小红书定制化创作
v1.0.0小红书定制化创作技能 - 固定操作流程，提高发布成功率
⭐ 1· 133·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (小红书定制化创作) match the SKILL.md steps for opening the creator site, choosing publish mode, pasting copy, generating images, and publishing. There are no unrelated environment variables, binaries, or install steps requested.
Instruction Scope
Instructions direct the agent to open specific 小红书 creator URLs and interact with the web UI (paste text, trigger image generation, click publish). This is within scope. One minor gap: the workflow says '记录到飞书"已发布内容库"' (record to Feishu) but provides no details or declared credentials for Feishu—implementation would rely on the agent's existing 'message' tool or external integration.
Install Mechanism
No install spec and no code files — instruction-only skill with no downloads or filesystem changes, which is the lowest-risk install profile.
Credentials
The skill declares no required environment variables or credentials. It does assume a logged-in browser session for 小红书 and uses 'browser' and 'message' tools; that is proportionate. Note: the implicit expectation of a Feishu recording mechanism is not declared as a required credential.
Persistence & Privilege
always is false and the skill is user-invocable (normal). The skill does not request persistent system privileges or to modify other skills/configurations.
Assessment
This skill is an instruction-only helper for publishing to 小红书 and appears coherent and low-risk. Before installing or using it: (1) ensure your browser is intentionally logged into the correct 小红书 account (the skill uses the existing session — cookies/sessions could be used to publish); (2) be aware the skill assumes the agent can control a browser tool to click and submit content — require explicit confirmation before allowing automatic publishes if you don't want posts made without review; (3) the SKILL.md mentions recording to Feishu but doesn't declare credentials—if you want that feature, verify how the agent will authenticate to Feishu and whether you need to provide a token or allow the agent to send messages; (4) avoid including highly sensitive data in the post content since it will be sent to the external site; (5) if you prefer, restrict the agent from autonomous invocation so it only runs when you explicitly call it.Like a lobster shell, security has layers — review code before you run it.
latestvk97bzkk3hhvy0e11a6yyzmjbhn83jh1a
License
MIT-0
Free to use, modify, and redistribute. No attribution required.