← 返回 Skills 市场
88
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install viral-video-predictor
功能描述
输入短视频脚本,自动预测爆款概率(钩子分析/节奏/情绪曲线/优化建议)
安全使用建议
This skill appears coherent and self-contained: it analyzes text scripts and returns scores and suggestions without requesting credentials or installing external code. Before installing or using it in production you may want to: 1) quickly search the index.js file (or the package) for suspicious calls such as network libraries (fetch/axios/http/https), child_process/exec, eval/new Function, or process.env to confirm there are no hidden external communications or secret access; 2) run the code locally on non-sensitive sample scripts to verify outputs; and 3) prefer running it in an isolated environment if you plan to feed sensitive or proprietary scripts. If you want, I can scan the provided index.js for specific patterns (network calls, exec/eval, environment access) and report findings.
功能分析
Type: OpenClaw Skill
Name: viral-video-predictor
Version: 1.0.0
The skill bundle is a legitimate tool for analyzing short video scripts for viral potential. The code in index.js performs rule-based text analysis (hook detection, pacing, and keyword checking) entirely locally without any network requests, file system access, or suspicious execution patterns.
能力评估
Purpose & Capability
Name/description (viral-video prediction and optimization) match the manifest, SKILL.md, README, and index.js functionality. Inputs/outputs declared in manifest correspond to the analysis functions implemented in index.js (hook/pacing/emotion/score/suggestions). No unrelated services, binaries, or credentials are requested.
Instruction Scope
SKILL.md instructs the agent only to accept a script and run analyses (hook detection, pacing, emotion curve, platform compliance, scoring, optimization). The included index.js implements those steps and does not instruct reading unrelated system files, environment variables, or sending data to external endpoints (no endpoints referenced in visible code).
Install Mechanism
No install spec is provided and no external packages or downloads are required. This is an instruction + single-file implementation, so nothing new is written to disk by an installer.
Credentials
The skill declares no required environment variables, credentials, or config paths. The code shown does not access process.env or other secret-bearing locations. The requested permissions are proportionate to the stated functionality.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request persistent presence or modify other skills/configuration. Autonomous invocation remains platform default but is not combined with other elevated privileges here.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install viral-video-predictor - 安装完成后,直接呼叫该 Skill 的名称或使用
/viral-video-predictor触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
付费技能首发 - 爆款预测
元数据
常见问题
短视频爆款预测脚本 是什么?
输入短视频脚本,自动预测爆款概率(钩子分析/节奏/情绪曲线/优化建议). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 88 次。
如何安装 短视频爆款预测脚本?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install viral-video-predictor」即可一键安装,无需额外配置。
短视频爆款预测脚本 是免费的吗?
是的,短视频爆款预测脚本 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
短视频爆款预测脚本 支持哪些平台?
短视频爆款预测脚本 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 短视频爆款预测脚本?
由 Amaxclaw(@amaxclaw)开发并维护,当前版本 v1.0.0。
推荐 Skills