Token导航 LogoToken导航TokenDH.com
开发只读clawhub未标认证来源可访问clear审计通过

creator-content-scorecard创作者内容记分卡

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

7,244

周安装

308

GitHub Stars

公开资料未说明

下载量

2,538
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:creator-content-scorecard(创作者内容记分卡)
来源仓库:https://github.com/leooooooow/creator-content-scorecard
安装命令:
openclaw skills install creator-content-scorecard
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install creator-content-scorecard

简介

通过对关键元素进行评分并提供清晰、优先的反馈来评估电子商务或联属网络营销的创作者内容,以提高转化率和效率。

SKILL.md

Creator Content Scorecard

Score a creator content draft, published post, or content concept so operators can judge quality, conversion fitness, and what to improve before the next iteration.

Use this skill when a user wants a structured evaluation of creator-led content for ecommerce, affiliate, or TikTok Shop workflows. It is useful for turning subjective reactions like “this feels weak” into a practical scorecard with diagnosis and next steps.

Solves

Content reviews often fail because feedback stays vague:

  • “The hook is weak” but nobody explains why
  • “It feels off-brand” without clear criteria
  • “It may not convert” without identifying the missing proof, offer, or CTA
  • different reviewers focus on different things, so quality is inconsistent

Goal: Turn creator content into a score-based review with clear reasons, risks, and highest-impact fixes.

Use when

  • Reviewing a creator script, draft, raw clip, caption, or published post
  • Comparing multiple content options before approval
  • Auditing why content feels weak even if it looks polished
  • Giving creators actionable feedback instead of taste-based comments
  • Building a repeatable QC process for creator or affiliate content

Do not use when

  • The user needs full attribution analysis or media-buying performance modeling
  • There is no real content artifact or summary to evaluate
  • The task is legal/compliance review only

Inputs

  • Content asset, transcript, script, caption, or summary
  • Product and offer details
  • Target audience
  • Channel and format
  • Goal of the content (click, sale, add to cart, lead, engagement)
  • Key proof points or claims
  • CTA expectation
  • Known constraints (brand, compliance, creator style)

Workflow

  1. Restate what the content is trying to do.
  2. Score the content across the most important dimensions.
  3. Explain what is helping and hurting performance.
  4. Identify the 3 biggest gaps limiting conversion or retention.
  5. Recommend concrete revisions in priority order.
  6. End with a go / revise / reject recommendation.

Scoring dimensions

Use a 1-5 score for each:

  • Hook strength
  • Audience relevance
  • Problem-solution clarity
  • Product demonstration / specificity
  • Proof / credibility
  • Offer clarity
  • CTA strength
  • Native creator feel
  • Conversion readiness

Output

Return:

  1. Content summary
  2. Score table or bullet score list
  3. What is working
  4. Biggest gaps
  5. Priority fixes
  6. Final recommendation: go / revise / reject

Quality bar

  • Specific to creator commerce and conversion logic
  • Distinguish engagement strength from sales strength
  • Prioritize feedback by likely business impact
  • Avoid fake precision and generic creative-writing notes
  • Make the feedback usable by operators and creators immediately

Resource

See references/output-template.md.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

76.68%
按下载量换算1,946

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills