📦 Anti-Slop — 反垃圾检测
v0.1.0一键扫描文本、代码或生成内容，快速识别“AI 垃圾”、低质重复与抄袭痕迹，给出原创度评分与改进建议，让输出更专业可信。
0· 82·0 当前·0 累计
by 下载技能包
最后更新
2026/4/11
安全扫描
OpenClaw
安全
high confidenceThe skill is instruction-only and its requested actions (inspect text for low-information content, verify claims with evidence, avoid filler) match its stated purpose; it asks for no credentials or installs and is internally coherent.
评估建议
This skill is an instruction-only reviewer for AI 'slop' and appears coherent. Before installing or enabling it, confirm whether you want the agent to be able to access the repository, files, or run CLI tools (the SKILL.md expects the agent to show file:line evidence and may reference commands like `gh pr view` and test output). The skill itself asks for no secrets or installs, but its usefulness depends on the agent environment having permission to read project files and run tools. If you have ...详细分析 ▾
✓ 用途与能力
Name/description are an editorial quality-check for AI output and the SKILL.md contains step-by-step review criteria and verification checks that align with that purpose. Nothing in the skill asks for unrelated services or credentials.
ℹ 指令范围
The instructions explicitly require reading text, locating file:line evidence, and verifying claimed actions (e.g., show test output, confirm a PR exists using `gh pr view`). This is consistent with a content-review skill, but it implicitly assumes the agent has access to the repository/files and CLI tools needed to prove claims. The SKILL.md does not attempt to access unrelated system paths or external endpoints.
✓ 安装机制
No install spec and no code files — instruction-only. This is low-risk; nothing will be downloaded or written to disk by the skill itself.
✓ 凭证需求
The skill requests no environment variables, credentials, or config paths. The verification steps mention running commands and reading files, which are appropriate for the stated task, but those runtime capabilities come from the agent environment and are not requested by the skill.
✓ 持久化与权限
The skill is not always-on and uses default autonomous-invocation settings. It does not request persistent presence, modify other skills, or ask to alter agent-wide config.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv0.1.02026/4/11
Initial release. Detect AI slop, ensure originality and information density.
● 无害
安装命令
点击复制官方npx clawhub@latest install antislop
镜像加速npx clawhub@latest install antislop --registry https://cn.longxiaskill.com