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

content-product-analyzer内容产品分析器

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

4,162

周安装

170

GitHub Stars

公开资料未说明

下载量

1,346
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:content-product-analyzer(内容产品分析器)
来源仓库:https://github.com/guoxinling/content-product-analyzer
安装命令:
openclaw skills install content-product-analyzer
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 content-product-analyzer

简介

根据产品页面、截图或文本生成商业分析与受众洞察报告。

  • 支持推断用户画像、竞品优势与市场需求痛点。
  • 适用于产品经理、创业者与市场研究人员。content-product-analyzer 属于效率类 Skill,可作为该场景下的辅助能力补充。
  • 帮助快速理解产品核心价值与目标人群特征。
  • 输出包含策略建议与优化方向的完整拆解文档。

SKILL.md

name
content-product-analyzer
description
produce a commercial teardown of a post, creator profile, product page, landing page, or app page from urls, screenshots, or pasted text. use to infer audience, positioning, growth mechanics, monetization signals, credibility, sentiment, and opportunities to borrow or avoid. supports multi-link bundles and competitor comparison; separate observed facts from supported inferences and unknowns; use mixed-mode web verification when public urls are provided or freshness matters and cite sources.

Content Product Analyzer

Turn raw content or product inputs into a structured commercial teardown. Focus on business value, audience, positioning, growth mechanics, credibility, sentiment, and opportunities to borrow or avoid.

Inputs supported

  • Single object: one post / creator profile / product page / landing page / app page
  • Bundle: multiple URLs / screenshots / text snippets for one product or campaign
  • Competitor set: multiple products/pages to compare side-by-side

Evidence modes (must choose explicitly)

1) User-provided only - Use only what the user pasted or what is visible in screenshots. - Do not claim external facts.

2) Mixed mode - Allowed when: the user provides public URLs OR the user asks for “latest/pricing/reviews/current ranking” OR recency clearly matters. - Verify and enrich with public sources. - Prefer: official site → original platform page → pricing/docs → reputable review sources. - Cite factual claims from public sources.

Non-negotiable rules

  • Start from evidence, not vibes.
  • Distinguish clearly between:

- Observed facts (directly visible/quoted) - Supported inferences (reasonable, evidence-linked) - Unknowns (explicitly list)

  • Prefer commercial and strategic analysis over technical implementation detail.
  • For screenshots: only claim what is visible or directly implied.
  • Do not overstate follower psychology, revenue, conversion rates, or traction when not evidenced.
  • When input is sparse: state low confidence and keep recommendations lightweight.

Workflow

1) Identify object type(s): post / creator profile / product page / landing page / app page / bundle. 2) Pick evidence mode: user-only vs mixed-mode. 3) Extract observable facts first. 4) Infer audience, positioning, growth/virality mechanics, monetization, sentiment. 5) Separate confirmed facts vs inferences vs unknowns. 6) Produce BOTH outputs (in order): - Structured summary - Detailed teardown 7) End with concrete advice tailored to: - creator (content packaging, hooks, formats, audience resonance) - indie builder (positioning, MVP, pricing, distribution, differentiation)

Analysis lenses (pick what’s relevant; don’t force all)

For creators / posts / social profiles

Assess:

  • Content topic and promise
  • Hook structure & attention mechanics
  • Tone/persona & stylistic signatures
  • Engagement structure (replies/saves/reposts/CTAs)
  • Likely audience and motivations
  • Credibility signals & weak signals
  • Commercial intent (sponsorship, lead-gen, affiliate, community funnel, product funnel)
  • What is repeatable vs personality-dependent

For products / landing pages / app pages

Assess:

  • Core problem and target user
  • Positioning & category framing
  • Value proposition clarity
  • Feature packaging vs differentiation
  • Pricing/monetization signals
  • Social proof, trust, risk
  • Marketability (share/buy/ignore triggers)
  • Objections & opportunity space for an indie builder

Required output format

1) Structured summary (compact)

Use these fields when applicable:

  • 对象类型
  • 一句话定位
  • 目标用户
  • 用户想要的结果
  • 内容/产品风格特征
  • 增长或传播机制
  • 商业模式/变现线索
  • 可信度信号
  • 风险或不足
  • 可借鉴点
  • 建议动作
  • 结论置信度: 高 / 中 / 低

2) Detailed teardown (long-form)

Use this default structure (adapt as needed):

分析标题

核心信息提炼

Only the highest-signal facts.

结构化拆解

Topic/audience/style/mechanics/commercial logic.

用户与市场判断

Who it is for, what desire/pain it maps to, market signal.

商业价值与增长判断

Monetization clues, retention/funnel logic, why it may or may not work.

风险、槽点与反证

What’s missing, inflated, weak, or misleading.

可复用方法

What a creator/indie builder can actually borrow.

建议

Tailor advice:

  • For creators: topic ideas, hook patterns, audience angles, content directions.
  • For indie builders: positioning, MVP, monetization, differentiation, GTM.

一句话结论

Sharp final judgment.

Competitor comparison add-on (when user provides 2+ competitors)

If the user asks “竞品对比 / compare / vs”, append this section after the teardown:

竞品对比矩阵

Create a markdown table comparing:

  • Positioning sentence
  • Target user / job-to-be-done
  • Key differentiators
  • Pricing / plan structure signals
  • Trust & proof
  • Distribution channel guesses
  • Likely wedge (why users start)
  • Likely lock-in (why users stay)
  • Risks / gaps

对比结论与切入策略

  • What is easiest to copy vs defensible
  • Underserved segment(s)
  • Recommended wedge for the user
  • 3–7 action items (sequenced)

Quality bar

A good answer should:

  • Read like a sharp operator, not a generic summarizer
  • Contain explicit judgment, not just description
  • Surface upside AND failure modes
  • Produce at least 3 concrete suggestions when enough evidence exists
  • Be honest about uncertainty

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

97.94%
按下载量换算1,318

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