ClawHub

Creator Course Outline

v1.0.0

为创作者课程生成模块结构、单元目标、作业与里程碑。；use for course, creator, curriculum workflows；do not use for 承诺学员结果, 替代正式教学设计评审.

⭐ 1· 193·0 current·0 all-time
byvx：17605205782@52yuanchangxing
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (course/creator curriculum work) align with the included assets: a template, spec.json, examples, and a Python script that generates structured Markdown reports. Requiring python3 only is proportional to the functionality.
ℹ
Instruction Scope
SKILL.md limits behavior to producing draft outputs and instructs use of the local script only when shell/exec is available. The script by default uses the 'structured_brief' mode (driven by resources/spec.json) which only reads the provided input file and template. However, the included run.py also contains directory- and pattern-audit functions and will read arbitrary files if invoked with a directory or CSV input—so executing the script against broad filesystem paths could expose local content. The SKILL.md does not instruct scanning arbitrary system paths, but the capability is present in the script.
✓
Install Mechanism
No install spec; instruction-only skill with an included Python script. No remote downloads or package installs are performed. This is low-risk from an install perspective.
✓
Credentials
No required environment variables, no credentials, and only python3 is declared. That is proportionate to a local content/template-driven authoring tool.
✓
Persistence & Privilege
always is false and the skill does not request persistent platform privileges. The script can write an output file if asked, but installation does not modify other skills or global agent configuration.
Assessment
This skill appears to do what it claims: generate course-outline drafts using local templates and a Python helper script. Before running the script, review scripts/run.py yourself. If you run it, provide only safe input (e.g., the example input file or a dedicated working directory) and avoid passing system-wide paths (/, /home, or other directories containing secrets). Use --dry-run or capture stdout instead of letting the skill write into system locations. If you are uncomfortable with an agent invoking the script autonomously, disable autonomous invocation or require explicit confirmation before execution.

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

latestvk970gbqfjccrdn6797v9fjx5cn830188

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

🎓 Clawdis
OSmacOS · Linux · Windows
Binspython3

Comments