Social Commerce Content Planner

v1.0.0

帮助社交电商运营系统规划内容主题、日历、直播脚本及短视频文案模板,提升选题与转化效果。

0· 49·0 current·0 all-time
byhaidong@harrylabsj
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 (社交电商内容规划) match the included files and runtime behavior: generation of topics, calendars, scripts, and checklists. The skill does not request unrelated credentials or binaries.
Instruction Scope
SKILL.md explicitly states '不接入实时API' and the handler.py implements only local, deterministic content generation (no network, no file reads, no env var access). Minor correctness note: the calendar generation uses a hard-coded year (2026), which affects date outputs but is not a security issue.
Install Mechanism
No install spec; the skill is instruction-only with included Python code. No downloads or external package installs are performed. Risk is low because only standard library is used and no archives/remote URLs are fetched.
Credentials
The skill declares no required environment variables, no primary credential, and the code does not access os.environ or secrets. The requested environment access is proportional (none) to the stated functionality.
Persistence & Privilege
always:false (default) and disable-model-invocation:false (normal). The skill does not modify other skills or global agent settings. Autonomous invocation is allowed by default but, given the local-only behavior, presents low risk.
Assessment
This skill appears coherent and low-risk: it runs locally, uses only the Python standard library, and asks for no credentials. Before installing, you may (1) run the bundled tests (python3 tests/test_handler.py) to verify behavior, (2) inspect handler.py yourself (it's short and readable) to confirm there are no network calls or hidden endpoints, (3) be aware the calendar uses a hard-coded year (2026) so date outputs may need updating, and (4) consider whether you want the agent to be allowed to call the skill autonomously — if not, disable autonomous invocation in the agent settings. Also remember to review generated marketing copy for platform policy and legal compliance before publishing.

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

latestvk97ez10apjyhvrkn1xszygkha584rtze

License

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

Comments