Novel Generator Skip
v1.0.0根据用户提供的内容方向自动生成提示词并创作爽文小说。适用场景：(1) 用户提供小说方向/题材/关键词，(2) 需要生成章节连贯的长篇爽文，(3) 需要维护角色、地点、情节的连续性，(4) 需要为关键情节生成图解，(5) 需要记录生成失败场景以优化后续创作。支持都市、修仙、玄幻、重生、系统流等多种题材。Use wh...
⭐ 0· 69·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (novel/爽文 generator) align with the actual behavior: generating prompts, outlines, chapters and maintaining local memory files (.learnings/) and output/ files. All declared capabilities are proportional to a writing tool.
Instruction Scope
SKILL.md explicitly instructs the agent to read/write files under the skill workspace (.learnings/* and output/*) before/after generating chapters, and to generate Mermaid or image-based diagrams for key scenes. It does not instruct reading unrelated system files, environment variables, or sending data to external endpoints. The requirement for file read/write permission is declared in the SKILL.md compatibility note and matches the instructions.
Install Mechanism
There is no install spec (instruction-only) and no downloads. The only code file is a small init-novel.sh script that initializes/clears local files. No external URLs, package installs, or archive extraction are used.
Credentials
The skill requires no environment variables, credentials, or config paths. Its file I/O is limited to the skill directory (.learnings/ and output/), which is consistent with its purpose.
Persistence & Privilege
The skill is not always-enabled and does not require elevated privileges. It persistently stores story state in .learnings/ (expected for continuity). Note: the init script supports a --clean option that deletes output/*.md and rewrites .learnings/* templates — this is normal but destructive to existing generated files if misused.
Assessment
This skill appears to do what it says: generate novels and keep local story memory in .learnings/. Before installing: (1) be aware it needs permission to read/write files in its skill folder (it will create/modify .learnings/ and output/); (2) back up any existing output/ or .learnings/ files before using the --clean init option since that will delete/overwrite files; (3) the skill does not request credentials or download external code, but if you plan to enable automatic diagram/image generation, confirm where images would be sent (the skill suggests using 'image generation tools' but does not itself call external endpoints); (4) if you run agents that can invoke skills autonomously, understand the agent will be able to read and update the local memory files — keep any sensitive content out of those files. Overall this skill is coherent for its stated purpose; review the init script and workflows and run it in a sandboxed project directory if you want to limit file writes.Like a lobster shell, security has layers — review code before you run it.
latestvk978pydfjzprfdbb40q6tbhjcx84bqaw
License
MIT-0
Free to use, modify, and redistribute. No attribution required.