AI写作提示词与公众号爆款文案指南
v1.0.0Use when helping user create writing prompts, determine public account (公众号) track, generate article drafts, rewrite content with human touch, or create clic...
⭐ 0· 16·0 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 and description match the SKILL.md instructions: the file is a comprehensive guide for building prompts, choosing a public-account track, drafting and rewriting articles, de-AI-ifying copy, and creating titles/images. There are no unexpected binaries, env vars, installs, or config paths requested — everything the skill needs is purely procedural text, which is proportionate to its stated purpose.
Instruction Scope
The instructions are narrowly focused on content creation workflows, prompt templates, and question flows. However, several instructions encourage wholesale extraction and verbatim restoration of third-party works (e.g., '100%纯还原作品完整文案') and direct output of full copied or lightly-rewritten text without explanatory steps. That raises legal and ethical concerns (copyright/plagiarism) and operational risk if the agent is used to fetch or republish others' content. The SKILL.md does not instruct reading system files or unrelated env vars, but it does remove intermediate review steps ('直接输出... 无需说明'), increasing the chance of accidental publication of copyrighted material.
Install Mechanism
Instruction-only skill with no install spec and no code files. This is the lowest-risk install posture — nothing will be written to disk or executed automatically by an installer.
Credentials
The skill declares no required environment variables, secrets, or config paths. There is no disproportionate credential or filesystem access requested.
Persistence & Privilege
Flags: always is false and there is no install-time persistence. The skill does not request elevated or permanent presence and does not modify other skills or agent settings. (Agent-autonomous invocation defaults are unchanged and not a concern by themselves.)
Assessment
This skill is coherent for helping create prompts and rewrite articles, but be aware of content-legal risks: several prompts instruct the agent to '100% restore' or verbatim extract other creators' works and to output full copies or lightly rewritten versions without explanation. Before using: (1) avoid instructing the agent to scrape or republish third-party content without permission; prefer user-provided source text or public-domain/licensed content; (2) add explicit constraints to prevent wholesale copying (require citation, transformation, or summary instead of full reproduction); (3) require a human review step before publishing; (4) check platform and copyright policies where you publish; and (5) be cautious about using the external tool link (创作罐头) — verify its terms and whether it requires credentials. These are legal/ethical risks, not signs of incoherence in the skill's design.Like a lobster shell, security has layers — review code before you run it.
latestvk9732yxzg9pajs14hwdvqcepgs84pzxk
License
MIT-0
Free to use, modify, and redistribute. No attribution required.