Outline Generator

v1.0.2

小说大纲生成器。根据小说类型、主题、字数生成 15 节拍结构化大纲。Use when: Architect 代理在 Phase 1 需要生成故事大纲、规划 15 节拍结构、创建卷章框架。

0· 71·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (15-beat novel outline generator) match its artifacts: a Python script, a types.yml config, and docs. Required env, binaries, and config paths are minimal and appropriate for the stated purpose.
Instruction Scope
SKILL.md only tells the agent to run the included Python script and optionally edit configs; the script reads the local configs/types.yml and outputs an outline file. There are no instructions to read unrelated system files, collect credentials, or transmit data externally.
Install Mechanism
No install spec is provided (instruction-only skill); dependencies are standard PyPI packages listed in requirements.txt (pyyaml, rich). This is proportionate for a CLI Python tool and poses normal installation risk (pip install).
Credentials
The skill declares no required environment variables, no credentials, and no config paths outside its skill folder. That is appropriate for a local outline generator.
Persistence & Privilege
always is false and the skill does not request persistent or privileged system presence. It writes output files (outline.md) within the workspace as expected for its function.
Assessment
This skill appears coherent and limited to generating novel outlines using the included Python script and local config. Before installing or running it, consider: 1) Inspect the full scripts/generate_outline.py for any network, subprocess, or os.environ usage (search for imports or calls to requests, urllib, socket, subprocess, os.environ, open('/etc') etc.). 2) Run it in a sandbox or virtualenv and pin/install dependencies from PyPI (preferably in an isolated environment). 3) If you will run it on sensitive hosts, confirm it only reads/writes files in the skill directory and doesn't call external endpoints. If you want, I can grep the full script for network, subprocess, or environment-access patterns and report any matches.

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

latestvk97c06ay2wna6fj3shapvjf0b9841994

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments