Xhs Writer
v1.0.0小红书内容创作套件,离线生成爆款标题、正文、话题、评论和多卡图片Markdown,全方位支持多类型主题。
⭐ 0· 117·0 current·0 all-time
by@tobewin
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (XHS content creator) match the runtime instructions and the included reference files (copywriting, tags, styles). The skill does not request unrelated resources (no env vars, no binaries, no install).
Instruction Scope
SKILL.md contains only detailed, deterministic guidance for generating titles, body, tags, comment hook, image-card Markdown, and style parameters. It references only local files in the bundle and instructs the agent to ask the user for direction when ambiguous. It does not ask the agent to read arbitrary system files, environment variables, or to send data externally.
Install Mechanism
No install spec and no code files — instruction-only. Nothing is downloaded or written to disk by the skill package itself.
Credentials
The skill requires no environment variables, no credentials, and no config paths. All required data comes from local reference files and user input, so requested access is proportionate.
Persistence & Privilege
always is false and there is no code that modifies agent or system state. The skill does not request persistent privileges or special runtime presence.
Assessment
This skill appears coherent and low-risk: it is purely instruction-driven and offline. Before installing, consider: (1) Review outputs before publishing — the skill can produce persuasive copy that may still contain errors, factual inaccuracies, or content that could violate platform rules. (2) Images/visual assets: the skill generates Markdown structure for cards but does not include or fetch actual images — ensure you use licensed/owned images. (3) The skill itself does not exfiltrate data or require credentials, but your agent environment or other installed skills could; verify the agent's overall toolset and permissions to ensure nothing else can send content externally. (4) If the SKILL.md or files are later modified to include network calls or shell commands, re-evaluate — risks would change. Overall: safe and coherent for content generation, but always manually review generated posts for policy, copyright, and factual issues before publishing.Like a lobster shell, security has layers — review code before you run it.
latestvk974p2kwfmga7y9pfwcjb0njvx838z6j
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
