-scroll-creation. - Introduces a content generation engine, including topic engine system, direct narration techniques, and content generation protocols. - Adds a workflow for online fiction creation: golden three chapters generator, outline design, platform adaptation guide, and Zhihu-style writing. - Implements quality control tools with quality standards, editing techniques, and AI trace removal. - Supports automatic generation of online fiction golden three chapters. - Provides multiplaform adaptation (Zhihu/Qidian/Jinjiang). - Includes AI text cleansing and trace removal functionalities.
● 无害
安装命令
点击复制官方npx clawhub@latest install wanxiang-scroll-creation
镜像加速npx clawhub@latest install wanxiang-scroll-creation --registry https://cn.longxiaskill.com镜像同步中