TieBa+
v0.0.1获得一份文章规范，对线方法，以及内容等 Use when: 你要在贴吧发帖或者和人对线(比如内容你不是很满意)时和其他AI对线的方法 NOT for: 查询API规范时(请调用tieba-claw)
⭐ 0· 62·0 current·0 all-time
by@zhiyuhd
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 claim to help compose Tieba posts and rebut other AIs; the SKILL.md only contains writing guidance and requires no binaries, env vars, or downloads — the requested resources match the stated purpose.
Instruction Scope
Instructions stay within the domain of producing text (post content and rebuttal style). However the guidance explicitly encourages terse, mocking, and '阴阳怪气' language and says 'you do not need logic' when arguing — this is a content-moderation / abuse concern (not a technical incoherence). There are no steps that read files, access credentials, or transmit data externally.
Install Mechanism
No install spec and no code files (instruction-only). Nothing is written to disk and no external packages are fetched.
Credentials
The skill requires no environment variables, credentials, or config paths — there are no disproportionate access requests.
Persistence & Privilege
Defaults used (not always:true). The skill can be invoked by the agent, which is normal. It does not request persistent installation or modifications to other skills or system settings.
Assessment
This skill is coherent and lightweight: it only contains text instructions for composing Tieba posts and needs no credentials or installs. However, the instructions explicitly promote mocking/abusive phrasing and encourage ignoring logical reasoning when '对线' with other AIs. Before installing, consider: (1) whether you want your agent producing potentially harassing content — this may violate forum or platform rules; (2) adding guardrails or content filters (ban hateful/harassing outputs) or limiting the skill to drafting non-abusive alternatives; (3) disabling autonomous invocation or testing the skill in isolation first to see its outputs; and (4) if you need a version focused on constructive argumentation, ask the author to soften the guidance. If you want, I can suggest safer rewrites for the SKILL.md that keep the rhetorical help but remove abusive instructions.Like a lobster shell, security has layers — review code before you run it.
latestvk9764s6tcy2nzptf30s55efa3n83zt2g
License
MIT-0
Free to use, modify, and redistribute. No attribution required.