免费版
v1.3.0Convert any content into platform-tailored posts for Twitter, LinkedIn, WeChat, Zhihu, Xiaohongshu, Douyin, and Toutiao in one step.
⭐ 1· 125·0 current·0 all-time
byMrReiyWsL@a799549967-lang
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (multi-platform content adaptor) aligns with the instructions and included marketing/usage files: it reads user content (text/file/URL) and generates platform-specific rewrites. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
SKILL.md instructs the agent to read user-supplied text, uploaded files, or a URL and to produce multiple platform-native versions in a single response — this is appropriate for the stated purpose. Minor note: it references contacting a Telegram handle and a ClawHub page for support/payment; the skill does not instruct automatic external transmission of user content, but users should avoid pasting sensitive data if they plan to send it to third parties.
Install Mechanism
No install spec, no code files to write or execute — lowest-risk instruction-only skill.
Credentials
The skill mentions support for external AI providers (阿里云百炼, DeepSeek) and says '录入 Key 就行' in the FAQ, but it does not declare required env vars or request keys itself. If you configure external model keys in OpenClaw, ensure those keys stay in the platform and are not shared with the skill author or external contacts.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent presence or permissions to modify other skills or system settings.
Assessment
This skill appears coherent and low-risk because it’s instruction-only and requests no credentials. Before installing or using it: 1) Do not paste personal, financial, or secret information into content you send to the skill (or any third-party support channels). 2) If you must configure external AI provider keys in OpenClaw, keep them in the OpenClaw settings and don’t hand them to the skill author or a Telegram contact. 3) Be cautious about paying or sharing account details via the referenced Telegram handle (@ShuaigeSkillBot) — verify the service independently. 4) If you need stronger assurance, ask the publisher for a homepage/repository or audit trail for the prompt-engineering rules they use.Like a lobster shell, security has layers — review code before you run it.
latestvk975zbsk018f4ydwc5n1kmj76x83trdn
License
MIT-0
Free to use, modify, and redistribute. No attribution required.