ClawHub

视频封标诊断

v0.1.0

Video packaging diagnosis for Chinese short-form creators. Use when Codex needs to diagnose why a video's title, cover, opening hook, or payoff structure is...

⭐ 0· 100·0 current·0 all-time
by@cellinlab

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for cellinlab/cell-video-packaging-diagnosis.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "视频封标诊断" (cellinlab/cell-video-packaging-diagnosis) from ClawHub.
Skill page: https://clawhub.ai/cellinlab/cell-video-packaging-diagnosis
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install cell-video-packaging-diagnosis

ClawHub CLI

Package manager switcher

npx clawhub@latest install cell-video-packaging-diagnosis
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name, description, and included reference assets (headlines, cover strategies, payoff structure, diagnosis template) align with a video packaging diagnosis task. No unrelated binaries, environment variables, or external services are required.
✓
Instruction Scope
SKILL.md confines the agent to diagnosing user-provided title/cover/opening/outline and using the local reference files. It does not instruct the agent to read arbitrary system files, call external endpoints, or collect unrelated data.
✓
Install Mechanism
No install spec or code is present; this is an instruction-only skill so nothing is written to disk or downloaded during install.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. Requested access is minimal and proportional to the stated purpose.
✓
Persistence & Privilege
always is false and the skill uses normal model-invocation behavior. It does not request persistent system-level privileges or modify other skills' configurations.
Assessment
This is an instruction-only, self-contained diagnostic aid—low technical risk. Before using, remember you will be sharing titles, cover descriptions/images, and script/outlines with the agent; avoid sending private or sensitive data. If you prefer, restrict autonomous invocation in your agent settings so the skill runs only when you call it.

Like a lobster shell, security has layers — review code before you run it.

latestvk9784zeyhm6atdprerr1afsh5984m22t
100downloads
0stars
1versions
Updated 2w ago
v0.1.0
MIT-0
@cellinlab
latest
Download

Video Packaging Diagnosis

Overview

这个 Skill 专门处理视频的：

  • 标题
  • 封面
  • 开头承接
  • promise 与兑现

它不是通用文案 Skill，也不是完整脚本 Skill。

Quick Start

  1. 先判断问题更像：标题、封面、开头，还是兑现关系。
  2. 先找一个最限制点击或留存的单点。
  3. 标题、封面、开头必须围绕同一个 promise。
  4. 给优化方案时，至少保留 2 条不同方向。

Default Contract

默认采用以下约定，除非用户另有说明：

  • 输出语言：中文
  • 先诊断，再给改法
  • 先看 promise 是否成立，再谈词句雕花
  • 如果平台没说明，按中文短视频语境处理

Workflow

Step 1: Scope the Material

用户可提供：

  • 标题
  • 封面图描述或图片
  • 开头脚本
  • 视频大纲

Step 2: Route the Diagnosis

场景按需读取
标题诊断references/contrast-headlines.md
封面诊断references/cover-strategies.md
开头 / 承接诊断references/payoff-structure.md
整体封标诊断三个文件都读

Step 3: Name the Real Bottleneck

常见瓶颈：

  • 标题没有对比和画面感
  • 封面没有视觉聚焦
  • 开头没有立刻确认标题 promise
  • 中段平，结尾又没有兑现

Step 4: Return Targeted Fixes

默认交付：

  • 一句话诊断
  • 主要问题 1-3 条
  • 2-3 个标题方向
  • 封面策略建议
  • 开头承接修正建议

Hard Rules

Do not:

  • 只改标题，不看封面和开头
  • 把所有问题都归因成“不够炸”
  • 没诊断就直接给一个答案

Always:

  • 把问题落到点击或留存
  • 检查标题、封面、开头是否在说同一件事
  • 给至少两种可比较方案

Resource Map

Comments

Loading comments...